mirror of
https://github.com/facebookresearch/deit.git
synced 2025-06-03 14:52:20 +08:00
b06fcba6bf
* support parallelized evaluation * remove shuffle arg of loader val, add sampler val in non-dist branch * replace timm eval sampler with torch sampler * add logger synchronizing to support parallelized evaluation * add command line argument dist-eval and warning
97 lines
3.4 KiB
Python
97 lines
3.4 KiB
Python
# Copyright (c) 2015-present, Facebook, Inc.
|
|
# All rights reserved.
|
|
"""
|
|
Train and eval functions used in main.py
|
|
"""
|
|
import math
|
|
import sys
|
|
from typing import Iterable, Optional
|
|
|
|
import torch
|
|
|
|
from timm.data import Mixup
|
|
from timm.utils import accuracy, ModelEma
|
|
|
|
import utils
|
|
|
|
|
|
def train_one_epoch(model: torch.nn.Module, criterion: torch.nn.Module,
|
|
data_loader: Iterable, optimizer: torch.optim.Optimizer,
|
|
device: torch.device, epoch: int, loss_scaler, max_norm: float = 0,
|
|
model_ema: Optional[ModelEma] = None, mixup_fn: Optional[Mixup] = None):
|
|
# TODO fix this for finetuning
|
|
model.train()
|
|
criterion.train()
|
|
metric_logger = utils.MetricLogger(delimiter=" ")
|
|
metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value:.6f}'))
|
|
header = 'Epoch: [{}]'.format(epoch)
|
|
print_freq = 10
|
|
|
|
for samples, targets in metric_logger.log_every(data_loader, print_freq, header):
|
|
samples = samples.to(device, non_blocking=True)
|
|
targets = targets.to(device, non_blocking=True)
|
|
|
|
if mixup_fn is not None:
|
|
samples, targets = mixup_fn(samples, targets)
|
|
|
|
with torch.cuda.amp.autocast():
|
|
outputs = model(samples)
|
|
loss = criterion(outputs, targets)
|
|
|
|
loss_value = loss.item()
|
|
|
|
if not math.isfinite(loss_value):
|
|
print("Loss is {}, stopping training".format(loss_value))
|
|
sys.exit(1)
|
|
|
|
optimizer.zero_grad()
|
|
|
|
# this attribute is added by timm on one optimizer (adahessian)
|
|
is_second_order = hasattr(optimizer, 'is_second_order') and optimizer.is_second_order
|
|
loss_scaler(loss, optimizer, clip_grad=max_norm,
|
|
parameters=model.parameters(), create_graph=is_second_order)
|
|
|
|
torch.cuda.synchronize()
|
|
if model_ema is not None:
|
|
model_ema.update(model)
|
|
|
|
metric_logger.update(loss=loss_value)
|
|
metric_logger.update(lr=optimizer.param_groups[0]["lr"])
|
|
# gather the stats from all processes
|
|
metric_logger.synchronize_between_processes()
|
|
print("Averaged stats:", metric_logger)
|
|
return {k: meter.global_avg for k, meter in metric_logger.meters.items()}
|
|
|
|
|
|
@torch.no_grad()
|
|
def evaluate(data_loader, model, device):
|
|
criterion = torch.nn.CrossEntropyLoss()
|
|
|
|
metric_logger = utils.MetricLogger(delimiter=" ")
|
|
header = 'Test:'
|
|
|
|
# switch to evaluation mode
|
|
model.eval()
|
|
|
|
for images, target in metric_logger.log_every(data_loader, 10, header):
|
|
images = images.to(device, non_blocking=True)
|
|
target = target.to(device, non_blocking=True)
|
|
|
|
# compute output
|
|
with torch.cuda.amp.autocast():
|
|
output = model(images)
|
|
loss = criterion(output, target)
|
|
|
|
acc1, acc5 = accuracy(output, target, topk=(1, 5))
|
|
|
|
batch_size = images.shape[0]
|
|
metric_logger.update(loss=loss.item())
|
|
metric_logger.meters['acc1'].update(acc1.item(), n=batch_size)
|
|
metric_logger.meters['acc5'].update(acc5.item(), n=batch_size)
|
|
# gather the stats from all processes
|
|
metric_logger.synchronize_between_processes()
|
|
print('* Acc@1 {top1.global_avg:.3f} Acc@5 {top5.global_avg:.3f} loss {losses.global_avg:.3f}'
|
|
.format(top1=metric_logger.acc1, top5=metric_logger.acc5, losses=metric_logger.loss))
|
|
|
|
return {k: meter.global_avg for k, meter in metric_logger.meters.items()}
|