102 lines
3.1 KiB
Python
102 lines
3.1 KiB
Python
import argparse
|
|
import time
|
|
|
|
import torch
|
|
from mmcv import Config
|
|
from mmcv.cnn import fuse_conv_bn
|
|
from mmcv.parallel import MMDataParallel
|
|
from mmcv.runner import load_checkpoint, wrap_fp16_model
|
|
|
|
from mmdet.datasets import (build_dataloader, build_dataset,
|
|
replace_ImageToTensor)
|
|
from mmdet.models import build_detector
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(description='MMDet benchmark a model')
|
|
parser.add_argument('config', help='test config file path')
|
|
parser.add_argument('checkpoint', help='checkpoint file')
|
|
parser.add_argument(
|
|
'--log-interval', default=50, help='interval of logging')
|
|
parser.add_argument(
|
|
'--fuse-conv-bn',
|
|
action='store_true',
|
|
help='Whether to fuse conv and bn, this will slightly increase'
|
|
'the inference speed')
|
|
args = parser.parse_args()
|
|
return args
|
|
|
|
|
|
def main():
|
|
args = parse_args()
|
|
|
|
cfg = Config.fromfile(args.config)
|
|
# import modules from string list.
|
|
if cfg.get('custom_imports', None):
|
|
from mmcv.utils import import_modules_from_strings
|
|
import_modules_from_strings(**cfg['custom_imports'])
|
|
# set cudnn_benchmark
|
|
if cfg.get('cudnn_benchmark', False):
|
|
torch.backends.cudnn.benchmark = True
|
|
cfg.model.pretrained = None
|
|
cfg.data.test.test_mode = True
|
|
|
|
# build the dataloader
|
|
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
|
|
if samples_per_gpu > 1:
|
|
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
|
|
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
|
|
dataset = build_dataset(cfg.data.test)
|
|
data_loader = build_dataloader(
|
|
dataset,
|
|
samples_per_gpu=1,
|
|
workers_per_gpu=cfg.data.workers_per_gpu,
|
|
dist=False,
|
|
shuffle=False)
|
|
|
|
# build the model and load checkpoint
|
|
cfg.model.train_cfg = None
|
|
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
|
|
fp16_cfg = cfg.get('fp16', None)
|
|
if fp16_cfg is not None:
|
|
wrap_fp16_model(model)
|
|
load_checkpoint(model, args.checkpoint, map_location='cpu')
|
|
if args.fuse_conv_bn:
|
|
model = fuse_conv_bn(model)
|
|
|
|
model = MMDataParallel(model, device_ids=[0])
|
|
|
|
model.eval()
|
|
|
|
# the first several iterations may be very slow so skip them
|
|
num_warmup = 5
|
|
pure_inf_time = 0
|
|
|
|
# benchmark with 2000 image and take the average
|
|
for i, data in enumerate(data_loader):
|
|
|
|
torch.cuda.synchronize()
|
|
start_time = time.perf_counter()
|
|
|
|
with torch.no_grad():
|
|
model(return_loss=False, rescale=True, **data)
|
|
|
|
torch.cuda.synchronize()
|
|
elapsed = time.perf_counter() - start_time
|
|
|
|
if i >= num_warmup:
|
|
pure_inf_time += elapsed
|
|
if (i + 1) % args.log_interval == 0:
|
|
fps = (i + 1 - num_warmup) / pure_inf_time
|
|
print(f'Done image [{i + 1:<3}/ 2000], fps: {fps:.1f} img / s')
|
|
|
|
if (i + 1) == 2000:
|
|
pure_inf_time += elapsed
|
|
fps = (i + 1 - num_warmup) / pure_inf_time
|
|
print(f'Overall fps: {fps:.1f} img / s')
|
|
break
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|