[Refactor] Update dev scripts to be compatible with selfsup tasks. (#1412)
* [Refactor] Update dev scripts to be compatible with selfsup tasks. * Fix some missing fields in config files. * Set maximum number of gpus for local training. * Update README files * Update according to comments.pull/1445/head
Ma Zerun
GitHub
parent
4f5b38f225
commit
6cedce234e
|
|
@ -1,25 +1,24 @@
|
|||
import logging
|
||||
import re
|
||||
import sys
|
||||
import tempfile
|
||||
from argparse import ArgumentParser
|
||||
from collections import OrderedDict
|
||||
from pathlib import Path
|
||||
from time import time
|
||||
from time import perf_counter
|
||||
from unittest.mock import Mock
|
||||
|
||||
import mmcv
|
||||
import numpy as np
|
||||
import torch
|
||||
from mmengine import Config, DictAction, MMLogger
|
||||
from mmengine import DictAction, MMLogger
|
||||
from mmengine.dataset import Compose, default_collate
|
||||
from mmengine.device import get_device
|
||||
from mmengine.fileio import FileClient
|
||||
from mmengine.model.utils import revert_sync_batchnorm
|
||||
from mmengine.runner import Runner, load_checkpoint
|
||||
from modelindex.load_model_index import load
|
||||
from rich.console import Console
|
||||
from rich.table import Table
|
||||
from utils import substitute_weights
|
||||
|
||||
from mmpretrain.apis import get_model
|
||||
from mmpretrain.apis import ModelHub, get_model, list_models
|
||||
from mmpretrain.datasets import CIFAR10, CIFAR100, ImageNet
|
||||
from mmpretrain.utils import register_all_modules
|
||||
from mmpretrain.visualization import UniversalVisualizer
|
||||
|
|
@ -33,6 +32,12 @@ classes_map = {
|
|||
'CIFAR-100': CIFAR100.CLASSES,
|
||||
}
|
||||
|
||||
logger = MMLogger.get_instance('validation', logger_name='mmpretrain')
|
||||
logger.handlers[0].stream = sys.stderr
|
||||
logger.addHandler(logging.FileHandler('benchmark_valid.log', mode='w'))
|
||||
# Force to use the logger in runners.
|
||||
Runner.build_logger = Mock(return_value=logger)
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = ArgumentParser(description='Valid all models in model-index.yml')
|
||||
|
|
@ -76,12 +81,12 @@ def parse_args():
|
|||
return args
|
||||
|
||||
|
||||
def inference(config_file, checkpoint, work_dir, args, exp_name):
|
||||
cfg = Config.fromfile(config_file)
|
||||
def inference(metainfo, checkpoint, work_dir, args, exp_name=None):
|
||||
cfg = metainfo.config
|
||||
cfg.work_dir = work_dir
|
||||
cfg.load_from = checkpoint
|
||||
cfg.log_level = 'WARN'
|
||||
cfg.experiment_name = exp_name
|
||||
cfg.experiment_name = exp_name or metainfo.name
|
||||
if args.cfg_options is not None:
|
||||
cfg.merge_from_dict(args.cfg_options)
|
||||
|
||||
|
|
@ -102,11 +107,11 @@ def inference(config_file, checkpoint, work_dir, args, exp_name):
|
|||
model.eval()
|
||||
forward = model.val_step
|
||||
else:
|
||||
# For configs only for get model.
|
||||
# For configs without data settings.
|
||||
model = get_model(cfg, device=get_device())
|
||||
model = revert_sync_batchnorm(model)
|
||||
model.eval()
|
||||
data = torch.empty(1, 3, 224, 224).to(model.data_preprocessor.device)
|
||||
data = torch.rand(1, 3, 224, 224).to(model.data_preprocessor.device)
|
||||
resolution = (224, 224)
|
||||
forward = model.extract_feat
|
||||
|
||||
|
|
@ -114,40 +119,38 @@ def inference(config_file, checkpoint, work_dir, args, exp_name):
|
|||
load_checkpoint(model, checkpoint, map_location='cpu')
|
||||
|
||||
# forward the model
|
||||
result = {'resolution': resolution}
|
||||
result = {'model': metainfo.name, 'resolution': resolution}
|
||||
with torch.no_grad():
|
||||
if args.inference_time:
|
||||
time_record = []
|
||||
forward(data) # warmup before profiling
|
||||
for _ in range(10):
|
||||
forward(data) # warmup before profiling
|
||||
torch.cuda.synchronize()
|
||||
start = time()
|
||||
start = perf_counter()
|
||||
forward(data)
|
||||
torch.cuda.synchronize()
|
||||
time_record.append((time() - start) / args.batch_size * 1000)
|
||||
time_record.append(
|
||||
(perf_counter() - start) / args.batch_size * 1000)
|
||||
result['time_mean'] = np.mean(time_record[1:-1])
|
||||
result['time_std'] = np.std(time_record[1:-1])
|
||||
else:
|
||||
forward(data)
|
||||
|
||||
result['model'] = config_file.stem
|
||||
|
||||
if args.flops:
|
||||
from fvcore.nn import FlopCountAnalysis, parameter_count
|
||||
from fvcore.nn.print_model_statistics import _format_size
|
||||
from mmengine.analysis import FlopAnalyzer, parameter_count
|
||||
from mmengine.analysis.print_helper import _format_size
|
||||
_format_size = _format_size if args.flops_str else lambda x: x
|
||||
with torch.no_grad():
|
||||
if hasattr(model, 'extract_feat'):
|
||||
model.forward = model.extract_feat
|
||||
model.to('cpu')
|
||||
inputs = (torch.randn((1, 3, *resolution)), )
|
||||
flops = _format_size(FlopCountAnalysis(model, inputs).total())
|
||||
params = _format_size(parameter_count(model)[''])
|
||||
result['flops'] = flops if args.flops_str else int(flops)
|
||||
result['params'] = params if args.flops_str else int(params)
|
||||
else:
|
||||
result['flops'] = ''
|
||||
result['params'] = ''
|
||||
model.forward = model.extract_feat
|
||||
model.to('cpu')
|
||||
inputs = (torch.randn((1, 3, *resolution)), )
|
||||
analyzer = FlopAnalyzer(model, inputs)
|
||||
# extract_feat only includes backbone
|
||||
analyzer._enable_warn_uncalled_mods = False
|
||||
flops = _format_size(analyzer.total())
|
||||
params = _format_size(parameter_count(model)[''])
|
||||
result['flops'] = flops if args.flops_str else int(flops)
|
||||
result['params'] = params if args.flops_str else int(params)
|
||||
|
||||
return result
|
||||
|
||||
|
|
@ -156,7 +159,7 @@ def show_summary(summary_data, args):
|
|||
table = Table(title='Validation Benchmark Regression Summary')
|
||||
table.add_column('Model')
|
||||
table.add_column('Validation')
|
||||
table.add_column('Resolution (h, w)')
|
||||
table.add_column('Resolution (h w)')
|
||||
if args.inference_time:
|
||||
table.add_column('Inference Time (std) (ms/im)')
|
||||
if args.flops:
|
||||
|
|
@ -179,82 +182,49 @@ def show_summary(summary_data, args):
|
|||
row.append(str(summary['params']))
|
||||
table.add_row(*row)
|
||||
|
||||
console.print(table)
|
||||
|
||||
|
||||
# Sample test whether the inference code is correct
|
||||
def main(args):
|
||||
register_all_modules()
|
||||
model_index_file = MMCLS_ROOT / 'model-index.yml'
|
||||
model_index = load(str(model_index_file))
|
||||
model_index.build_models_with_collections()
|
||||
models = OrderedDict({model.name: model for model in model_index.models})
|
||||
|
||||
logger = MMLogger(
|
||||
'validation',
|
||||
logger_name='validation',
|
||||
log_file='benchmark_test_image.log',
|
||||
log_level=logging.INFO)
|
||||
|
||||
if args.models:
|
||||
patterns = [re.compile(pattern) for pattern in args.models]
|
||||
filter_models = {}
|
||||
for k, v in models.items():
|
||||
if any([re.match(pattern, k) for pattern in patterns]):
|
||||
filter_models[k] = v
|
||||
if len(filter_models) == 0:
|
||||
models = set()
|
||||
for pattern in args.models:
|
||||
models.update(list_models(pattern=pattern))
|
||||
if len(models) == 0:
|
||||
print('No model found, please specify models in:')
|
||||
print('\n'.join(models.keys()))
|
||||
print('\n'.join(list_models()))
|
||||
return
|
||||
models = filter_models
|
||||
else:
|
||||
models = list_models()
|
||||
|
||||
summary_data = {}
|
||||
tmpdir = tempfile.TemporaryDirectory()
|
||||
for model_name, model_info in models.items():
|
||||
for model_name in models:
|
||||
|
||||
model_info = ModelHub.get(model_name)
|
||||
if model_info.config is None:
|
||||
continue
|
||||
|
||||
config = Path(model_info.config)
|
||||
assert config.exists(), f'{model_name}: {config} not found.'
|
||||
|
||||
logger.info(f'Processing: {model_name}')
|
||||
|
||||
http_prefix = 'https://download.openmmlab.com/mmclassification/'
|
||||
if args.checkpoint_root is not None:
|
||||
root = args.checkpoint_root
|
||||
if 's3://' in args.checkpoint_root:
|
||||
from petrel_client.common.exception import AccessDeniedError
|
||||
file_client = FileClient.infer_client(uri=root)
|
||||
checkpoint = file_client.join_path(
|
||||
root, model_info.weights[len(http_prefix):])
|
||||
try:
|
||||
exists = file_client.exists(checkpoint)
|
||||
except AccessDeniedError:
|
||||
exists = False
|
||||
else:
|
||||
checkpoint = Path(root) / model_info.weights[len(http_prefix):]
|
||||
exists = checkpoint.exists()
|
||||
if exists:
|
||||
checkpoint = str(checkpoint)
|
||||
else:
|
||||
print(f'WARNING: {model_name}: {checkpoint} not found.')
|
||||
checkpoint = None
|
||||
weights = model_info.weights
|
||||
if args.checkpoint_root is not None and weights is not None:
|
||||
checkpoint = substitute_weights(weights, args.checkpoint_root)
|
||||
else:
|
||||
checkpoint = None
|
||||
|
||||
try:
|
||||
# build the model from a config file and a checkpoint file
|
||||
result = inference(MMCLS_ROOT / config, checkpoint, tmpdir.name,
|
||||
args, model_name)
|
||||
result = inference(model_info, checkpoint, tmpdir.name, args)
|
||||
result['valid'] = 'PASS'
|
||||
except Exception as e:
|
||||
if 'CUDA out of memory' in str(e):
|
||||
logger.error(f'"{config}" :\nCUDA out of memory')
|
||||
logger.error(f'"{model_name}" :\nCUDA out of memory')
|
||||
result = {'valid': 'CUDA OOM'}
|
||||
else:
|
||||
import traceback
|
||||
logger.error(f'"{config}" :\n{traceback.format_exc()}')
|
||||
logger.error(f'"{model_name}" :\n{traceback.format_exc()}')
|
||||
result = {'valid': 'FAIL'}
|
||||
|
||||
summary_data[model_name] = result
|
||||
|
|
|
|||
|
|
@ -1,9 +1,10 @@
|
|||
import argparse
|
||||
import fnmatch
|
||||
import logging
|
||||
import os
|
||||
import os.path as osp
|
||||
import pickle
|
||||
import re
|
||||
from collections import OrderedDict
|
||||
from collections import OrderedDict, defaultdict
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
|
|
@ -11,57 +12,57 @@ from modelindex.load_model_index import load
|
|||
from rich.console import Console
|
||||
from rich.syntax import Syntax
|
||||
from rich.table import Table
|
||||
from utils import METRICS_MAP, MMCLS_ROOT, substitute_weights
|
||||
|
||||
# Avoid to import MMPretrain to accelerate speed to show summary
|
||||
|
||||
console = Console()
|
||||
MMCLS_ROOT = Path(__file__).absolute().parents[2]
|
||||
METRICS_MAP = {
|
||||
'Top 1 Accuracy': 'accuracy/top1',
|
||||
'Top 5 Accuracy': 'accuracy/top5'
|
||||
}
|
||||
logger = logging.getLogger('test')
|
||||
logger.addHandler(logging.StreamHandler())
|
||||
logger.addHandler(logging.FileHandler('benchmark_test.log', mode='w'))
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Test all models' accuracy in model-index.yml")
|
||||
parser.add_argument(
|
||||
'partition', type=str, help='Cluster partition to use.')
|
||||
parser.add_argument('checkpoint_root', help='Checkpoint file root path.')
|
||||
parser.add_argument(
|
||||
'--job-name',
|
||||
type=str,
|
||||
default='cls-test-benchmark',
|
||||
help='Slurm job name prefix')
|
||||
parser.add_argument('--port', type=int, default=29666, help='dist port')
|
||||
'--local', action='store_true', help='run at local instead of slurm.')
|
||||
parser.add_argument(
|
||||
'--models', nargs='+', type=str, help='Specify model names to run.')
|
||||
parser.add_argument(
|
||||
'--work-dir',
|
||||
default='work_dirs/benchmark_test',
|
||||
help='the dir to save metric')
|
||||
parser.add_argument(
|
||||
'--run', action='store_true', help='run script directly')
|
||||
parser.add_argument(
|
||||
'--local',
|
||||
action='store_true',
|
||||
help='run at local instead of cluster.')
|
||||
parser.add_argument(
|
||||
'--mail', type=str, help='Mail address to watch test status.')
|
||||
parser.add_argument(
|
||||
'--mail-type',
|
||||
nargs='+',
|
||||
default=['BEGIN'],
|
||||
choices=['NONE', 'BEGIN', 'END', 'FAIL', 'REQUEUE', 'ALL'],
|
||||
help='Mail address to watch test status.')
|
||||
parser.add_argument(
|
||||
'--quotatype',
|
||||
default=None,
|
||||
choices=['reserved', 'auto', 'spot'],
|
||||
help='Quota type, only available for phoenix-slurm>=0.2')
|
||||
parser.add_argument(
|
||||
'--summary',
|
||||
action='store_true',
|
||||
help='Summarize benchmark test results.')
|
||||
parser.add_argument('--save', action='store_true', help='Save the summary')
|
||||
parser.add_argument(
|
||||
'--gpus', type=int, default=1, help='How many GPUS to use.')
|
||||
parser.add_argument(
|
||||
'--no-skip',
|
||||
action='store_true',
|
||||
help='Whether to skip models without results record in the metafile.')
|
||||
parser.add_argument(
|
||||
'--work-dir',
|
||||
default='work_dirs/benchmark_test',
|
||||
help='the dir to save metric')
|
||||
parser.add_argument('--port', type=int, default=29666, help='dist port')
|
||||
parser.add_argument(
|
||||
'--partition',
|
||||
type=str,
|
||||
default='mm_model',
|
||||
help='(for slurm) Cluster partition to use.')
|
||||
parser.add_argument(
|
||||
'--job-name',
|
||||
type=str,
|
||||
default='cls-test-benchmark',
|
||||
help='(for slurm) Slurm job name prefix')
|
||||
parser.add_argument(
|
||||
'--quotatype',
|
||||
default=None,
|
||||
choices=['reserved', 'auto', 'spot'],
|
||||
help='(for slurm) Quota type, only available for phoenix-slurm>=0.2')
|
||||
parser.add_argument(
|
||||
'--cfg-options',
|
||||
nargs='+',
|
||||
|
|
@ -74,64 +75,53 @@ def parse_args():
|
|||
|
||||
|
||||
def create_test_job_batch(commands, model_info, args, port, script_name):
|
||||
|
||||
fname = model_info.name
|
||||
|
||||
model_name = model_info.name
|
||||
config = Path(model_info.config)
|
||||
assert config.exists(), f'{fname}: {config} not found.'
|
||||
|
||||
http_prefix = 'https://download.openmmlab.com/mmclassification/'
|
||||
if 's3://' in args.checkpoint_root:
|
||||
from mmengine.fileio import FileClient
|
||||
from petrel_client.common.exception import AccessDeniedError
|
||||
file_client = FileClient.infer_client(uri=args.checkpoint_root)
|
||||
checkpoint = file_client.join_path(
|
||||
args.checkpoint_root, model_info.weights[len(http_prefix):])
|
||||
try:
|
||||
exists = file_client.exists(checkpoint)
|
||||
except AccessDeniedError:
|
||||
exists = False
|
||||
if model_info.weights is not None:
|
||||
checkpoint = substitute_weights(model_info.weights,
|
||||
args.checkpoint_root)
|
||||
if checkpoint is None:
|
||||
logger.warning(f'{model_name}: {checkpoint} not found.')
|
||||
return None
|
||||
else:
|
||||
checkpoint_root = Path(args.checkpoint_root)
|
||||
checkpoint = checkpoint_root / model_info.weights[len(http_prefix):]
|
||||
exists = checkpoint.exists()
|
||||
if not exists:
|
||||
print(f'WARNING: {fname}: {checkpoint} not found.')
|
||||
return None
|
||||
|
||||
job_name = f'{args.job_name}_{fname}'
|
||||
work_dir = Path(args.work_dir) / fname
|
||||
job_name = f'{args.job_name}_{model_name}'
|
||||
work_dir = Path(args.work_dir) / model_name
|
||||
work_dir.mkdir(parents=True, exist_ok=True)
|
||||
result_file = work_dir / 'result.pkl'
|
||||
|
||||
if args.mail is not None and 'NONE' not in args.mail_type:
|
||||
mail_cfg = (f'#SBATCH --mail {args.mail}\n'
|
||||
f'#SBATCH --mail-type {args.mail_type}\n')
|
||||
else:
|
||||
mail_cfg = ''
|
||||
|
||||
if args.quotatype is not None:
|
||||
quota_cfg = f'#SBATCH --quotatype {args.quotatype}\n'
|
||||
quota_cfg = f'#SBATCH --quotatype {args.quotatype}'
|
||||
else:
|
||||
quota_cfg = ''
|
||||
|
||||
launcher = 'none' if args.local else 'slurm'
|
||||
runner = 'python' if args.local else 'srun python'
|
||||
if not args.local:
|
||||
launcher = 'srun python'
|
||||
runner = 'slurm'
|
||||
elif args.gpus > 1:
|
||||
launcher = 'pytorch'
|
||||
runner = ('torchrun --master_addr="127.0.0.1" '
|
||||
f'--master_port={port} --nproc_per_node={args.gpus}')
|
||||
else:
|
||||
launcher = 'none'
|
||||
runner = 'python -u'
|
||||
|
||||
job_script = (f'#!/bin/bash\n'
|
||||
f'#SBATCH --output {work_dir}/job.%j.out\n'
|
||||
f'#SBATCH --partition={args.partition}\n'
|
||||
f'#SBATCH --job-name {job_name}\n'
|
||||
f'#SBATCH --gres=gpu:8\n'
|
||||
f'{mail_cfg}{quota_cfg}'
|
||||
f'#SBATCH --ntasks-per-node=8\n'
|
||||
f'#SBATCH --ntasks=8\n'
|
||||
f'#SBATCH --gres=gpu:{min(8, args.gpus)}\n'
|
||||
f'{quota_cfg}\n'
|
||||
f'#SBATCH --ntasks-per-node={min(8, args.gpus)}\n'
|
||||
f'#SBATCH --ntasks={args.gpus}\n'
|
||||
f'#SBATCH --cpus-per-task=5\n\n'
|
||||
f'{runner} -u {script_name} {config} {checkpoint} '
|
||||
f'--work-dir={work_dir} '
|
||||
f'--out={result_file} '
|
||||
f'--cfg-option dist_params.port={port} '
|
||||
f'{runner} {script_name} {config} {checkpoint} '
|
||||
f'--work-dir={work_dir} --cfg-option '
|
||||
f'env_cfg.dist_cfg.port={port} '
|
||||
f'{" ".join(args.cfg_options)} '
|
||||
f'--out={result_file} --out-item="metrics" '
|
||||
f'--launcher={launcher}\n')
|
||||
|
||||
with open(work_dir / 'job.sh', 'w') as f:
|
||||
|
|
@ -146,33 +136,17 @@ def create_test_job_batch(commands, model_info, args, port, script_name):
|
|||
return work_dir / 'job.sh'
|
||||
|
||||
|
||||
def test(args):
|
||||
# parse model-index.yml
|
||||
model_index_file = MMCLS_ROOT / 'model-index.yml'
|
||||
model_index = load(str(model_index_file))
|
||||
model_index.build_models_with_collections()
|
||||
models = OrderedDict({model.name: model for model in model_index.models})
|
||||
|
||||
def test(models, args):
|
||||
script_name = osp.join('tools', 'test.py')
|
||||
port = args.port
|
||||
|
||||
commands = []
|
||||
if args.models:
|
||||
patterns = [re.compile(pattern) for pattern in args.models]
|
||||
filter_models = {}
|
||||
for k, v in models.items():
|
||||
if any([re.match(pattern, k) for pattern in patterns]):
|
||||
filter_models[k] = v
|
||||
if len(filter_models) == 0:
|
||||
print('No model found, please specify models in:')
|
||||
print('\n'.join(models.keys()))
|
||||
return
|
||||
models = filter_models
|
||||
|
||||
preview_script = ''
|
||||
for model_info in models.values():
|
||||
|
||||
if model_info.results is None:
|
||||
# Skip pre-train model
|
||||
continue
|
||||
|
||||
script_path = create_test_job_batch(commands, model_info, args, port,
|
||||
|
|
@ -205,44 +179,41 @@ def test(args):
|
|||
console.print('Please set "--run" to start the job')
|
||||
|
||||
|
||||
def save_summary(summary_data, models_map, work_dir):
|
||||
summary_path = work_dir / 'test_benchmark_summary.md'
|
||||
def save_summary(summary_data, work_dir):
|
||||
summary_path = work_dir / 'test_benchmark_summary.csv'
|
||||
file = open(summary_path, 'w')
|
||||
headers = [
|
||||
'Model', 'Top-1 Expected(%)', 'Top-1 (%)', 'Top-5 Expected (%)',
|
||||
'Top-5 (%)', 'Config'
|
||||
]
|
||||
file.write('# Test Benchmark Regression Summary\n')
|
||||
file.write('| ' + ' | '.join(headers) + ' |\n')
|
||||
file.write('|:' + ':|:'.join(['---'] * len(headers)) + ':|\n')
|
||||
columns = defaultdict(list)
|
||||
for model_name, summary in summary_data.items():
|
||||
if len(summary) == 0:
|
||||
# Skip models without results
|
||||
continue
|
||||
row = [model_name]
|
||||
if 'Top 1 Accuracy' in summary:
|
||||
metric = summary['Top 1 Accuracy']
|
||||
row.append(str(round(metric['expect'], 2)))
|
||||
row.append(str(round(metric['result'], 2)))
|
||||
else:
|
||||
row.extend([''] * 2)
|
||||
if 'Top 5 Accuracy' in summary:
|
||||
metric = summary['Top 5 Accuracy']
|
||||
row.append(str(round(metric['expect'], 2)))
|
||||
row.append(str(round(metric['result'], 2)))
|
||||
else:
|
||||
row.extend([''] * 2)
|
||||
columns['Name'].append(model_name)
|
||||
|
||||
model_info = models_map[model_name]
|
||||
row.append(model_info.config)
|
||||
file.write('| ' + ' | '.join(row) + ' |\n')
|
||||
for metric_key in METRICS_MAP:
|
||||
if metric_key in summary:
|
||||
metric = summary[metric_key]
|
||||
expect = round(metric['expect'], 2)
|
||||
result = round(metric['result'], 2)
|
||||
columns[f'{metric_key} (expect)'].append(str(expect))
|
||||
columns[f'{metric_key}'].append(str(result))
|
||||
else:
|
||||
columns[f'{metric_key} (expect)'].append('')
|
||||
columns[f'{metric_key}'].append('')
|
||||
|
||||
columns = {
|
||||
field: column
|
||||
for field, column in columns.items() if ''.join(column)
|
||||
}
|
||||
file.write(','.join(columns.keys()) + '\n')
|
||||
for row in zip(*columns.values()):
|
||||
file.write(','.join(row) + '\n')
|
||||
file.close()
|
||||
print('Summary file saved at ' + str(summary_path))
|
||||
logger.info('Summary file saved at ' + str(summary_path))
|
||||
|
||||
|
||||
def show_summary(summary_data):
|
||||
table = Table(title='Test Benchmark Regression Summary')
|
||||
table.add_column('Model')
|
||||
table.add_column('Name')
|
||||
for metric in METRICS_MAP:
|
||||
table.add_column(f'{metric} (expect)')
|
||||
table.add_column(f'{metric}')
|
||||
|
|
@ -274,33 +245,20 @@ def show_summary(summary_data):
|
|||
row.append('')
|
||||
table.add_row(*row)
|
||||
|
||||
# Remove empty columns
|
||||
table.columns = [
|
||||
column for column in table.columns if ''.join(column._cells)
|
||||
]
|
||||
console.print(table)
|
||||
|
||||
|
||||
def summary(args):
|
||||
model_index_file = MMCLS_ROOT / 'model-index.yml'
|
||||
model_index = load(str(model_index_file))
|
||||
model_index.build_models_with_collections()
|
||||
models = OrderedDict({model.name: model for model in model_index.models})
|
||||
|
||||
def summary(models, args):
|
||||
work_dir = Path(args.work_dir)
|
||||
|
||||
if args.models:
|
||||
patterns = [re.compile(pattern) for pattern in args.models]
|
||||
filter_models = {}
|
||||
for k, v in models.items():
|
||||
if any([re.match(pattern, k) for pattern in patterns]):
|
||||
filter_models[k] = v
|
||||
if len(filter_models) == 0:
|
||||
print('No model found, please specify models in:')
|
||||
print('\n'.join(models.keys()))
|
||||
return
|
||||
models = filter_models
|
||||
|
||||
summary_data = {}
|
||||
for model_name, model_info in models.items():
|
||||
|
||||
if model_info.results is None:
|
||||
if model_info.results is None and not args.no_skip:
|
||||
continue
|
||||
|
||||
# Skip if not found result file.
|
||||
|
|
@ -327,16 +285,35 @@ def summary(args):
|
|||
|
||||
show_summary(summary_data)
|
||||
if args.save:
|
||||
save_summary(summary_data, models, work_dir)
|
||||
save_summary(summary_data, work_dir)
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
|
||||
# parse model-index.yml
|
||||
model_index_file = MMCLS_ROOT / 'model-index.yml'
|
||||
model_index = load(str(model_index_file))
|
||||
model_index.build_models_with_collections()
|
||||
models = OrderedDict({model.name: model for model in model_index.models})
|
||||
|
||||
if args.models:
|
||||
filter_models = {}
|
||||
for pattern in args.models:
|
||||
filter_models.update({
|
||||
name: models[name]
|
||||
for name in fnmatch.filter(models, pattern + '*')
|
||||
})
|
||||
if len(filter_models) == 0:
|
||||
logger.error('No model found, please specify models in:\n' +
|
||||
'\n'.join(models.keys()))
|
||||
return
|
||||
models = filter_models
|
||||
|
||||
if args.summary:
|
||||
summary(args)
|
||||
summary(models, args)
|
||||
else:
|
||||
test(args)
|
||||
test(models, args)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
|
|
|||
|
|
@ -1,9 +1,12 @@
|
|||
import argparse
|
||||
import fnmatch
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import os.path as osp
|
||||
import re
|
||||
from collections import OrderedDict
|
||||
from collections import defaultdict
|
||||
from copy import deepcopy
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from zipfile import ZipFile
|
||||
|
|
@ -13,19 +16,20 @@ from modelindex.load_model_index import load
|
|||
from rich.console import Console
|
||||
from rich.syntax import Syntax
|
||||
from rich.table import Table
|
||||
from utils import METRICS_MAP, MMCLS_ROOT
|
||||
|
||||
# Avoid to import MMPretrain to accelerate speed to show summary
|
||||
|
||||
console = Console()
|
||||
MMCLS_ROOT = Path(__file__).absolute().parents[2]
|
||||
logger = logging.getLogger('train')
|
||||
logger.addHandler(logging.StreamHandler())
|
||||
logger.addHandler(logging.FileHandler('benchmark_train.log', mode='w'))
|
||||
CYCLE_LEVELS = ['month', 'quarter', 'half-year', 'no-training']
|
||||
METRICS_MAP = {
|
||||
'Top 1 Accuracy': 'accuracy/top1',
|
||||
'Top 5 Accuracy': 'accuracy/top5'
|
||||
}
|
||||
|
||||
|
||||
class RangeAction(argparse.Action):
|
||||
|
||||
def __call__(self, parser, namespace, values: str, option_string):
|
||||
def __call__(self, _, namespace, values: str, __):
|
||||
matches = re.match(r'([><=]*)([-\w]+)', values)
|
||||
if matches is None:
|
||||
raise ValueError(f'Unavailable range option {values}')
|
||||
|
|
@ -49,15 +53,25 @@ def parse_args():
|
|||
parser = argparse.ArgumentParser(
|
||||
description='Train models (in bench_train.yml) and compare accuracy.')
|
||||
parser.add_argument(
|
||||
'partition', type=str, help='Cluster partition to use.')
|
||||
parser.add_argument(
|
||||
'--job-name',
|
||||
type=str,
|
||||
default='cls-train-benchmark',
|
||||
help='Slurm job name prefix')
|
||||
parser.add_argument('--port', type=int, default=29666, help='dist port')
|
||||
'--local',
|
||||
action='store_true',
|
||||
help='run at local instead of cluster.')
|
||||
parser.add_argument(
|
||||
'--models', nargs='+', type=str, help='Specify model names to run.')
|
||||
parser.add_argument(
|
||||
'--run', action='store_true', help='run script directly')
|
||||
parser.add_argument(
|
||||
'--summary',
|
||||
action='store_true',
|
||||
help='Summarize benchmark train results.')
|
||||
parser.add_argument(
|
||||
'--save',
|
||||
action='store_true',
|
||||
help='Save the summary and archive log files.')
|
||||
parser.add_argument(
|
||||
'--non-distributed',
|
||||
action='store_true',
|
||||
help='Use non-distributed environment (for debug).')
|
||||
parser.add_argument(
|
||||
'--range',
|
||||
type=str,
|
||||
|
|
@ -70,33 +84,22 @@ def parse_args():
|
|||
'--work-dir',
|
||||
default='work_dirs/benchmark_train',
|
||||
help='the dir to save train log')
|
||||
parser.add_argument('--port', type=int, default=29666, help='dist port')
|
||||
parser.add_argument(
|
||||
'--run', action='store_true', help='run script directly')
|
||||
'--partition',
|
||||
type=str,
|
||||
default='mm_model',
|
||||
help='(for slurm) Cluster partition to use.')
|
||||
parser.add_argument(
|
||||
'--local',
|
||||
action='store_true',
|
||||
help='run at local instead of cluster.')
|
||||
parser.add_argument(
|
||||
'--mail', type=str, help='Mail address to watch train status.')
|
||||
parser.add_argument(
|
||||
'--mail-type',
|
||||
nargs='+',
|
||||
default=['BEGIN', 'END', 'FAIL'],
|
||||
choices=['NONE', 'BEGIN', 'END', 'FAIL', 'REQUEUE', 'ALL'],
|
||||
help='Mail address to watch train status.')
|
||||
'--job-name',
|
||||
type=str,
|
||||
default='cls-train-benchmark',
|
||||
help='(for slurm) Slurm job name prefix')
|
||||
parser.add_argument(
|
||||
'--quotatype',
|
||||
default=None,
|
||||
choices=['reserved', 'auto', 'spot'],
|
||||
help='Quota type, only available for phoenix-slurm>=0.2')
|
||||
parser.add_argument(
|
||||
'--summary',
|
||||
action='store_true',
|
||||
help='Summarize benchmark train results.')
|
||||
parser.add_argument(
|
||||
'--save',
|
||||
action='store_true',
|
||||
help='Save the summary and archive log files.')
|
||||
help='(for slurm) Quota type, only available for phoenix-slurm>=0.2')
|
||||
parser.add_argument(
|
||||
'--cfg-options',
|
||||
nargs='+',
|
||||
|
|
@ -118,72 +121,90 @@ def get_gpu_number(model_info):
|
|||
return gpus
|
||||
|
||||
|
||||
def create_train_job_batch(commands, model_info, args, port, script_name):
|
||||
|
||||
fname = model_info.name
|
||||
|
||||
gpus = get_gpu_number(model_info)
|
||||
gpus_per_node = min(gpus, 8)
|
||||
|
||||
def create_train_job_batch(model_info, args, port, pretrain_info=None):
|
||||
model_name = model_info.name
|
||||
config = Path(model_info.config)
|
||||
assert config.exists(), f'"{fname}": {config} not found.'
|
||||
gpus = get_gpu_number(model_info)
|
||||
|
||||
job_name = f'{args.job_name}_{fname}'
|
||||
work_dir = Path(args.work_dir) / fname
|
||||
job_name = f'{args.job_name}_{model_name}'
|
||||
work_dir = Path(args.work_dir) / model_name
|
||||
work_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
if args.mail is not None and 'NONE' not in args.mail_type:
|
||||
mail_cfg = (f'#SBATCH --mail {args.mail}\n'
|
||||
f'#SBATCH --mail-type {args.mail_type}\n')
|
||||
else:
|
||||
mail_cfg = ''
|
||||
cfg_options = deepcopy(args.cfg_options)
|
||||
|
||||
if args.quotatype is not None:
|
||||
quota_cfg = f'#SBATCH --quotatype {args.quotatype}\n'
|
||||
quota_cfg = f'#SBATCH --quotatype {args.quotatype}'
|
||||
else:
|
||||
quota_cfg = ''
|
||||
|
||||
launcher = 'none' if args.local else 'slurm'
|
||||
runner = 'python' if args.local else 'srun python'
|
||||
if pretrain_info is not None:
|
||||
pretrain = Path(args.work_dir) / pretrain_info.name / 'last_checkpoint'
|
||||
pretrain_cfg = (f'model.backbone.init_cfg.checkpoint="$(<{pretrain})" '
|
||||
'model.backbone.init_cfg.type="Pretrained" '
|
||||
'model.backbone.init_cfg.prefix="backbone."')
|
||||
else:
|
||||
pretrain_cfg = ''
|
||||
|
||||
if not args.local:
|
||||
launcher = 'slurm'
|
||||
runner = 'srun python'
|
||||
elif not args.non_distributed:
|
||||
launcher = 'pytorch'
|
||||
if gpus > 8:
|
||||
gpus = 8
|
||||
cfg_options.append('auto_scale_lr.enable=True')
|
||||
runner = ('torchrun --master_addr="127.0.0.1" '
|
||||
f'--master_port={port} --nproc_per_node={gpus}')
|
||||
else:
|
||||
launcher = 'none'
|
||||
runner = 'python -u'
|
||||
|
||||
job_script = (f'#!/bin/bash\n'
|
||||
f'#SBATCH --output {work_dir}/job.%j.out\n'
|
||||
f'#SBATCH --partition={args.partition}\n'
|
||||
f'#SBATCH --job-name {job_name}\n'
|
||||
f'#SBATCH --gres=gpu:{gpus_per_node}\n'
|
||||
f'{mail_cfg}{quota_cfg}'
|
||||
f'#SBATCH --ntasks-per-node={gpus_per_node}\n'
|
||||
f'#SBATCH --gres=gpu:{min(8, gpus)}\n'
|
||||
f'{quota_cfg}\n'
|
||||
f'#SBATCH --ntasks-per-node={min(8, gpus)}\n'
|
||||
f'#SBATCH --ntasks={gpus}\n'
|
||||
f'#SBATCH --cpus-per-task=5\n\n'
|
||||
f'{runner} -u {script_name} {config} '
|
||||
f'{runner} tools/train.py {config} '
|
||||
f'--work-dir={work_dir} --cfg-option '
|
||||
f'env_cfg.dist_cfg.port={port} '
|
||||
f'{" ".join(args.cfg_options)} '
|
||||
f'{" ".join(cfg_options)} '
|
||||
f'default_hooks.checkpoint.max_keep_ckpts=2 '
|
||||
f'default_hooks.checkpoint.save_best="auto" '
|
||||
f'{pretrain_cfg} '
|
||||
f'--launcher={launcher}\n')
|
||||
|
||||
with open(work_dir / 'job.sh', 'w') as f:
|
||||
f.write(job_script)
|
||||
|
||||
commands.append(f'echo "{config}"')
|
||||
if args.local:
|
||||
commands.append(f'bash {work_dir}/job.sh')
|
||||
else:
|
||||
commands.append(f'sbatch {work_dir}/job.sh')
|
||||
|
||||
return work_dir / 'job.sh'
|
||||
|
||||
|
||||
def train(models, args):
|
||||
script_name = osp.join('tools', 'train.py')
|
||||
port = args.port
|
||||
|
||||
commands = []
|
||||
|
||||
for model_info in models.values():
|
||||
script_path = create_train_job_batch(commands, model_info, args, port,
|
||||
script_name)
|
||||
script_path = create_train_job_batch(model_info, args, port)
|
||||
if hasattr(model_info, 'downstream'):
|
||||
downstream_info = model_info.downstream
|
||||
downstream_script = create_train_job_batch(
|
||||
downstream_info, args, port, pretrain_info=model_info)
|
||||
else:
|
||||
downstream_script = None
|
||||
|
||||
if args.local:
|
||||
command = f'bash {script_path}'
|
||||
if downstream_script:
|
||||
command += f' && bash {downstream_script}'
|
||||
else:
|
||||
command = f'JOBID=$(sbatch --parsable {script_path})'
|
||||
if downstream_script:
|
||||
command += f' && sbatch --dependency=afterok:$JOBID {downstream_script}' # noqa: E501
|
||||
commands.append(command)
|
||||
|
||||
port += 1
|
||||
|
||||
command_str = '\n'.join(commands)
|
||||
|
|
@ -211,63 +232,67 @@ def train(models, args):
|
|||
console.print('Please set "--run" to start the job')
|
||||
|
||||
|
||||
def save_summary(summary_data, models_map, work_dir):
|
||||
def save_summary(summary_data, work_dir):
|
||||
date = datetime.now().strftime('%Y%m%d-%H%M%S')
|
||||
zip_path = work_dir / f'archive-{date}.zip'
|
||||
zip_file = ZipFile(zip_path, 'w')
|
||||
summary_path = work_dir / 'benchmark_summary.md'
|
||||
|
||||
summary_path = work_dir / 'benchmark_summary.csv'
|
||||
file = open(summary_path, 'w')
|
||||
headers = [
|
||||
'Model', 'Top-1 Expected(%)', 'Top-1 (%)', 'Top-1 best(%)',
|
||||
'best epoch', 'Top-5 Expected (%)', 'Top-5 (%)', 'Config', 'Log'
|
||||
]
|
||||
file.write('# Train Benchmark Regression Summary\n')
|
||||
file.write('| ' + ' | '.join(headers) + ' |\n')
|
||||
file.write('|:' + ':|:'.join(['---'] * len(headers)) + ':|\n')
|
||||
columns = defaultdict(list)
|
||||
for model_name, summary in summary_data.items():
|
||||
if len(summary) == 0:
|
||||
# Skip models without results
|
||||
continue
|
||||
row = [model_name]
|
||||
if 'Top 1 Accuracy' in summary:
|
||||
metric = summary['Top 1 Accuracy']
|
||||
row.append(f"{metric['expect']:.2f}")
|
||||
row.append(f"{metric['last']:.2f}")
|
||||
row.append(f"{metric['best']:.2f}")
|
||||
row.append(f"{metric['best_epoch']:.2f}")
|
||||
else:
|
||||
row.extend([''] * 4)
|
||||
if 'Top 5 Accuracy' in summary:
|
||||
metric = summary['Top 5 Accuracy']
|
||||
row.append(f"{metric['expect']:.2f}")
|
||||
row.append(f"{metric['last']:.2f}")
|
||||
else:
|
||||
row.extend([''] * 2)
|
||||
columns['Name'].append(model_name)
|
||||
|
||||
model_info = models_map[model_name]
|
||||
row.append(model_info.config)
|
||||
row.append(str(summary['log_file'].relative_to(work_dir)))
|
||||
for metric_key in METRICS_MAP:
|
||||
if metric_key in summary:
|
||||
metric = summary[metric_key]
|
||||
expect = str(round(metric['expect'], 2))
|
||||
result = str(round(metric['result'], 2))
|
||||
columns[f'{metric_key} (expect)'].append(expect)
|
||||
columns[f'{metric_key}'].append(result)
|
||||
best = str(round(metric['best'], 2))
|
||||
best_epoch = str(int(metric['best_epoch']))
|
||||
columns[f'{metric_key} (best)'].append(best)
|
||||
columns[f'{metric_key} (best epoch)'].append(best_epoch)
|
||||
else:
|
||||
columns[f'{metric_key} (expect)'].append('')
|
||||
columns[f'{metric_key}'].append('')
|
||||
columns[f'{metric_key} (best)'].append('')
|
||||
columns[f'{metric_key} (best epoch)'].append('')
|
||||
|
||||
columns['Log'].append(str(summary['log_file'].relative_to(work_dir)))
|
||||
zip_file.write(summary['log_file'])
|
||||
file.write('| ' + ' | '.join(row) + ' |\n')
|
||||
|
||||
columns = {
|
||||
field: column
|
||||
for field, column in columns.items() if ''.join(column)
|
||||
}
|
||||
file.write(','.join(columns.keys()) + '\n')
|
||||
for row in zip(*columns.values()):
|
||||
file.write(','.join(row) + '\n')
|
||||
file.close()
|
||||
zip_file.write(summary_path)
|
||||
zip_file.close()
|
||||
print('Summary file saved at ' + str(summary_path))
|
||||
print('Log files archived at ' + str(zip_path))
|
||||
logger.info('Summary file saved at ' + str(summary_path))
|
||||
logger.info('Log files archived at ' + str(zip_path))
|
||||
|
||||
|
||||
def show_summary(summary_data):
|
||||
table = Table(title='Train Benchmark Regression Summary')
|
||||
table.add_column('Model')
|
||||
table.add_column('Name')
|
||||
for metric in METRICS_MAP:
|
||||
table.add_column(f'{metric} (expect)')
|
||||
table.add_column(f'{metric}')
|
||||
table.add_column(f'{metric} (best)')
|
||||
table.add_column('Date')
|
||||
|
||||
def set_color(value, expect):
|
||||
if value > expect:
|
||||
return 'green'
|
||||
elif value > expect - 0.2:
|
||||
elif value >= expect - 0.2:
|
||||
return 'white'
|
||||
else:
|
||||
return 'red'
|
||||
|
|
@ -277,25 +302,30 @@ def show_summary(summary_data):
|
|||
for metric_key in METRICS_MAP:
|
||||
if metric_key in summary:
|
||||
metric = summary[metric_key]
|
||||
expect = metric['expect']
|
||||
last = metric['last']
|
||||
expect = round(metric['expect'], 2)
|
||||
last = round(metric['last'], 2)
|
||||
last_epoch = metric['last_epoch']
|
||||
last_color = set_color(last, expect)
|
||||
best = metric['best']
|
||||
best_color = set_color(best, expect)
|
||||
best_epoch = metric['best_epoch']
|
||||
best_epoch = round(metric['best_epoch'], 2)
|
||||
row.append(f'{expect:.2f}')
|
||||
row.append(
|
||||
f'[{last_color}]{last:.2f}[/{last_color}] ({last_epoch})')
|
||||
row.append(
|
||||
f'[{best_color}]{best:.2f}[/{best_color}] ({best_epoch})')
|
||||
else:
|
||||
row.extend([''] * 3)
|
||||
table.add_row(*row)
|
||||
|
||||
# Remove empty columns
|
||||
table.columns = [
|
||||
column for column in table.columns if ''.join(column._cells)
|
||||
]
|
||||
console.print(table)
|
||||
|
||||
|
||||
def summary(models, args):
|
||||
|
||||
work_dir = Path(args.work_dir)
|
||||
dir_map = {p.name: p for p in work_dir.iterdir() if p.is_dir()}
|
||||
|
||||
|
|
@ -306,9 +336,17 @@ def summary(models, args):
|
|||
|
||||
if model_name not in dir_map:
|
||||
continue
|
||||
elif hasattr(model_info, 'downstream'):
|
||||
downstream_name = model_info.downstream.name
|
||||
if downstream_name not in dir_map:
|
||||
continue
|
||||
else:
|
||||
sub_dir = dir_map[downstream_name]
|
||||
model_info = model_info.downstream
|
||||
else:
|
||||
# Skip if not found any vis_data folder.
|
||||
sub_dir = dir_map[model_name]
|
||||
|
||||
# Skip if not found any vis_data folder.
|
||||
sub_dir = dir_map[model_name]
|
||||
log_files = [f for f in sub_dir.glob('*/vis_data/scalars.json')]
|
||||
if len(log_files) == 0:
|
||||
continue
|
||||
|
|
@ -317,11 +355,8 @@ def summary(models, args):
|
|||
# parse train log
|
||||
with open(log_file) as f:
|
||||
json_logs = [json.loads(s) for s in f.readlines()]
|
||||
val_logs = [
|
||||
log for log in json_logs
|
||||
# TODO: need a better method to extract validate log
|
||||
if 'loss' not in log and 'accuracy/top1' in log
|
||||
]
|
||||
# TODO: need a better method to extract validate log
|
||||
val_logs = [log for log in json_logs if 'loss' not in log]
|
||||
|
||||
if len(val_logs) == 0:
|
||||
continue
|
||||
|
|
@ -351,12 +386,13 @@ def summary(models, args):
|
|||
|
||||
show_summary(summary_data)
|
||||
if args.save:
|
||||
save_summary(summary_data, models, work_dir)
|
||||
save_summary(summary_data, work_dir)
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
|
||||
# parse model-index.yml
|
||||
model_index_file = MMCLS_ROOT / 'model-index.yml'
|
||||
model_index = load(str(model_index_file))
|
||||
model_index.build_models_with_collections()
|
||||
|
|
@ -364,25 +400,28 @@ def main():
|
|||
|
||||
with open(Path(__file__).parent / 'bench_train.yml', 'r') as f:
|
||||
train_items = yaml.safe_load(f)
|
||||
models = OrderedDict()
|
||||
models = {}
|
||||
for item in train_items:
|
||||
name = item['Name']
|
||||
model_info = all_models[name]
|
||||
model_info.cycle = item.get('Cycle', None)
|
||||
cycle = getattr(model_info, 'cycle', 'month')
|
||||
cycle = item['Cycle']
|
||||
cycle_level = CYCLE_LEVELS.index(cycle)
|
||||
if cycle_level in args.range:
|
||||
model_info = all_models[name]
|
||||
if 'Downstream' in item:
|
||||
downstream = item['Downstream']
|
||||
setattr(model_info, 'downstream', all_models[downstream])
|
||||
models[name] = model_info
|
||||
|
||||
if args.models:
|
||||
patterns = [re.compile(pattern) for pattern in args.models]
|
||||
filter_models = {}
|
||||
for k, v in models.items():
|
||||
if any([re.match(pattern, k) for pattern in patterns]):
|
||||
filter_models[k] = v
|
||||
for pattern in args.models:
|
||||
filter_models.update({
|
||||
name: models[name]
|
||||
for name in fnmatch.filter(models, pattern + '*')
|
||||
})
|
||||
if len(filter_models) == 0:
|
||||
print('No model found, please specify models in:')
|
||||
print('\n'.join(models.keys()))
|
||||
logger.error('No model found, please specify models in:\n' +
|
||||
'\n'.join(models.keys()))
|
||||
return
|
||||
models = filter_models
|
||||
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@
|
|||
- Name: swin-small_16xb64_in1k
|
||||
Cycle: month
|
||||
|
||||
- Name: vit-base-p16_pt-32xb128-mae_in1k
|
||||
- Name: vit-base-p16_32xb128-mae_in1k
|
||||
Cycle: month
|
||||
|
||||
- Name: resnet50_8xb256-rsb-a1-600e_in1k
|
||||
|
|
@ -34,53 +34,85 @@
|
|||
- Name: regnetx-1.6gf_8xb128_in1k
|
||||
Cycle: half-year
|
||||
|
||||
- Name: van-small_8xb128_in1k
|
||||
Cycle: no-training
|
||||
- Name: conformer-small-p32_8xb128_in1k
|
||||
Cycle: half-year
|
||||
|
||||
- Name: res2net50-w14-s8_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: convnext-small_32xb128_in1k
|
||||
Cycle: month
|
||||
|
||||
- Name: repvgg-A2_3rdparty_4xb64-coslr-120e_in1k
|
||||
Cycle: no-training
|
||||
- Name: mobilenet-v3-small_8xb128_in1k
|
||||
Cycle: half-year
|
||||
|
||||
- Name: tnt-small-p16_3rdparty_in1k
|
||||
Cycle: no-training
|
||||
- Name: mobileone-s2_8xb32_in1k
|
||||
Cycle: quarter
|
||||
|
||||
- Name: mlp-mixer-base-p16_3rdparty_64xb64_in1k
|
||||
Cycle: no-training
|
||||
- Name: repvgg-b2g4_8xb32_in1k
|
||||
Cycle: half-year
|
||||
|
||||
- Name: conformer-small-p16_3rdparty_8xb128_in1k
|
||||
Cycle: no-training
|
||||
- Name: barlowtwins_resnet50_8xb256-coslr-300e_in1k
|
||||
Cycle: half-year
|
||||
Downstream: resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k
|
||||
|
||||
- Name: twins-pcpvt-base_3rdparty_8xb128_in1k
|
||||
Cycle: no-training
|
||||
- Name: beit_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: beit-base-p16_beit-pre_8xb128-coslr-100e_in1k
|
||||
|
||||
- Name: efficientnet-b0_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k
|
||||
|
||||
- Name: convnext-small_3rdparty_32xb128_in1k
|
||||
Cycle: no-training
|
||||
- Name: byol_resnet50_16xb256-coslr-200e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: resnet50_byol-pre_8xb512-linear-coslr-90e_in1k
|
||||
|
||||
- Name: hrnet-w18_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: cae_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
Cycle: half-year
|
||||
Downstream: beit-base-p16_cae-pre_8xb128-coslr-100e_in1k
|
||||
|
||||
- Name: repmlp-base_3rdparty_8xb64_in1k
|
||||
Cycle: no-training
|
||||
- Name: densecl_resnet50_8xb32-coslr-200e_in1k
|
||||
Cycle: half-year
|
||||
Downstream: resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k
|
||||
|
||||
- Name: wide-resnet50_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k
|
||||
Cycle: half-year
|
||||
Downstream: vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k
|
||||
|
||||
- Name: cspresnet50_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
|
||||
Cycle: month
|
||||
Downstream: vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
|
||||
- Name: convmixer-768-32_10xb64_in1k
|
||||
Cycle: no-training
|
||||
- Name: maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: vit-base-p16_maskfeat-pre_8xb256-coslr-100e_in1k
|
||||
|
||||
- Name: densenet169_4xb256_in1k
|
||||
Cycle: no-training
|
||||
- Name: milan_vit-base-p16_16xb256-amp-coslr-400e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k
|
||||
|
||||
- Name: poolformer-s24_3rdparty_32xb128_in1k
|
||||
Cycle: no-training
|
||||
- Name: mixmim_mixmim-base_16xb128-coslr-300e_in1k
|
||||
Cycle: half-year
|
||||
Downstream: mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k
|
||||
|
||||
- Name: inception-v3_3rdparty_8xb32_in1k
|
||||
Cycle: no-training
|
||||
- Name: mocov2_resnet50_8xb32-coslr-200e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: resnet50_mocov2-pre_8xb32-linear-steplr-100e_in1k
|
||||
|
||||
- Name: mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k
|
||||
Cycle: month
|
||||
Downstream: vit-small-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
|
||||
- Name: simclr_resnet50_16xb256-coslr-200e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
|
||||
- Name: simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px
|
||||
Cycle: month
|
||||
Downstream: swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px
|
||||
|
||||
- Name: simsiam_resnet50_8xb32-coslr-100e_in1k
|
||||
Cycle: quarter
|
||||
Downstream: resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k
|
||||
|
||||
- Name: swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px
|
||||
Cycle: half-year
|
||||
Downstream: resnet50_swav-pre_8xb32-linear-coslr-100e_in1k
|
||||
|
|
|
|||
|
|
@ -0,0 +1,30 @@
|
|||
from pathlib import Path
|
||||
|
||||
HTTP_PREFIX = 'https://download.openmmlab.com/'
|
||||
MMCLS_ROOT = Path(__file__).absolute().parents[2]
|
||||
METRICS_MAP = {
|
||||
'Top 1 Accuracy': 'accuracy/top1',
|
||||
'Top 5 Accuracy': 'accuracy/top5',
|
||||
'Recall@1': 'retrieval/Recall@1',
|
||||
}
|
||||
|
||||
|
||||
def substitute_weights(download_link, root):
|
||||
if 's3://' in root:
|
||||
from mmengine.fileio.backends import PetrelBackend
|
||||
from petrel_client.common.exception import AccessDeniedError
|
||||
file_backend = PetrelBackend()
|
||||
checkpoint = file_backend.join_path(root,
|
||||
download_link[len(HTTP_PREFIX):])
|
||||
try:
|
||||
exists = file_backend.exists(checkpoint)
|
||||
except AccessDeniedError:
|
||||
exists = False
|
||||
else:
|
||||
checkpoint = Path(root) / download_link[len(HTTP_PREFIX):]
|
||||
exists = checkpoint.exists()
|
||||
|
||||
if exists:
|
||||
return str(checkpoint)
|
||||
else:
|
||||
return None
|
||||
|
|
@ -69,10 +69,17 @@ def parse_args():
|
|||
parser = argparse.ArgumentParser(description=prog_description)
|
||||
parser.add_argument('--src', type=Path, help='The path of the matafile.')
|
||||
parser.add_argument('--out', '-o', type=Path, help='The output path.')
|
||||
parser.add_argument(
|
||||
'--inplace',
|
||||
'-i',
|
||||
action='store_true',
|
||||
help='Modify the source metafile inplace.')
|
||||
parser.add_argument(
|
||||
'--view', action='store_true', help='Only pretty print the metafile.')
|
||||
parser.add_argument('--csv', type=str, help='Use a csv to update models.')
|
||||
args = parser.parse_args()
|
||||
if args.inplace:
|
||||
args.out = args.src
|
||||
return args
|
||||
|
||||
|
||||
|
|
@ -82,6 +89,7 @@ def get_flops(config_path):
|
|||
from fvcore.nn import FlopCountAnalysis, parameter_count
|
||||
from mmengine.config import Config
|
||||
from mmengine.dataset import Compose
|
||||
from mmengine.model.utils import revert_sync_batchnorm
|
||||
from mmengine.registry import DefaultScope
|
||||
|
||||
import mmpretrain.datasets # noqa: F401
|
||||
|
|
@ -109,6 +117,8 @@ def get_flops(config_path):
|
|||
resolution = (224, 224)
|
||||
|
||||
model = init_model(cfg, device='cpu')
|
||||
model = revert_sync_batchnorm(model)
|
||||
model.eval()
|
||||
|
||||
with torch.no_grad():
|
||||
model.forward = model.extract_feat
|
||||
|
|
@ -265,8 +275,9 @@ def fill_model_by_prompt(model: dict, defaults: dict):
|
|||
if model.get('Converted From') is None and model.get(
|
||||
'Weights') is not None:
|
||||
if Confirm.ask(
|
||||
'Is the checkpoint is converted from [red]other repository[/]?'
|
||||
):
|
||||
'Is the checkpoint is converted '
|
||||
'from [red]other repository[/]?',
|
||||
default=False):
|
||||
converted_from = {}
|
||||
converted_from['Weights'] = prompt(
|
||||
'Please fill the original checkpoint download link: ')
|
||||
|
|
@ -280,7 +291,7 @@ def fill_model_by_prompt(model: dict, defaults: dict):
|
|||
|
||||
order = [
|
||||
'Name', 'Metadata', 'In Collection', 'Results', 'Weights', 'Config',
|
||||
'Converted From'
|
||||
'Converted From', 'Downstream'
|
||||
]
|
||||
model = {k: model[k] for k in sorted(model.keys(), key=order.index)}
|
||||
return model
|
||||
|
|
@ -315,8 +326,8 @@ def update_model_by_dict(model: dict, update_dict: dict, defaults: dict):
|
|||
model['Metadata']['Parameters'] = params
|
||||
|
||||
# Metadata.Training Data
|
||||
if 'metadata.training data' in update_dict:
|
||||
train_data = update_dict['metadata.training data'].strip()
|
||||
if 'training dataset' in update_dict:
|
||||
train_data = update_dict['training dataset'].strip()
|
||||
train_data = re.split(r'\s+', train_data)
|
||||
if len(train_data) > 1:
|
||||
model['Metadata']['Training Data'] = train_data
|
||||
|
|
@ -324,8 +335,8 @@ def update_model_by_dict(model: dict, update_dict: dict, defaults: dict):
|
|||
model['Metadata']['Training Data'] = train_data[0]
|
||||
|
||||
# Results.Dataset
|
||||
if 'results.dataset' in update_dict:
|
||||
test_data = update_dict['results.dataset'].strip()
|
||||
if 'test dataset' in update_dict:
|
||||
test_data = update_dict['test dataset'].strip()
|
||||
results = model.get('Results') or [{}]
|
||||
result = results[0]
|
||||
result['Dataset'] = test_data
|
||||
|
|
@ -333,8 +344,8 @@ def update_model_by_dict(model: dict, update_dict: dict, defaults: dict):
|
|||
|
||||
# Results.Metrics.Top 1 Accuracy
|
||||
result = None
|
||||
if 'results.metrics.top 1 accuracy' in update_dict:
|
||||
top1 = update_dict['results.metrics.top 1 accuracy']
|
||||
if 'top-1' in update_dict:
|
||||
top1 = update_dict['top-1']
|
||||
results = model.get('Results') or [{}]
|
||||
result = results[0]
|
||||
result.setdefault('Metrics', {})
|
||||
|
|
@ -343,8 +354,8 @@ def update_model_by_dict(model: dict, update_dict: dict, defaults: dict):
|
|||
model['Results'] = results
|
||||
|
||||
# Results.Metrics.Top 5 Accuracy
|
||||
if 'results.metrics.top 5 accuracy' in update_dict:
|
||||
top5 = update_dict['results.metrics.top 5 accuracy']
|
||||
if 'top-5' in update_dict:
|
||||
top5 = update_dict['top-5']
|
||||
results = model.get('Results') or [{}]
|
||||
result = results[0]
|
||||
result.setdefault('Metrics', {})
|
||||
|
|
@ -374,7 +385,7 @@ def update_model_by_dict(model: dict, update_dict: dict, defaults: dict):
|
|||
|
||||
order = [
|
||||
'Name', 'Metadata', 'In Collection', 'Results', 'Weights', 'Config',
|
||||
'Converted From'
|
||||
'Converted From', 'Downstream'
|
||||
]
|
||||
model = {k: model[k] for k in sorted(model.keys(), key=order.index)}
|
||||
return model
|
||||
|
|
@ -396,6 +407,17 @@ def format_model(model: dict):
|
|||
title='Model')
|
||||
|
||||
|
||||
def order_models(model):
|
||||
order = []
|
||||
order.append(int('Downstream' not in model))
|
||||
order.append(int('3rdparty' in model['Name']))
|
||||
order.append(model.get('Metadata', {}).get('Parameters', 0))
|
||||
order.append(model.get('Metadata', {}).get('FLOPs', 0))
|
||||
order.append(len(model['Name']))
|
||||
|
||||
return tuple(order)
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
|
||||
|
|
@ -446,13 +468,12 @@ def main():
|
|||
console.print(format_model(model))
|
||||
updated_models.append(model)
|
||||
|
||||
while Confirm.ask('Add new model?'):
|
||||
while Confirm.ask('Add new model?', default=False):
|
||||
model = fill_model_by_prompt({}, model_defaults)
|
||||
updated_models.append(model)
|
||||
|
||||
# Save updated models even error happened.
|
||||
updated_models.sort(key=lambda item: (item.get('Metadata', {}).get(
|
||||
'FLOPs', 0), len(item['Name'])))
|
||||
updated_models.sort(key=order_models)
|
||||
if args.out is not None:
|
||||
with open(args.out, 'w') as f:
|
||||
yaml_dump({'Collections': [collection]}, f)
|
||||
|
|
|
|||
|
|
@ -2,7 +2,6 @@
|
|||
import argparse
|
||||
import re
|
||||
import warnings
|
||||
from collections import OrderedDict
|
||||
from pathlib import Path
|
||||
|
||||
from modelindex.load_model_index import load
|
||||
|
|
@ -108,6 +107,7 @@ def parse_args():
|
|||
'--table', action='store_true', help='Only generate summary tables')
|
||||
parser.add_argument(
|
||||
'--update', type=str, help='Update the specified readme file.')
|
||||
parser.add_argument('--out', type=str, help='Output to the file.')
|
||||
parser.add_argument(
|
||||
'--update-items',
|
||||
type=str,
|
||||
|
|
@ -431,7 +431,12 @@ def main():
|
|||
if 'citation' not in content:
|
||||
content['citation'] = '## Citation\n```bibtex\n```\n'
|
||||
|
||||
print(combine_readme(content))
|
||||
content = combine_readme(content)
|
||||
if args.out is not None:
|
||||
with open(args.out, 'w') as f:
|
||||
f.write(content)
|
||||
else:
|
||||
print(content)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/barlowtwins/benchmarks/resnet50_8xb32-linear-coslr-
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :-------------------------------------------- | :--------: | :-------: | :------------------------------------------------------: | :------------------------------------------------------------------------------: |
|
||||
| `barlowtwins_resnet50_8xb256-coslr-300e_in1k` | N/A | N/A | [config](barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.json) |
|
||||
| `barlowtwins_resnet50_8xb256-coslr-300e_in1k` | 174.54 | 4.11 | [config](barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k` | [BARLOWTWINS](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) | N/A | N/A | 71.80 | [config](benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.json) |
|
||||
| `resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k` | [BARLOWTWINS](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) | 25.56 | 4.11 | 71.80 | [config](benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,30 +9,36 @@ Collections:
|
|||
- ResNet
|
||||
- BarlowTwins
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2103.03230
|
||||
Title: "Barlow Twins: Self-Supervised Learning via Redundancy Reduction"
|
||||
Title: 'Barlow Twins: Self-Supervised Learning via Redundancy Reduction'
|
||||
URL: https://arxiv.org/abs/2103.03230
|
||||
README: configs/barlowtwins/README.md
|
||||
|
||||
Models:
|
||||
- Name: barlowtwins_resnet50_8xb256-coslr-300e_in1k
|
||||
In Collection: BarlowTwins
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 4109364224
|
||||
Parameters: 174535744
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BarlowTwins
|
||||
Results: null
|
||||
Config: configs/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth
|
||||
Config: configs/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k
|
||||
- Name: resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k
|
||||
In Collection: BarlowTwins
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 256
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BarlowTwins
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 71.8
|
||||
Config: configs/barlowtwins/benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth
|
||||
Config: configs/barlowtwins/benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -12,8 +12,8 @@ Collections:
|
|||
- Scaled Dot-Product Attention
|
||||
- Tanh Activation
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2106.08254
|
||||
Title: 'BEiT: BERT Pre-Training of Image Transformers'
|
||||
URL: https://arxiv.org/abs/2106.08254
|
||||
README: configs/beit/README.md
|
||||
Code:
|
||||
URL: https://github.com/open-mmlab/mmclassification/blob/dev-1.x/mmcls/models/backbones/beit.py
|
||||
|
|
@ -21,39 +21,41 @@ Collections:
|
|||
|
||||
Models:
|
||||
- Name: beit_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
In Collection: BEiT
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86530984
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BEiT
|
||||
Results: null
|
||||
Config: configs/beit/beit_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth
|
||||
Config: configs/beit/beit_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- beit-base-p16_beit-pre_8xb128-coslr-100e_in1k
|
||||
- Name: beit-base-p16_beit-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: BEiT
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86530984
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BEiT
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.1
|
||||
Config: configs/beit/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth
|
||||
Config: configs/beit/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
- Name: beit-base-p16_beit-in21k-pre_3rdparty_in1k
|
||||
In Collection: BEiT
|
||||
Metadata:
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86530984
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: BEiT
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
|
|
@ -61,7 +63,7 @@ Models:
|
|||
Top 1 Accuracy: 85.28
|
||||
Top 5 Accuracy: 97.59
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/beit/beit-base_3rdparty_in1k_20221114-c0a4df23.pth
|
||||
Config: configs/beit/benchmarks/beit-base-p16_8xb64_in1k.py
|
||||
Converted From:
|
||||
Weights: https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_224_pt22k_ft22kto1k.pth
|
||||
Code: https://github.com/microsoft/unilm/tree/master/beit
|
||||
Config: configs/beit/benchmarks/beit-base-p16_8xb64_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/beitv2/benchmarks/beit-base-p16_8xb128-coslr-100e_i
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :------------------------------------------------ | :--------: | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------------------: |
|
||||
| `beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k` | N/A | N/A | [config](beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.json) |
|
||||
| `beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k` | 192.81 | 17.58 | [config](beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
|
||||
| :-------------------------------------- | :----------------------------------------: | :--------: | :-------: | :-------: | :-------: | :--------------------------------------: | :----------------------------------------: |
|
||||
| `beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k` | [BEITV2](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth) | N/A | N/A | 85.00 | N/A | [config](benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.json) |
|
||||
| `beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k` | [BEITV2](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth) | 86.53 | 17.58 | 85.00 | N/A | [config](benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.json) |
|
||||
| `beit-base-p16_beitv2-in21k-pre_3rdparty_in1k`\* | BEITV2 ImageNet-21k | 86.53 | 17.58 | 86.47 | 97.99 | [config](benchmarks/beit-base-p16_8xb64_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/beit/beitv2-base_3rdparty_in1k_20221114-73e11905.pth) |
|
||||
|
||||
*Models with * are converted from the [official repo](https://github.com/microsoft/unilm/tree/master/beit2). The config files of these models are only for inference. We haven't reprodcue the training results.*
|
||||
|
|
|
|||
|
|
@ -12,8 +12,8 @@ Collections:
|
|||
- Scaled Dot-Product Attention
|
||||
- Tanh Activation
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2208.06366
|
||||
Title: 'BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers'
|
||||
URL: https://arxiv.org/abs/2208.06366
|
||||
README: configs/beitv2/README.md
|
||||
Code:
|
||||
URL: https://github.com/open-mmlab/mmclassification/blob/dev-1.x/mmcls/models/backbones/beit.py
|
||||
|
|
@ -21,35 +21,41 @@ Collections:
|
|||
|
||||
Models:
|
||||
- Name: beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
In Collection: BEiTv2
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 17581223424
|
||||
Parameters: 192811376
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BEiTv2
|
||||
Results: null
|
||||
Config: configs/beitv2/beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth
|
||||
Config: configs/beitv2/beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k
|
||||
- Name: beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: BEiTv2
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86530984
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BEiTv2
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.0
|
||||
Config: configs/beitv2/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth
|
||||
Config: configs/beitv2/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
- Name: beit-base-p16_beitv2-in21k-pre_3rdparty_in1k
|
||||
In Collection: BEiTv2
|
||||
Metadata:
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86530984
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: BEiTv2
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
|
|
@ -57,7 +63,7 @@ Models:
|
|||
Top 1 Accuracy: 86.47
|
||||
Top 5 Accuracy: 97.99
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/beit/beitv2-base_3rdparty_in1k_20221114-73e11905.pth
|
||||
Config: configs/beitv2/benchmarks/beit-base-p16_8xb64_in1k.py
|
||||
Converted From:
|
||||
Weights: https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21kto1k.pth
|
||||
Code: https://github.com/microsoft/unilm/tree/master/beit2
|
||||
Config: configs/beitv2/benchmarks/beit-base-p16_8xb64_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/byol/benchmarks/resnet50_8xb512-linear-coslr-90e_in
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :-------------------------------------- | :--------: | :-------: | :------------------------------------------------: | :------------------------------------------------------------------------------------------: |
|
||||
| `byol_resnet50_16xb256-coslr-200e_in1k` | N/A | N/A | [config](byol_resnet50_16xb256-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.json) |
|
||||
| `byol_resnet50_16xb256-coslr-200e_in1k` | 68.02 | 4.11 | [config](byol_resnet50_16xb256-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_byol-pre_8xb512-linear-coslr-90e_in1k` | [BYOL](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth) | N/A | N/A | 71.80 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.json) |
|
||||
| `resnet50_byol-pre_8xb512-linear-coslr-90e_in1k` | [BYOL](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth) | 25.56 | 4.11 | 71.80 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,30 +9,36 @@ Collections:
|
|||
- ResNet
|
||||
- BYOL
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2006.07733
|
||||
Title: "Bootstrap your own latent: A new approach to self-supervised Learning"
|
||||
Title: 'Bootstrap your own latent: A new approach to self-supervised Learning'
|
||||
URL: https://arxiv.org/abs/2006.07733
|
||||
README: configs/byol/README.md
|
||||
|
||||
Models:
|
||||
- Name: byol_resnet50_16xb256-coslr-200e_in1k
|
||||
In Collection: BYOL
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 68024448
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BYOL
|
||||
Results: null
|
||||
Config: configs/byol/byol_resnet50_16xb256-coslr-200e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth
|
||||
Config: configs/byol/byol_resnet50_16xb256-coslr-200e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_byol-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: resnet50_byol-pre_8xb512-linear-coslr-90e_in1k
|
||||
In Collection: BYOL
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: BYOL
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 71.8
|
||||
Config: configs/byol/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth
|
||||
Config: configs/byol/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ print(predict['pred_score'])
|
|||
import torch
|
||||
from mmpretrain import get_model
|
||||
|
||||
model = get_model('cae_vit-base-p16_8xb256-amp-coslr-300e_in1k', pretrained=True)
|
||||
model = get_model('cae_beit-base-p16_8xb256-amp-coslr-300e_in1k', pretrained=True)
|
||||
inputs = torch.rand(1, 3, 224, 224)
|
||||
out = model(inputs)
|
||||
print(type(out))
|
||||
|
|
@ -48,7 +48,7 @@ Prepare your dataset according to the [docs](https://mmclassification.readthedoc
|
|||
Train:
|
||||
|
||||
```shell
|
||||
python tools/train.py configs/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
python tools/train.py configs/cae/cae_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
```
|
||||
|
||||
Test:
|
||||
|
|
@ -63,15 +63,15 @@ python tools/test.py configs/cae/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k
|
|||
|
||||
### Pretrained models
|
||||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :-------------------------------------------- | :--------: | :-------: | :------------------------------------------------------: | :------------------------------------------------------------------------------: |
|
||||
| `cae_vit-base-p16_8xb256-amp-coslr-300e_in1k` | N/A | N/A | [config](cae_vit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.json) |
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :--------------------------------------------- | :--------: | :-------: | :-------------------------------------------------------: | :----------------------------------------------------------------------------: |
|
||||
| `cae_beit-base-p16_8xb256-amp-coslr-300e_in1k` | 288.43 | 17.58 | [config](cae_beit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `beit-base-p16_cae-pre_8xb128-coslr-100e_in1k` | [CAE](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.pth) | N/A | N/A | 83.20 | [config](benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.json) |
|
||||
| `beit-base-p16_cae-pre_8xb128-coslr-100e_in1k` | [CAE](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.pth) | 86.68 | 17.58 | 83.20 | [config](benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -8,30 +8,36 @@ Collections:
|
|||
Architecture:
|
||||
- ViT
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2202.03026
|
||||
Title: "Context Autoencoder for Self-Supervised Representation Learning"
|
||||
Title: Context Autoencoder for Self-Supervised Representation Learning
|
||||
URL: https://arxiv.org/abs/2202.03026
|
||||
README: configs/cae/README.md
|
||||
|
||||
Models:
|
||||
- Name: cae_vit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
In Collection: CAE
|
||||
- Name: cae_beit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 17581976064
|
||||
Parameters: 288429952
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: CAE
|
||||
Results: null
|
||||
Config: configs/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k/cae_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221230-808170f3.pth
|
||||
Config: configs/cae/cae_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- beit-base-p16_cae-pre_8xb128-coslr-100e_in1k
|
||||
- Name: beit-base-p16_cae-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: CAE
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581219584
|
||||
Parameters: 86682280
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: CAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.2
|
||||
Config: configs/cae/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth
|
||||
Config: configs/cae/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -20,6 +20,44 @@ Collections:
|
|||
Version: v1.0.0
|
||||
|
||||
Models:
|
||||
- Name: vit-base-p32_clip-openai-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 4364335104
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- OpenAI
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 81.77
|
||||
Top 5 Accuracy: 95.89
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_openai-pre_3rdparty_in1k_20221220-a0182ba9.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_224.openai_ft_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 4364335104
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- LAION-2B
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 82.46
|
||||
Top 5 Accuracy: 96.12
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_laion2b-pre_3rdparty_in1k_20221220-194df57f.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b_ft_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-in12k-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 4364335104
|
||||
|
|
@ -40,64 +78,6 @@ Models:
|
|||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b_ft_in12k_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 4364335104
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- LAION-2B
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 82.46
|
||||
Top 5 Accuracy: 96.12
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_laion2b-pre_3rdparty_in1k_20221220-194df57f.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b_ft_in1k
|
||||
- Name: vit-base-p32_clip-openai-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 4364335104
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- OpenAI
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 81.77
|
||||
Top 5 Accuracy: 95.89
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_openai-pre_3rdparty_in1k_20221220-a0182ba9.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_224.openai_ft_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-in12k-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 12661054464
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- LAION-2B
|
||||
- ImageNet-12k
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.39
|
||||
Top 5 Accuracy: 97.67
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_laion2b-in12k-pre_3rdparty_in1k-384px_20221220-c7757552.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k-384px.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_384.laion2b_ft_in12k_in1k
|
||||
- Name: vit-base-p32_clip-openai-in12k-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 12661054464
|
||||
|
|
@ -118,10 +98,10 @@ Models:
|
|||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_384.openai_ft_in12k_in1k
|
||||
- Name: vit-base-p16_clip-laion2b-in12k-pre_3rdparty_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-in12k-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 16855600128
|
||||
Parameters: 86568424
|
||||
FLOPs: 12661054464
|
||||
Parameters: 88225000
|
||||
Training Data:
|
||||
- LAION-2B
|
||||
- ImageNet-12k
|
||||
|
|
@ -130,14 +110,33 @@ Models:
|
|||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 86.02
|
||||
Top 5 Accuracy: 97.76
|
||||
Top 1 Accuracy: 85.39
|
||||
Top 5 Accuracy: 97.67
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k_20221220-a5e31f8c.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p32_laion2b-in12k-pre_3rdparty_in1k-384px_20221220-c7757552.pth
|
||||
Config: configs/clip/vit-base-p32_pt-64xb64_in1k-384px.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_384.laion2b_ft_in12k_in1k
|
||||
- Name: vit-base-p16_clip-openai-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 16855600128
|
||||
Parameters: 86568424
|
||||
Training Data:
|
||||
- OpenAI
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.3
|
||||
Top 5 Accuracy: 97.5
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_openai-pre_3rdparty_in1k_20221220-c7d9c899.pth
|
||||
Config: configs/clip/vit-base-p16_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in12k_in1k
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in1k
|
||||
- Name: vit-base-p16_clip-laion2b-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 16855600128
|
||||
|
|
@ -177,25 +176,26 @@ Models:
|
|||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in12k_in1k
|
||||
- Name: vit-base-p16_clip-openai-pre_3rdparty_in1k
|
||||
- Name: vit-base-p16_clip-laion2b-in12k-pre_3rdparty_in1k
|
||||
Metadata:
|
||||
FLOPs: 16855600128
|
||||
Parameters: 86568424
|
||||
Training Data:
|
||||
- OpenAI
|
||||
- LAION-2B
|
||||
- ImageNet-12k
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.3
|
||||
Top 5 Accuracy: 97.5
|
||||
Top 1 Accuracy: 86.02
|
||||
Top 5 Accuracy: 97.76
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_openai-pre_3rdparty_in1k_20221220-c7d9c899.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k_20221220-a5e31f8c.pth
|
||||
Config: configs/clip/vit-base-p16_pt-64xb64_in1k.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in1k
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in12k_in1k
|
||||
- Name: vit-base-p32_clip-laion2b-in12k-pre_3rdparty_in1k-448px
|
||||
Metadata:
|
||||
FLOPs: 17202416640
|
||||
|
|
@ -216,26 +216,25 @@ Models:
|
|||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch32_clip_448.laion2b_ft_in12k_in1k
|
||||
- Name: vit-base-p16_clip-laion2b-in12k-pre_3rdparty_in1k-384px
|
||||
- Name: vit-base-p16_clip-openai-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 49370078208
|
||||
Parameters: 86568424
|
||||
Training Data:
|
||||
- LAION-2B
|
||||
- ImageNet-12k
|
||||
- OpenAI
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 87.17
|
||||
Top 5 Accuracy: 98.02
|
||||
Top 1 Accuracy: 86.25
|
||||
Top 5 Accuracy: 97.9
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k-384px_20221220-84ed0cc0.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_openai-pre_3rdparty_in1k-384px_20221220-eb012e87.pth
|
||||
Config: configs/clip/vit-base-p16_pt-64xb64_in1k-384px.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_384.openai_ft_in1k
|
||||
- Name: vit-base-p16_clip-laion2b-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 49370078208
|
||||
|
|
@ -275,22 +274,23 @@ Models:
|
|||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_384.openai_ft_in12k_in1k
|
||||
- Name: vit-base-p16_clip-openai-pre_3rdparty_in1k-384px
|
||||
- Name: vit-base-p16_clip-laion2b-in12k-pre_3rdparty_in1k-384px
|
||||
Metadata:
|
||||
FLOPs: 49370078208
|
||||
Parameters: 86568424
|
||||
Training Data:
|
||||
- OpenAI
|
||||
- LAION-2B
|
||||
- ImageNet-12k
|
||||
- ImageNet-1k
|
||||
In Collection: CLIP
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 86.25
|
||||
Top 5 Accuracy: 97.9
|
||||
Top 1 Accuracy: 87.17
|
||||
Top 5 Accuracy: 98.02
|
||||
Task: Image Classification
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_openai-pre_3rdparty_in1k-384px_20221220-eb012e87.pth
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/clip/clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k-384px_20221220-84ed0cc0.pth
|
||||
Config: configs/clip/vit-base-p16_pt-64xb64_in1k-384px.py
|
||||
Converted From:
|
||||
Code: https://github.com/rwightman/pytorch-image-models
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_384.openai_ft_in1k
|
||||
Weights: https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :--------------------------------------- | :--------: | :-------: | :-------------------------------------------------: | :----------------------------------------------------------------------------------------: |
|
||||
| `densecl_resnet50_8xb32-coslr-200e_in1k` | N/A | N/A | [config](densecl_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.json) |
|
||||
| `densecl_resnet50_8xb32-coslr-200e_in1k` | 64.85 | 4.11 | [config](densecl_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k` | [DENSECL](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) | N/A | N/A | 63.50 | [config](benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.json) |
|
||||
| `resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k` | [DENSECL](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) | 25.56 | 4.11 | 63.50 | [config](benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,30 +9,36 @@ Collections:
|
|||
Architecture:
|
||||
- ResNet
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2011.09157
|
||||
Title: "Dense contrastive learning for self-supervised visual pre-training"
|
||||
Title: Dense contrastive learning for self-supervised visual pre-training
|
||||
URL: https://arxiv.org/abs/2011.09157
|
||||
README: configs/densecl/README.md
|
||||
|
||||
Models:
|
||||
- Name: densecl_resnet50_8xb32-coslr-200e_in1k
|
||||
In Collection: DenseCL
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 256
|
||||
FLOPs: 4109364224
|
||||
Parameters: 64850560
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: DenseCL
|
||||
Results: null
|
||||
Config: configs/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth
|
||||
Config: configs/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k
|
||||
- Name: resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k
|
||||
In Collection: DenseCL
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 256
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: DenseCL
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 63.5
|
||||
Config: configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth
|
||||
Config: configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -21,7 +21,7 @@ We launch EVA, a vision-centric foundation model to explore the limits of visual
|
|||
```python
|
||||
from mmpretrain import inference_model
|
||||
|
||||
predict = inference_model('beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-336px', 'demo/bird.JPEG')
|
||||
predict = inference_model('vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k', 'demo/bird.JPEG')
|
||||
print(predict['pred_class'])
|
||||
print(predict['pred_score'])
|
||||
```
|
||||
|
|
@ -32,7 +32,7 @@ print(predict['pred_score'])
|
|||
import torch
|
||||
from mmpretrain import get_model
|
||||
|
||||
model = get_model('beit-g-p14_3rdparty-eva_30m', pretrained=True)
|
||||
model = get_model('eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k', pretrained=True)
|
||||
inputs = torch.rand(1, 3, 224, 224)
|
||||
out = model(inputs)
|
||||
print(type(out))
|
||||
|
|
@ -54,7 +54,7 @@ python tools/train.py configs/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_
|
|||
Test:
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/eva/eva-g-p14_8xb16_in1k-336px.py https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px_20221213-210f9071.pth
|
||||
python tools/test.py configs/eva/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth
|
||||
```
|
||||
|
||||
<!-- [TABS-END] -->
|
||||
|
|
@ -65,12 +65,12 @@ python tools/test.py configs/eva/eva-g-p14_8xb16_in1k-336px.py https://download.
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :--------------------------------------------------- | :--------: | :-------: | :-------------------------------------------------------------: | :----------------------------------------------------------------: |
|
||||
| `beit-g-p14_3rdparty-eva_30m`\* | 1011.60 | 267.17 | [config](eva-g-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_3rdparty_30m_20221213-3b7aca97.pth) |
|
||||
| `beit-g-p16_3rdparty-eva_30m`\* | 1011.32 | 203.52 | [config](eva-g-p16_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p16_3rdparty_30m_20221213-7bed23ee.pth) |
|
||||
| `beit-g-p14_eva-30m-pre_3rdparty_in21k`\* | 1011.60 | 267.17 | [config](eva-g-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) |
|
||||
| `eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k` | 111.78 | 17.58 | [config](eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.json) |
|
||||
| `beit-l-p14_3rdparty-eva_in21k`\* | 303.18 | 81.08 | [config](eva-l-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth) |
|
||||
| `beit-l-p14_eva-pre_3rdparty_in21k`\* | 303.18 | 81.08 | [config](eva-l-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in21k_20221213-8f194fa2.pth) |
|
||||
| `eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k` | N/A | N/A | [config](eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.json) |
|
||||
| `beit-g-p16_3rdparty-eva_30m`\* | 1011.32 | 203.52 | [config](eva-g-p16_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p16_3rdparty_30m_20221213-7bed23ee.pth) |
|
||||
| `beit-g-p14_3rdparty-eva_30m`\* | 1011.60 | 267.17 | [config](eva-g-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_3rdparty_30m_20221213-3b7aca97.pth) |
|
||||
| `beit-g-p14_eva-30m-pre_3rdparty_in21k`\* | 1011.60 | 267.17 | [config](eva-g-p14_headless.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) |
|
||||
|
||||
*Models with * are converted from the [official repo](https://github.com/baaivision/EVA). The config files of these models are only for inference. We haven't reprodcue the training results.*
|
||||
|
||||
|
|
@ -78,14 +78,14 @@ python tools/test.py configs/eva/eva-g-p14_8xb16_in1k-336px.py https://download.
|
|||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
|
||||
| :-------------------------------------- | :----------------------------------------: | :--------: | :-------: | :-------: | :-------: | :--------------------------------------: | :----------------------------------------: |
|
||||
| `beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-336px`\* | [EVA merged-30M ImageNet-21k](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) | 1013.01 | 620.64 | 89.61 | 98.93 | [config](eva-g-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px_20221213-210f9071.pth) |
|
||||
| `beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-560px`\* | [EVA merged-30M ImageNet-21k](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) | 1014.45 | 1906.76 | 89.71 | 98.96 | [config](eva-g-p14_8xb16_in1k-560px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-560px_20221213-fa1c3652.pth) |
|
||||
| `beit-l-p14_eva-pre_3rdparty_in1k-336px`\* | [EVA](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth) | 304.53 | 191.10 | 88.66 | 98.75 | [config](eva-l-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-336px_20221214-07785cfd.pth) |
|
||||
| `beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px`\* | EVA ImageNet-21k | 304.53 | 191.10 | 89.17 | 98.86 | [config](eva-l-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px_20221213-f25b7634.pth) |
|
||||
| `vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k` | [EVA MAE STYLE](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) | 86.57 | 17.58 | 83.70 | N/A | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.json) |
|
||||
| `vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k` | [EVA MAE STYLE](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) | 86.57 | 17.58 | 69.00 | N/A | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.json) |
|
||||
| `beit-l-p14_eva-pre_3rdparty_in1k-196px`\* | [EVA](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth) | 304.14 | 61.57 | 87.94 | 98.5 | [config](eva-l-p14_8xb16_in1k-196px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-196px_20221214-2adf4d28.pth) |
|
||||
| `beit-l-p14_eva-in21k-pre_3rdparty_in1k-196px`\* | EVA ImageNet-21k | 304.14 | 61.57 | 88.58 | 98.65 | [config](eva-l-p14_8xb16_in1k-196px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-196px_20221213-b730c7e7.pth) |
|
||||
| `vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k` | [EVA mae-style](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) | N/A | N/A | 83.70 | N/A | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.json) |
|
||||
| `vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k` | [EVA mae-style](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth) | N/A | N/A | 69.00 | N/A | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.json) |
|
||||
| `beit-l-p14_eva-pre_3rdparty_in1k-336px`\* | [EVA](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth) | 304.53 | 191.10 | 88.66 | 98.75 | [config](eva-l-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-336px_20221214-07785cfd.pth) |
|
||||
| `beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px`\* | EVA ImageNet-21k | 304.53 | 191.10 | 89.17 | 98.86 | [config](eva-l-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px_20221213-f25b7634.pth) |
|
||||
| `beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-336px`\* | [EVA 30M ImageNet-21k](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) | 1013.01 | 620.64 | 89.61 | 98.93 | [config](eva-g-p14_8xb16_in1k-336px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px_20221213-210f9071.pth) |
|
||||
| `beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-560px`\* | [EVA 30M ImageNet-21k](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth) | 1014.45 | 1906.76 | 89.71 | 98.96 | [config](eva-g-p14_8xb16_in1k-560px.py) | [model](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-560px_20221213-fa1c3652.pth) |
|
||||
|
||||
*Models with * are converted from the [official repo](https://github.com/baaivision/EVA). The config files of these models are only for inference. We haven't reprodcue the training results.*
|
||||
|
||||
|
|
|
|||
|
|
@ -12,64 +12,214 @@ Collections:
|
|||
- Scaled Dot-Product Attention
|
||||
- Tanh Activation
|
||||
Paper:
|
||||
Title: 'EVA: Exploring the Limits of Masked Visual Representation Learning at
|
||||
Scale'
|
||||
URL: https://arxiv.org/abs/2211.07636
|
||||
Title: 'EVA: Exploring the Limits of Masked Visual Representation Learning at Scale'
|
||||
README: configs/eva/README.md
|
||||
Code:
|
||||
URL:
|
||||
Version:
|
||||
URL: null
|
||||
Version: null
|
||||
|
||||
Models:
|
||||
- Name: beit-g-p14_3rdparty-eva_30m
|
||||
In Collection: EVA
|
||||
- Name: eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k
|
||||
Metadata:
|
||||
FLOPs: 267174833024
|
||||
Parameters: 1011596672
|
||||
Training Data:
|
||||
- merged-30M
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_3rdparty_30m_20221213-3b7aca97.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_psz14.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-g-p14_headless.py
|
||||
Downstream:
|
||||
- beit-g-p14_eva-30m-pre_3rdparty_in21k
|
||||
|
||||
- Name: beit-g-p16_3rdparty-eva_30m
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111776512
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth
|
||||
Config: configs/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k
|
||||
- vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k
|
||||
- Name: vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.7
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth
|
||||
Config: configs/eva/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
- Name: vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 69.0
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth
|
||||
Config: configs/eva/benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in1k-196px
|
||||
Metadata:
|
||||
FLOPs: 61565981696
|
||||
Parameters: 304142312
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 87.94
|
||||
Top 5 Accuracy: 98.5
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-196px_20221214-2adf4d28.pth
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-196px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_196px_1k_ft_88p0.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
- Name: beit-l-p14_eva-in21k-pre_3rdparty_in1k-196px
|
||||
Metadata:
|
||||
FLOPs: 61565981696
|
||||
Parameters: 304142312
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 88.58
|
||||
Top 5 Accuracy: 98.65
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-196px_20221213-b730c7e7.pth
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-196px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_196px_21k_to_1k_ft_88p6.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
- Name: beit-l-p14_3rdparty-eva_in21k
|
||||
Metadata:
|
||||
FLOPs: 81075147776
|
||||
Parameters: 303178752
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth
|
||||
Config: configs/eva/eva-l-p14_headless.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Downstream:
|
||||
- beit-l-p14_eva-pre_3rdparty_in21k
|
||||
- beit-l-p14_eva-pre_3rdparty_in1k-336px
|
||||
- beit-l-p14_eva-pre_3rdparty_in1k-196px
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in21k
|
||||
Metadata:
|
||||
FLOPs: 81075147776
|
||||
Parameters: 303178752
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in21k_20221213-8f194fa2.pth
|
||||
Config: configs/eva/eva-l-p14_headless.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_21k_ft.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in1k-336px
|
||||
Metadata:
|
||||
FLOPs: 191100916736
|
||||
Parameters: 304531432
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 88.66
|
||||
Top 5 Accuracy: 98.75
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-336px_20221214-07785cfd.pth
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-336px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_336px_1k_ft_88p65.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Downstream:
|
||||
- beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px
|
||||
- beit-l-p14_eva-in21k-pre_3rdparty_in1k-196px
|
||||
- Name: beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px
|
||||
Metadata:
|
||||
FLOPs: 191100916736
|
||||
Parameters: 304531432
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.17
|
||||
Top 5 Accuracy: 98.86
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px_20221213-f25b7634.pth
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-336px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_336px_21k_to_1k_ft_89p2.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
- Name: beit-g-p16_3rdparty-eva_30m
|
||||
Metadata:
|
||||
FLOPs: 203517463424
|
||||
Parameters: 1011315072
|
||||
Training Data:
|
||||
- merged-30M
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p16_3rdparty_30m_20221213-7bed23ee.pth
|
||||
Config: configs/eva/eva-g-p16_headless.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_psz14to16.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-g-p16_headless.py
|
||||
|
||||
- Name: beit-g-p14_eva-30m-pre_3rdparty_in21k
|
||||
- Name: beit-g-p14_3rdparty-eva_30m
|
||||
Metadata:
|
||||
FLOPs: 267174833024
|
||||
Parameters: 1011596672
|
||||
Training Data:
|
||||
- merged-30M
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_3rdparty_30m_20221213-3b7aca97.pth
|
||||
Config: configs/eva/eva-g-p14_headless.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_psz14.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Downstream:
|
||||
- beit-g-p14_eva-30m-pre_3rdparty_in21k
|
||||
- Name: beit-g-p14_eva-30m-pre_3rdparty_in21k
|
||||
Metadata:
|
||||
FLOPs: 267174833024
|
||||
Parameters: 1011596672
|
||||
Training Data:
|
||||
- merged-30M
|
||||
- ImageNet-21k
|
||||
In Collection: EVA
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth
|
||||
Config: configs/eva/eva-g-p14_headless.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_21k_224px_psz14.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-g-p14_headless.py
|
||||
Downstream:
|
||||
- beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-336px
|
||||
- beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-560px
|
||||
|
||||
- Name: beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-336px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 620642757504
|
||||
Parameters: 1013005672
|
||||
|
|
@ -77,20 +227,19 @@ Models:
|
|||
- merged-30M
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.61
|
||||
Top 5 Accuracy: 98.93
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.61
|
||||
Top 5 Accuracy: 98.93
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px_20221213-210f9071.pth
|
||||
Config: configs/eva/eva-g-p14_8xb16_in1k-336px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_21k_1k_336px_psz14_ema_89p6.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-g-p14_8xb16_in1k-336px.py
|
||||
|
||||
- Name: beit-g-p14_eva-30m-in21k-pre_3rdparty_in1k-560px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 1906761591680
|
||||
Parameters: 1014447464
|
||||
|
|
@ -98,165 +247,15 @@ Models:
|
|||
- merged-30M
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
In Collection: EVA
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.71
|
||||
Top 5 Accuracy: 98.96
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.71
|
||||
Top 5 Accuracy: 98.96
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-560px_20221213-fa1c3652.pth
|
||||
Config: configs/eva/eva-g-p14_8xb16_in1k-560px.py
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_21k_1k_560px_psz14_ema_89p7.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-g-p14_8xb16_in1k-560px.py
|
||||
|
||||
- Name: beit-l-p14_3rdparty-eva_in21k
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 81075147776
|
||||
Parameters: 303178752
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_3rdparty-mim_in21k_20221213-3a5da50b.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_headless.py
|
||||
Downstream:
|
||||
- beit-l-p14_eva-pre_3rdparty_in21k
|
||||
- beit-l-p14_eva-pre_3rdparty_in1k-336px
|
||||
- beit-l-p14_eva-pre_3rdparty_in1k-196px
|
||||
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in21k
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 81075147776
|
||||
Parameters: 303178752
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in21k_20221213-8f194fa2.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_21k_ft.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_headless.py
|
||||
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in1k-336px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 191100916736
|
||||
Parameters: 304531432
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 88.66
|
||||
Top 5 Accuracy: 98.75
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-336px_20221214-07785cfd.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_336px_1k_ft_88p65.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-336px.py
|
||||
Downstream:
|
||||
- beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px
|
||||
- beit-l-p14_eva-in21k-pre_3rdparty_in1k-196px
|
||||
|
||||
- Name: beit-l-p14_eva-in21k-pre_3rdparty_in1k-336px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 191100916736
|
||||
Parameters: 304531432
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 89.17
|
||||
Top 5 Accuracy: 98.86
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px_20221213-f25b7634.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_336px_21k_to_1k_ft_89p2.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-336px.py
|
||||
|
||||
- Name: beit-l-p14_eva-pre_3rdparty_in1k-196px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 61565981696
|
||||
Parameters: 304142312
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 87.94
|
||||
Top 5 Accuracy: 98.50
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in1k-196px_20221214-2adf4d28.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_196px_1k_ft_88p0.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-196px.py
|
||||
|
||||
- Name: beit-l-p14_eva-in21k-pre_3rdparty_in1k-196px
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
FLOPs: 61565981696
|
||||
Parameters: 304142312
|
||||
Training Data:
|
||||
- ImageNet-21k
|
||||
- ImageNet-1k
|
||||
Results:
|
||||
- Dataset: ImageNet-1k
|
||||
Task: Image Classification
|
||||
Metrics:
|
||||
Top 1 Accuracy: 88.58
|
||||
Top 5 Accuracy: 98.65
|
||||
Weights: https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-196px_20221213-b730c7e7.pth
|
||||
Converted From:
|
||||
Weights: https://huggingface.co/BAAI/EVA/blob/main/eva_l_psz14_196px_21k_to_1k_ft_88p6.pt
|
||||
Code: https://github.com/baaivision/EVA
|
||||
Config: configs/eva/eva-l-p14_8xb16_in1k-196px.py
|
||||
|
||||
- Name: eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth
|
||||
Downstream:
|
||||
- vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k
|
||||
- vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k
|
||||
- Name: vit-base-p16_eva-mae-style-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.7
|
||||
Config: configs/eva/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth
|
||||
- Name: vit-base-p16_eva-mae-style-pre_8xb2048-linear-coslr-100e_in1k
|
||||
In Collection: EVA
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 69.0
|
||||
Config: configs/eva/benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
```python
|
||||
from mmpretrain import inference_model
|
||||
|
||||
predict = inference_model('vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k', 'demo/bird.JPEG')
|
||||
predict = inference_model('vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k', 'demo/bird.JPEG')
|
||||
print(predict['pred_class'])
|
||||
print(predict['pred_score'])
|
||||
```
|
||||
|
|
@ -69,7 +69,7 @@ python tools/train.py configs/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
|
|||
Test:
|
||||
|
||||
```shell
|
||||
python tools/test.py configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py None
|
||||
python tools/test.py configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py None
|
||||
```
|
||||
|
||||
<!-- [TABS-END] -->
|
||||
|
|
@ -80,35 +80,35 @@ python tools/test.py configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :---------------------------------------------- | :--------: | :-------: | :--------------------------------------------------------: | :--------------------------------------------------------------------------: |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-300e_in1k` | N/A | N/A | [config](mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-400e_in1k` | N/A | N/A | [config](mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-800e_in1k` | N/A | N/A | [config](mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k` | N/A | N/A | [config](mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-400e_in1k` | N/A | N/A | [config](mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-800e_in1k` | N/A | N/A | [config](mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k` | N/A | N/A | [config](mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.json) |
|
||||
| `mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k` | N/A | N/A | [config](mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-300e_in1k` | 111.91 | 17.58 | [config](mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-400e_in1k` | 111.91 | 17.58 | [config](mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-800e_in1k` | 111.91 | 17.58 | [config](mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.json) |
|
||||
| `mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k` | 111.91 | 17.58 | [config](mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-400e_in1k` | 329.54 | 61.60 | [config](mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-800e_in1k` | 329.54 | 61.60 | [config](mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.json) |
|
||||
| `mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k` | 329.54 | 61.60 | [config](mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.json) |
|
||||
| `mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k` | 657.07 | 167.40 | [config](mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) | N/A | N/A | 60.80 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k` | [MAE 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) | N/A | N/A | 83.10 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) | N/A | N/A | 62.50 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) | N/A | N/A | 83.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) | N/A | N/A | 65.10 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) | N/A | N/A | 83.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) | N/A | N/A | 67.10 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) | N/A | N/A | 83.50 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.json) |
|
||||
| `vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) | N/A | N/A | 70.70 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) | N/A | N/A | 85.20 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) | N/A | N/A | 73.70 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) | N/A | N/A | 85.40 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) | N/A | N/A | 75.50 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) | N/A | N/A | 85.70 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) | N/A | N/A | 86.90 | [config](benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.json) |
|
||||
| `vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) | N/A | N/A | 87.30 | [config](benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.json) |
|
||||
| `vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k` | [MAE 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) | 86.57 | 17.58 | 83.10 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) | 86.57 | 17.58 | 83.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) | 86.57 | 17.58 | 83.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) | 86.57 | 17.58 | 83.50 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.json) |
|
||||
| `vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth) | 86.57 | 17.58 | 60.80 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth) | 86.57 | 17.58 | 62.50 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth) | 86.57 | 17.58 | 65.10 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth) | 86.57 | 17.58 | 67.10 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) | 304.32 | 61.60 | 85.20 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) | 304.32 | 61.60 | 85.40 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) | 304.32 | 61.60 | 85.70 | [config](benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 400-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth) | 304.33 | 61.60 | 70.70 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth) | 304.33 | 61.60 | 73.70 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth) | 304.33 | 61.60 | 75.50 | [config](benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py) | N/A |
|
||||
| `vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) | 632.04 | 167.40 | 86.90 | [config](benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.json) |
|
||||
| `vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px` | [MAE 1600-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth) | 633.03 | 732.13 | 87.30 | [config](benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -8,282 +8,360 @@ Collections:
|
|||
Architecture:
|
||||
- ViT
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2111.06377
|
||||
Title: "Masked Autoencoders Are Scalable Vision Learners"
|
||||
Title: Masked Autoencoders Are Scalable Vision Learners
|
||||
URL: https://arxiv.org/abs/2111.06377
|
||||
README: configs/mae/README.md
|
||||
|
||||
Models:
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111907840
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 60.8
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111907840
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111907840
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111907840
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
|
||||
Metadata:
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
FLOPs: 61603111936
|
||||
Parameters: 329541888
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
|
||||
Downstream:
|
||||
- vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
FLOPs: 61603111936
|
||||
Parameters: 329541888
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
|
||||
Downstream:
|
||||
- vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
FLOPs: 61603111936
|
||||
Parameters: 329541888
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
|
||||
Downstream:
|
||||
- vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
FLOPs: 167400741120
|
||||
Parameters: 657074508
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth
|
||||
Config: configs/mae/mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py
|
||||
Downstream:
|
||||
- vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
- vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
|
||||
- Name: vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.1
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth
|
||||
Downstream:
|
||||
- vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 62.5
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.3
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth
|
||||
Downstream:
|
||||
- vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 65.1
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.3
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
|
||||
- Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth
|
||||
Downstream:
|
||||
- vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
|
||||
- Name: vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 67.1
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.5
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth
|
||||
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth
|
||||
Downstream:
|
||||
- vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
- Name: vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 70.7
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
|
||||
Top 1 Accuracy: 60.8
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 62.5
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 65.1
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 67.1
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
|
||||
Metadata:
|
||||
Epochs: 50
|
||||
Batch Size: 1024
|
||||
FLOPs: 61602103296
|
||||
Parameters: 304324584
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.2
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
|
||||
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth
|
||||
Downstream:
|
||||
- vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 73.7
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 50
|
||||
Batch Size: 1024
|
||||
FLOPs: 61602103296
|
||||
Parameters: 304324584
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.4
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
|
||||
|
||||
- Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth
|
||||
Downstream:
|
||||
- vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
- vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
- Name: vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 75.5
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 50
|
||||
Batch Size: 1024
|
||||
FLOPs: 61602103296
|
||||
Parameters: 304324584
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.7
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
|
||||
|
||||
- Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k
|
||||
In Collection: MAE
|
||||
- Name: vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 1600
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mae/mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth
|
||||
Downstream:
|
||||
- vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
- vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
|
||||
- Name: vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 61603112960
|
||||
Parameters: 304326632
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 70.7
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 61603112960
|
||||
Parameters: 304326632
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 73.7
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 16384
|
||||
FLOPs: 61603112960
|
||||
Parameters: 304326632
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 75.5
|
||||
Weights: null
|
||||
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
|
||||
- Name: vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
|
||||
Metadata:
|
||||
Epochs: 50
|
||||
Batch Size: 1024
|
||||
FLOPs: 167399096320
|
||||
Parameters: 632043240
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 86.9
|
||||
Config: configs/mae/benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth
|
||||
Config: configs/mae/benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py
|
||||
- Name: vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
|
||||
In Collection: MAE
|
||||
Metadata:
|
||||
Epochs: 50
|
||||
Batch Size: 256
|
||||
FLOPs: 732131983360
|
||||
Parameters: 633026280
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MAE
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 87.3
|
||||
Config: configs/mae/benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth
|
||||
Config: configs/mae/benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/maskfeat/benchmarks/vit-base-p16_8xb256-coslr-100e_
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :------------------------------------------------- | :--------: | :-------: | :-----------------------------------------------------------: | :--------------------------------------------------------------------: |
|
||||
| `maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k` | N/A | N/A | [config](maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.json) |
|
||||
| `maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k` | 85.88 | 17.58 | [config](maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `vit-base-p16_maskfeat-pre_8xb256-coslr-100e_in1k` | [MASKFEAT](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth) | N/A | N/A | 83.40 | [config](benchmarks/vit-base-p16_8xb256-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.json) |
|
||||
| `vit-base-p16_maskfeat-pre_8xb256-coslr-100e_in1k` | [MASKFEAT](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth) | 86.57 | 17.58 | 83.40 | [config](benchmarks/vit-base-p16_8xb256-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -8,30 +8,36 @@ Collections:
|
|||
Architecture:
|
||||
- ViT
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2112.09133v1
|
||||
Title: "Masked Feature Prediction for Self-Supervised Visual Pre-Training"
|
||||
Title: Masked Feature Prediction for Self-Supervised Visual Pre-Training
|
||||
URL: https://arxiv.org/abs/2112.09133v1
|
||||
README: configs/maskfeat/README.md
|
||||
|
||||
Models:
|
||||
- Name: maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k
|
||||
In Collection: MaskFeat
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 17581972224
|
||||
Parameters: 85882692
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MaskFeat
|
||||
Results: null
|
||||
Config: configs/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth
|
||||
Config: configs/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_maskfeat-pre_8xb256-coslr-100e_in1k
|
||||
- Name: vit-base-p16_maskfeat-pre_8xb256-coslr-100e_in1k
|
||||
In Collection: MaskFeat
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MaskFeat
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.4
|
||||
Config: configs/maskfeat/benchmarks/vit-base-p16_8xb256-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth
|
||||
Config: configs/maskfeat/benchmarks/vit-base-p16_8xb256-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -83,14 +83,14 @@ python tools/test.py configs/milan/benchmarks/vit-base-p16_8xb128-coslr-100e_in1
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :----------------------------------------------- | :--------: | :-------: | :---------------------------------------------------------: | :------------------------------------------------------------------------: |
|
||||
| `milan_vit-base-p16_16xb256-amp-coslr-400e_in1k` | N/A | N/A | [config](milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.json) |
|
||||
| `milan_vit-base-p16_16xb256-amp-coslr-400e_in1k` | 111.91 | 17.58 | [config](milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `vit-base-p16_milan-pre_8xb128-coslr-100e_in1k` | [MILAN](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) | N/A | N/A | 85.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.json) |
|
||||
| `vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k` | [MILAN](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) | N/A | N/A | 78.90 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.json) |
|
||||
| `vit-base-p16_milan-pre_8xb128-coslr-100e_in1k` | [MILAN](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) | 86.57 | 17.58 | 85.30 | [config](benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.json) |
|
||||
| `vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k` | [MILAN](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth) | 86.57 | 17.58 | 78.90 | [config](benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -8,44 +8,52 @@ Collections:
|
|||
Architecture:
|
||||
- ViT
|
||||
Paper:
|
||||
URL: https://arxiv.org/pdf/2208.06049
|
||||
Title: "MILAN: Masked Image Pretraining on Language Assisted Representation"
|
||||
Title: 'MILAN: Masked Image Pretraining on Language Assisted Representation'
|
||||
URL: https://arxiv.org/pdf/2208.06049
|
||||
README: configs/milan/README.md
|
||||
|
||||
Models:
|
||||
- Name: milan_vit-base-p16_16xb256-amp-coslr-400e_in1k
|
||||
In Collection: MILAN
|
||||
Metadata:
|
||||
Epochs: 400
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 111907584
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MILAN
|
||||
Results: null
|
||||
Config: configs/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth
|
||||
Config: configs/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_milan-pre_8xb128-coslr-100e_in1k
|
||||
- vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k
|
||||
|
||||
- Name: vit-base-p16_milan-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: MILAN
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581215744
|
||||
Parameters: 86566120
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MILAN
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 85.3
|
||||
Config: configs/milan/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth
|
||||
Config: configs/milan/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
||||
- Name: vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k
|
||||
In Collection: MILAN
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 16384
|
||||
FLOPs: 17581972992
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MILAN
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 78.9
|
||||
Config: configs/milan/benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth
|
||||
Config: configs/milan/benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -82,13 +82,13 @@ python tools/test.py configs/mixmim/benchmarks/mixmim-base_8xb128-coslr-100e_in1
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :------------------------------------------- | :--------: | :-------: | :-----------------------------------------------------: | :--------------------------------------------------------------------------------: |
|
||||
| `mixmim_mixmim-base_16xb128-coslr-300e_in1k` | N/A | N/A | [config](mixmim_mixmim-base_16xb128-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.json) |
|
||||
| `mixmim_mixmim-base_16xb128-coslr-300e_in1k` | 114.67 | 16.35 | [config](mixmim_mixmim-base_16xb128-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k` | [MIXMIM](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth) | N/A | N/A | 84.63 | [config](benchmarks/mixmim-base_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.json) |
|
||||
| `mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k` | [MIXMIM](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth) | 88.34 | 16.35 | 84.63 | [config](benchmarks/mixmim-base_8xb128-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -12,7 +12,8 @@ Collections:
|
|||
- Scaled Dot-Product Attention
|
||||
- Tanh Activation
|
||||
Paper:
|
||||
Title: 'MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning'
|
||||
Title: 'MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation
|
||||
Learning'
|
||||
URL: https://arxiv.org/abs/2205.13137
|
||||
README: configs/mixmim/README.md
|
||||
Code:
|
||||
|
|
@ -21,24 +22,30 @@ Collections:
|
|||
|
||||
Models:
|
||||
- Name: mixmim_mixmim-base_16xb128-coslr-300e_in1k
|
||||
In Collection: MixMIM
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 2048
|
||||
FLOPs: 16351906816
|
||||
Parameters: 114665784
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MixMIM
|
||||
Results: null
|
||||
Config: configs/mixmim/mixmim_mixmim-base_16xb128-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth
|
||||
Config: configs/mixmim/mixmim_mixmim-base_16xb128-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k
|
||||
- Name: mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k
|
||||
In Collection: MixMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 1024
|
||||
FLOPs: 16351906816
|
||||
Parameters: 88344352
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MixMIM
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 84.63
|
||||
Config: configs/mixmim/benchmarks/mixmim-base_8xb128-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth
|
||||
Config: configs/mixmim/benchmarks/mixmim-base_8xb128-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/mocov2/benchmarks/resnet50_8xb32-linear-steplr-100e
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :-------------------------------------- | :--------: | :-------: | :------------------------------------------------: | :------------------------------------------------------------------------------------------: |
|
||||
| `mocov2_resnet50_8xb32-coslr-200e_in1k` | N/A | N/A | [config](mocov2_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.json) |
|
||||
| `mocov2_resnet50_8xb32-coslr-200e_in1k` | 55.93 | 4.11 | [config](mocov2_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_mocov2-pre_8xb32-linear-steplr-100e_in1k` | [MOCOV2](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth) | N/A | N/A | 67.50 | [config](benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.json) |
|
||||
| `resnet50_mocov2-pre_8xb32-linear-steplr-100e_in1k` | [MOCOV2](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth) | 25.56 | 4.11 | 67.50 | [config](benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -10,30 +10,36 @@ Collections:
|
|||
- ResNet
|
||||
- MoCo
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2003.04297
|
||||
Title: "Improved Baselines with Momentum Contrastive Learning"
|
||||
Title: Improved Baselines with Momentum Contrastive Learning
|
||||
URL: https://arxiv.org/abs/2003.04297
|
||||
README: configs/mocov2/README.md
|
||||
|
||||
Models:
|
||||
- Name: mocov2_resnet50_8xb32-coslr-200e_in1k
|
||||
In Collection: MoCoV2
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 256
|
||||
FLOPs: 4109364224
|
||||
Parameters: 55933312
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV2
|
||||
Results: null
|
||||
Config: configs/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth
|
||||
Config: configs/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_mocov2-pre_8xb32-linear-steplr-100e_in1k
|
||||
- Name: resnet50_mocov2-pre_8xb32-linear-steplr-100e_in1k
|
||||
In Collection: MoCoV2
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 256
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV2
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 67.5
|
||||
Config: configs/mocov2/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth
|
||||
Config: configs/mocov2/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,24 +65,24 @@ python tools/test.py configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :------------------------------------------------- | :--------: | :-------: | :-----------------------------------------------------------: | :--------------------------------------------------------------------: |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-100e_in1k` | N/A | N/A | [config](mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.json) |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-300e_in1k` | N/A | N/A | [config](mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.json) |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-800e_in1k` | N/A | N/A | [config](mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.json) |
|
||||
| `mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k` | N/A | N/A | [config](mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.json) |
|
||||
| `mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k` | N/A | N/A | [config](mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.json) |
|
||||
| `mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k` | N/A | N/A | [config](mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.json) |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-100e_in1k` | 68.01 | 4.11 | [config](mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.json) |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-300e_in1k` | 68.01 | 4.11 | [config](mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.json) |
|
||||
| `mocov3_resnet50_8xb512-amp-coslr-800e_in1k` | 68.01 | 4.11 | [config](mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.json) |
|
||||
| `mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k` | 84.27 | 4.61 | [config](mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.json) |
|
||||
| `mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k` | 215.68 | 17.58 | [config](mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.json) |
|
||||
| `mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k` | 652.78 | 61.60 | [config](mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_mocov3-100e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth) | N/A | N/A | 69.60 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.json) |
|
||||
| `resnet50_mocov3-300e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth) | N/A | N/A | 72.80 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.json) |
|
||||
| `resnet50_mocov3-800e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth) | N/A | N/A | 74.40 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.json) |
|
||||
| `vit-small-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth) | N/A | N/A | 73.60 | [config](benchmarks/vit-small-p16_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.json) |
|
||||
| `vit-base-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) | N/A | N/A | 76.90 | [config](benchmarks/vit-base-p16_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.json) |
|
||||
| `vit-base-p16_mocov3-pre_8xb64-coslr-150e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) | N/A | N/A | 83.00 | [config](benchmarks/vit-base-p16_8xb64-coslr-150e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.json) |
|
||||
| `vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth) | N/A | N/A | 83.70 | [config](benchmarks/vit-large-p16_8xb64-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.json) |
|
||||
| `resnet50_mocov3-100e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth) | 25.56 | 4.11 | 69.60 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.json) |
|
||||
| `resnet50_mocov3-300e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 300-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth) | 25.56 | 4.11 | 72.80 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.json) |
|
||||
| `resnet50_mocov3-800e-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth) | 25.56 | 4.11 | 74.40 | [config](benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.json) |
|
||||
| `vit-small-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth) | 22.05 | 4.61 | 73.60 | [config](benchmarks/vit-small-p16_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.json) |
|
||||
| `vit-base-p16_mocov3-pre_8xb64-coslr-150e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) | 86.57 | 17.58 | 83.00 | [config](benchmarks/vit-base-p16_8xb64-coslr-150e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.json) |
|
||||
| `vit-base-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth) | 86.57 | 17.58 | 76.90 | [config](benchmarks/vit-base-p16_8xb128-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.json) |
|
||||
| `vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k` | [MOCOV3](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth) | 304.33 | 61.60 | 83.70 | [config](benchmarks/vit-large-p16_8xb64-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -10,158 +10,192 @@ Collections:
|
|||
- ViT
|
||||
- MoCo
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2104.02057
|
||||
Title: "An Empirical Study of Training Self-Supervised Vision Transformers"
|
||||
Title: An Empirical Study of Training Self-Supervised Vision Transformers
|
||||
URL: https://arxiv.org/abs/2104.02057
|
||||
README: configs/mocov3/README.md
|
||||
|
||||
Models:
|
||||
- Name: mocov3_resnet50_8xb512-amp-coslr-100e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 68012160
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_mocov3-100e-pre_8xb128-linear-coslr-90e_in1k
|
||||
- Name: resnet50_mocov3-100e-pre_8xb128-linear-coslr-90e_in1k
|
||||
- Name: mocov3_resnet50_8xb512-amp-coslr-300e_in1k
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 68012160
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_mocov3-300e-pre_8xb128-linear-coslr-90e_in1k
|
||||
- Name: mocov3_resnet50_8xb512-amp-coslr-800e_in1k
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 68012160
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_mocov3-800e-pre_8xb128-linear-coslr-90e_in1k
|
||||
- Name: resnet50_mocov3-100e-pre_8xb128-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 69.6
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth
|
||||
|
||||
- Name: mocov3_resnet50_8xb512-amp-coslr-300e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth
|
||||
Downstream:
|
||||
- resnet50_mocov3-300e-pre_8xb128-linear-coslr-90e_in1k
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
- Name: resnet50_mocov3-300e-pre_8xb128-linear-coslr-90e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 72.8
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth
|
||||
|
||||
- Name: mocov3_resnet50_8xb512-amp-coslr-800e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 800
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth
|
||||
Downstream:
|
||||
- resnet50_mocov3-800e-pre_8xb128-linear-coslr-90e_in1k
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
- Name: resnet50_mocov3-800e-pre_8xb128-linear-coslr-90e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 74.4
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth
|
||||
|
||||
Config: configs/mocov3/benchmarks/resnet50_8xb128-linear-coslr-90e_in1k.py
|
||||
- Name: mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
FLOPs: 4607954304
|
||||
Parameters: 84266752
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth
|
||||
Config: configs/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- vit-small-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
- Name: vit-small-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
FLOPs: 4607954304
|
||||
Parameters: 22050664
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 73.6
|
||||
Config: configs/mocov3/benchmarks/vit-small-p16_8xb128-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth
|
||||
|
||||
Config: configs/mocov3/benchmarks/vit-small-p16_8xb128-linear-coslr-90e_in1k.py
|
||||
- Name: mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
FLOPs: 17581972224
|
||||
Parameters: 215678464
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth
|
||||
Config: configs/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- vit-base-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
- vit-base-p16_mocov3-pre_8xb64-coslr-150e_in1k
|
||||
- Name: vit-base-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 76.9
|
||||
Config: configs/mocov3/benchmarks/vit-base-p16_8xb128-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth
|
||||
- Name: vit-base-p16_mocov3-pre_8xb64-coslr-150e_in1k
|
||||
In Collection: MoCoV3
|
||||
Metadata:
|
||||
Epochs: 150
|
||||
Batch Size: 512
|
||||
FLOPs: 17581972224
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.0
|
||||
Config: configs/mocov3/benchmarks/vit-base-p16_8xb64-coslr-150e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth
|
||||
|
||||
- Name: mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k
|
||||
Config: configs/mocov3/benchmarks/vit-base-p16_8xb64-coslr-150e_in1k.py
|
||||
- Name: vit-base-p16_mocov3-pre_8xb128-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 1024
|
||||
FLOPs: 17581972224
|
||||
Parameters: 86567656
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 76.9
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth
|
||||
Config: configs/mocov3/benchmarks/vit-base-p16_8xb128-linear-coslr-90e_in1k.py
|
||||
- Name: mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k
|
||||
Metadata:
|
||||
Epochs: 300
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth
|
||||
Downstream:
|
||||
- vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k
|
||||
- Name: vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k
|
||||
FLOPs: 61603111936
|
||||
Parameters: 652781568
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth
|
||||
Config: configs/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py
|
||||
Downstream:
|
||||
- vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k
|
||||
- Name: vit-large-p16_mocov3-pre_8xb64-coslr-100e_in1k
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 512
|
||||
FLOPs: 61603111936
|
||||
Parameters: 304326632
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: MoCoV3
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.7
|
||||
Config: configs/mocov3/benchmarks/vit-large-p16_8xb64-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth
|
||||
Config: configs/mocov3/benchmarks/vit-large-p16_8xb64-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,15 +65,15 @@ python tools/test.py configs/simclr/benchmarks/resnet50_8xb512-linear-coslr-90e_
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :---------------------------------------- | :--------: | :-------: | :--------------------------------------------------: | :--------------------------------------------------------------------------------------: |
|
||||
| `simclr_resnet50_16xb256-coslr-200e_in1k` | N/A | N/A | [config](simclr_resnet50_16xb256-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.json) |
|
||||
| `simclr_resnet50_16xb256-coslr-800e_in1k` | N/A | N/A | [config](simclr_resnet50_16xb256-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.json) |
|
||||
| `simclr_resnet50_16xb256-coslr-200e_in1k` | 27.97 | 4.11 | [config](simclr_resnet50_16xb256-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.json) |
|
||||
| `simclr_resnet50_16xb256-coslr-800e_in1k` | 27.97 | 4.11 | [config](simclr_resnet50_16xb256-coslr-800e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k` | [SIMCLR 200-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth) | N/A | N/A | 66.90 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.json) |
|
||||
| `resnet50_simclr-800e-pre_8xb512-linear-coslr-90e_in1k` | [SIMCLR 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth) | N/A | N/A | 69.20 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.json) |
|
||||
| `resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k` | [SIMCLR 200-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth) | 25.56 | 4.11 | 66.90 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.json) |
|
||||
| `resnet50_simclr-800e-pre_8xb512-linear-coslr-90e_in1k` | [SIMCLR 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth) | 25.56 | 4.11 | 69.20 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,53 +9,64 @@ Collections:
|
|||
- ResNet
|
||||
- SimCLR
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2002.05709
|
||||
Title: "A simple framework for contrastive learning of visual representations"
|
||||
Title: A simple framework for contrastive learning of visual representations
|
||||
URL: https://arxiv.org/abs/2002.05709
|
||||
README: configs/simclr/README.md
|
||||
|
||||
Models:
|
||||
- Name: simclr_resnet50_16xb256-coslr-200e_in1k
|
||||
In Collection: SimCLR
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 27968832
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimCLR
|
||||
Results: null
|
||||
Config: configs/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth
|
||||
Config: configs/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: simclr_resnet50_16xb256-coslr-800e_in1k
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109364224
|
||||
Parameters: 27968832
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimCLR
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth
|
||||
Config: configs/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_simclr-800e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: resnet50_simclr-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimCLR
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 66.9
|
||||
Config: configs/simclr/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth
|
||||
|
||||
- Name: simclr_resnet50_16xb256-coslr-800e_in1k
|
||||
In Collection: SimCLR
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 4096
|
||||
Results: null
|
||||
Config: configs/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth
|
||||
Downstream:
|
||||
- resnet50_simclr-800e-pre_8xb512-linear-coslr-90e_in1k
|
||||
Config: configs/simclr/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
- Name: resnet50_simclr-800e-pre_8xb512-linear-coslr-90e_in1k
|
||||
In Collection: SimCLR
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimCLR
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 69.2
|
||||
Config: configs/simclr/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth
|
||||
Config: configs/simclr/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,18 +65,18 @@ python tools/test.py configs/simmim/benchmarks/swin-base-w6_8xb256-coslr-100e_in
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :-------------------------------------------------------- | :--------: | :-------: | :-----------------------------------------------------------: | :-------------------------------------------------------------: |
|
||||
| `simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px` | N/A | N/A | [config](simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.json) |
|
||||
| `simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px` | N/A | N/A | [config](simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.json) |
|
||||
| `simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px` | N/A | N/A | [config](simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.json) |
|
||||
| `simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px` | 89.87 | 18.83 | [config](simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.json) |
|
||||
| `simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px` | 89.87 | 18.83 | [config](simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.json) |
|
||||
| `simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px` | 199.92 | 55.85 | [config](simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px` | [SIMMIM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) | N/A | N/A | 82.70 | [config](benchmarks/swin-base-w6_8xb256-coslr-100e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.json) |
|
||||
| `swin-base-w7_simmim-100e-pre_8xb256-coslr-100e_in1k` | [SIMMIM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) | N/A | N/A | 83.50 | [config](benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py) | N/A |
|
||||
| `swin-base-w6_simmim-800e-pre_8xb256-coslr-100e_in1k-192px` | [SIMMIM 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth) | N/A | N/A | 83.80 | [config](benchmarks/swin-base-w6_8xb256-coslr-100e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.json) |
|
||||
| `swin-large-w14_simmim-800e-pre_8xb256-coslr-100e_in1k` | [SIMMIM 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth) | N/A | N/A | 84.80 | [config](benchmarks/swin-large-w14_8xb256-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.json) |
|
||||
| `swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px` | [SIMMIM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) | 87.75 | 11.30 | 82.70 | [config](benchmarks/swin-base-w6_8xb256-coslr-100e_in1k-192px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.json) |
|
||||
| `swin-base-w7_simmim-100e-pre_8xb256-coslr-100e_in1k` | [SIMMIM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth) | 87.77 | 15.47 | 83.50 | [config](benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py) | N/A |
|
||||
| `swin-base-w6_simmim-800e-pre_8xb256-coslr-100e_in1k-192px` | [SIMMIM 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth) | 87.77 | 15.47 | 83.80 | [config](benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.json) |
|
||||
| `swin-large-w14_simmim-800e-pre_8xb256-coslr-100e_in1k` | [SIMMIM 800-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth) | 196.85 | 38.85 | 84.80 | [config](benchmarks/swin-large-w14_8xb256-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ model = dict(
|
|||
# optimizer settings
|
||||
optim_wrapper = dict(
|
||||
type='AmpOptimWrapper',
|
||||
optimizer=dict(type='AdamW', lr=5e-3),
|
||||
optimizer=dict(type='AdamW', lr=5e-3, weight_decay=0.05),
|
||||
clip_grad=dict(max_norm=5.0),
|
||||
constructor='LearningRateDecayOptimWrapperConstructor',
|
||||
paramwise_cfg=dict(
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ model = dict(
|
|||
# optimizer settings
|
||||
optim_wrapper = dict(
|
||||
type='AmpOptimWrapper',
|
||||
optimizer=dict(type='AdamW', lr=5e-3),
|
||||
optimizer=dict(type='AdamW', lr=5e-3, weight_decay=0.05),
|
||||
clip_grad=dict(max_norm=5.0),
|
||||
constructor='LearningRateDecayOptimWrapperConstructor',
|
||||
paramwise_cfg=dict(
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ model = dict(
|
|||
# optimizer settings
|
||||
optim_wrapper = dict(
|
||||
type='AmpOptimWrapper',
|
||||
optimizer=dict(type='AdamW', lr=5e-3),
|
||||
optimizer=dict(type='AdamW', lr=5e-3, weight_decay=0.05),
|
||||
clip_grad=dict(max_norm=5.0),
|
||||
constructor='LearningRateDecayOptimWrapperConstructor',
|
||||
paramwise_cfg=dict(
|
||||
|
|
|
|||
|
|
@ -8,88 +8,108 @@ Collections:
|
|||
Architecture:
|
||||
- Swin
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2111.09886
|
||||
Title: "SimMIM: A Simple Framework for Masked Image Modeling"
|
||||
Title: 'SimMIM: A Simple Framework for Masked Image Modeling'
|
||||
URL: https://arxiv.org/abs/2111.09886
|
||||
README: configs/simmim/README.md
|
||||
|
||||
Models:
|
||||
- Name: simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 18832161792
|
||||
Parameters: 89874104
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results: null
|
||||
Config: configs/simmim/simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth
|
||||
Config: configs/simmim/simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py
|
||||
Downstream:
|
||||
- swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px
|
||||
- swin-base-w7_simmim-100e-pre_8xb256-coslr-100e_in1k
|
||||
- Name: swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px
|
||||
In Collection: SimMIM
|
||||
- Name: simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 18832161792
|
||||
Parameters: 89874104
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth
|
||||
Config: configs/simmim/simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px.py
|
||||
Downstream:
|
||||
- swin-base-w6_simmim-800e-pre_8xb256-coslr-100e_in1k-192px
|
||||
- Name: simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 55849130496
|
||||
Parameters: 199920372
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth
|
||||
Config: configs/simmim/simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px.py
|
||||
Downstream:
|
||||
- swin-large-w14_simmim-800e-pre_8xb256-coslr-100e_in1k
|
||||
- Name: swin-base-w6_simmim-100e-pre_8xb256-coslr-100e_in1k-192px
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 11303976960
|
||||
Parameters: 87750176
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 82.7
|
||||
Config: configs/simmim/benchmarks/swin-base-w6_8xb256-coslr-100e_in1k-192px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth
|
||||
Config: configs/simmim/benchmarks/swin-base-w6_8xb256-coslr-100e_in1k-192px.py
|
||||
- Name: swin-base-w7_simmim-100e-pre_8xb256-coslr-100e_in1k
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 15466852352
|
||||
Parameters: 87768224
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.5
|
||||
Weights: null
|
||||
Config: configs/simmim/benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py
|
||||
|
||||
- Name: simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
Results: null
|
||||
Config: configs/simmim/simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth
|
||||
Downstream:
|
||||
- swin-base-w6_simmim-800e-pre_8xb256-coslr-100e_in1k-192px
|
||||
- Name: swin-base-w6_simmim-800e-pre_8xb256-coslr-100e_in1k-192px
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 15466852352
|
||||
Parameters: 87768224
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 83.8
|
||||
Config: configs/simmim/benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth
|
||||
|
||||
- Name: simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
Results: null
|
||||
Config: configs/simmim/simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth
|
||||
Downstream:
|
||||
- swin-large-w14_simmim-800e-pre_8xb256-coslr-100e_in1k
|
||||
Config: configs/simmim/benchmarks/swin-base-w7_8xb256-coslr-100e_in1k.py
|
||||
- Name: swin-large-w14_simmim-800e-pre_8xb256-coslr-100e_in1k
|
||||
In Collection: SimMIM
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 2048
|
||||
FLOPs: 38853083136
|
||||
Parameters: 196848316
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimMIM
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 84.8
|
||||
Config: configs/simmim/benchmarks/swin-large-w14_8xb256-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth
|
||||
Config: configs/simmim/benchmarks/swin-large-w14_8xb256-coslr-100e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,15 +65,15 @@ python tools/test.py configs/simsiam/benchmarks/resnet50_8xb512-linear-coslr-90e
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :--------------------------------------- | :--------: | :-------: | :-------------------------------------------------: | :----------------------------------------------------------------------------------------: |
|
||||
| `simsiam_resnet50_8xb32-coslr-100e_in1k` | N/A | N/A | [config](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.json) |
|
||||
| `simsiam_resnet50_8xb32-coslr-200e_in1k` | N/A | N/A | [config](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.json) |
|
||||
| `simsiam_resnet50_8xb32-coslr-100e_in1k` | 38.20 | 4.11 | [config](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.json) |
|
||||
| `simsiam_resnet50_8xb32-coslr-200e_in1k` | 38.20 | 4.11 | [config](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k` | [SIMSIAM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth) | N/A | N/A | 68.30 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.json) |
|
||||
| `resnet50_simsiam-200e-pre_8xb512-linear-coslr-90e_in1k` | [SIMSIAM 200-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth) | N/A | N/A | 69.80 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.json) |
|
||||
| `resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k` | [SIMSIAM 100-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth) | 25.56 | 4.11 | 68.30 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.json) |
|
||||
| `resnet50_simsiam-200e-pre_8xb512-linear-coslr-90e_in1k` | [SIMSIAM 200-Epochs](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth) | 25.56 | 4.11 | 69.80 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,53 +9,64 @@ Collections:
|
|||
Architecture:
|
||||
- ResNet
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2011.10566
|
||||
Title: "Exploring simple siamese representation learning"
|
||||
Title: Exploring simple siamese representation learning
|
||||
URL: https://arxiv.org/abs/2011.10566
|
||||
README: configs/simsiam/README.md
|
||||
|
||||
Models:
|
||||
- Name: simsiam_resnet50_8xb32-coslr-100e_in1k
|
||||
In Collection: SimSiam
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 256
|
||||
FLOPs: 4109364224
|
||||
Parameters: 38199360
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimSiam
|
||||
Results: null
|
||||
Config: configs/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth
|
||||
Config: configs/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: simsiam_resnet50_8xb32-coslr-200e_in1k
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 256
|
||||
FLOPs: 4109364224
|
||||
Parameters: 38199360
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimSiam
|
||||
Results: null
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth
|
||||
Config: configs/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Downstream:
|
||||
- resnet50_simsiam-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
- Name: resnet50_simsiam-100e-pre_8xb512-linear-coslr-90e_in1k
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimSiam
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 68.3
|
||||
Config: configs/simsiam/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth
|
||||
|
||||
- Name: simsiam_resnet50_8xb32-coslr-200e_in1k
|
||||
In Collection: SimSiam
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 256
|
||||
Results: null
|
||||
Config: configs/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth
|
||||
Downstream:
|
||||
- resnet50_simsiam-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
Config: configs/simsiam/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
- Name: resnet50_simsiam-200e-pre_8xb512-linear-coslr-90e_in1k
|
||||
In Collection: SimSiam
|
||||
Metadata:
|
||||
Epochs: 90
|
||||
Batch Size: 4096
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SimSiam
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 69.8
|
||||
Config: configs/simsiam/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth
|
||||
Config: configs/simsiam/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
|
|
|
|||
|
|
@ -65,13 +65,13 @@ python tools/test.py configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in
|
|||
|
||||
| Model | Params (M) | Flops (G) | Config | Download |
|
||||
| :----------------------------------------------------- | :--------: | :-------: | :------------------------------------------------------------: | :---------------------------------------------------------------: |
|
||||
| `swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px` | N/A | N/A | [config](swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.json) |
|
||||
| `swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px` | 28.35 | 4.11 | [config](swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.json) |
|
||||
|
||||
### Image Classification on ImageNet-1k
|
||||
|
||||
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
|
||||
| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
|
||||
| `resnet50_swav-pre_8xb32-linear-coslr-100e_in1k` | [SWAV](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) | N/A | N/A | 70.50 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.json) |
|
||||
| `resnet50_swav-pre_8xb32-linear-coslr-100e_in1k` | [SWAV](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) | 25.56 | 4.11 | 70.50 | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -9,30 +9,36 @@ Collections:
|
|||
- ResNet
|
||||
- SwAV
|
||||
Paper:
|
||||
URL: https://arxiv.org/abs/2006.09882
|
||||
Title: "Unsupervised Learning of Visual Features by Contrasting Cluster Assignments"
|
||||
Title: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
|
||||
URL: https://arxiv.org/abs/2006.09882
|
||||
README: configs/swav/README.md
|
||||
|
||||
Models:
|
||||
- Name: swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px
|
||||
In Collection: SwAV
|
||||
Metadata:
|
||||
Epochs: 200
|
||||
Batch Size: 256
|
||||
FLOPs: 4109364224
|
||||
Parameters: 28354752
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SwAV
|
||||
Results: null
|
||||
Config: configs/swav/swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth
|
||||
Config: configs/swav/swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py
|
||||
Downstream:
|
||||
- resnet50_swav-pre_8xb32-linear-coslr-100e_in1k
|
||||
- Name: resnet50_swav-pre_8xb32-linear-coslr-100e_in1k
|
||||
In Collection: SwAV
|
||||
Metadata:
|
||||
Epochs: 100
|
||||
Batch Size: 256
|
||||
FLOPs: 4109464576
|
||||
Parameters: 25557032
|
||||
Training Data: ImageNet-1k
|
||||
In Collection: SwAV
|
||||
Results:
|
||||
- Task: Image Classification
|
||||
Dataset: ImageNet-1k
|
||||
Metrics:
|
||||
Top 1 Accuracy: 70.5
|
||||
Config: configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth
|
||||
Config: configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py
|
||||
|
|
|
|||
|
|
@ -145,14 +145,8 @@ def generate_summary_table(models):
|
|||
if model.results is None:
|
||||
continue
|
||||
name = model.name
|
||||
if model.metadata.parameters is not None:
|
||||
params = f'{model.metadata.parameters / 1e6:.2f}' # Params
|
||||
else:
|
||||
params = ''
|
||||
if model.metadata.flops is not None:
|
||||
flops = f'{model.metadata.flops / 1e9:.2f}' # Params
|
||||
else:
|
||||
flops = ''
|
||||
params = f'{model.metadata.parameters / 1e6:.2f}' # Params
|
||||
flops = f'{model.metadata.flops / 1e9:.2f}' # Params
|
||||
result = model.results[0]
|
||||
top1 = result.metrics.get('Top 1 Accuracy')
|
||||
top5 = result.metrics.get('Top 5 Accuracy')
|
||||
|
|
|
|||
|
|
@ -145,14 +145,8 @@ def generate_summary_table(models):
|
|||
if model.results is None:
|
||||
continue
|
||||
name = model.name
|
||||
if model.metadata.parameters is not None:
|
||||
params = f'{model.metadata.parameters / 1e6:.2f}' # Params
|
||||
else:
|
||||
params = ''
|
||||
if model.metadata.flops is not None:
|
||||
flops = f'{model.metadata.flops / 1e9:.2f}' # Params
|
||||
else:
|
||||
flops = ''
|
||||
params = f'{model.metadata.parameters / 1e6:.2f}' # Params
|
||||
flops = f'{model.metadata.flops / 1e9:.2f}' # Params
|
||||
result = model.results[0]
|
||||
top1 = result.metrics.get('Top 1 Accuracy')
|
||||
top5 = result.metrics.get('Top 5 Accuracy')
|
||||
|
|
|
|||
|
|
@ -282,9 +282,9 @@ def list_models(pattern=None, exclude_patterns=None, task=None) -> List[str]:
|
|||
task_matches = []
|
||||
for key in matches:
|
||||
metainfo = ModelHub._models_dict[key]
|
||||
if metainfo.results is None:
|
||||
continue
|
||||
if task in [result.task for result in metainfo.results]:
|
||||
if metainfo.results is None and task == 'null':
|
||||
task_matches.append(key)
|
||||
elif task in [result.task for result in metainfo.results]:
|
||||
task_matches.append(key)
|
||||
matches = task_matches
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue