in main.py [0:0]
def main(args):
utils.init_distributed_mode(args)
print(args)
if args.distillation_type != 'none' and args.finetune and not args.eval:
raise NotImplementedError("Finetuning with distillation not yet supported")
device = torch.device(args.device)
# fix the seed for reproducibility
seed = args.seed + utils.get_rank()
torch.manual_seed(seed)
np.random.seed(seed)
# random.seed(seed)
cudnn.benchmark = True
dataset_train, args.nb_classes = build_dataset(is_train=True, args=args)
dataset_val, _ = build_dataset(is_train=False, args=args)
if True: # args.distributed:
num_tasks = utils.get_world_size()
global_rank = utils.get_rank()
if args.repeated_aug:
sampler_train = RASampler(
dataset_train, num_replicas=num_tasks, rank=global_rank, shuffle=True
)
else:
sampler_train = torch.utils.data.DistributedSampler(
dataset_train, num_replicas=num_tasks, rank=global_rank, shuffle=True
)
if args.dist_eval:
if len(dataset_val) % num_tasks != 0:
print('Warning: Enabling distributed evaluation with an eval dataset not divisible by process number. '
'This will slightly alter validation results as extra duplicate entries are added to achieve '
'equal num of samples per-process.')
sampler_val = torch.utils.data.DistributedSampler(
dataset_val, num_replicas=num_tasks, rank=global_rank, shuffle=False)
else:
sampler_val = torch.utils.data.SequentialSampler(dataset_val)
else:
sampler_train = torch.utils.data.RandomSampler(dataset_train)
sampler_val = torch.utils.data.SequentialSampler(dataset_val)
data_loader_train = torch.utils.data.DataLoader(
dataset_train, sampler=sampler_train,
batch_size=args.batch_size,
num_workers=args.num_workers,
pin_memory=args.pin_mem,
drop_last=True,
)
data_loader_val = torch.utils.data.DataLoader(
dataset_val, sampler=sampler_val,
batch_size=int(1.5 * args.batch_size),
num_workers=args.num_workers,
pin_memory=args.pin_mem,
drop_last=False
)
mixup_fn = None
mixup_active = args.mixup > 0 or args.cutmix > 0. or args.cutmix_minmax is not None
if mixup_active:
mixup_fn = Mixup(
mixup_alpha=args.mixup, cutmix_alpha=args.cutmix, cutmix_minmax=args.cutmix_minmax,
prob=args.mixup_prob, switch_prob=args.mixup_switch_prob, mode=args.mixup_mode,
label_smoothing=args.smoothing, num_classes=args.nb_classes)
print(f"Creating model: {args.model}")
model = create_model(
args.model,
pretrained=False,
num_classes=args.nb_classes,
drop_rate=args.drop,
drop_path_rate=args.drop_path,
drop_block_rate=None,
)
if args.finetune:
if args.finetune.startswith('https'):
checkpoint = torch.hub.load_state_dict_from_url(
args.finetune, map_location='cpu', check_hash=True)
else:
checkpoint = torch.load(args.finetune, map_location='cpu')
checkpoint_model = checkpoint['model']
state_dict = model.state_dict()
for k in ['head.weight', 'head.bias', 'head_dist.weight', 'head_dist.bias']:
if k in checkpoint_model and checkpoint_model[k].shape != state_dict[k].shape:
print(f"Removing key {k} from pretrained checkpoint")
del checkpoint_model[k]
# interpolate position embedding
pos_embed_checkpoint = checkpoint_model['pos_embed']
embedding_size = pos_embed_checkpoint.shape[-1]
num_patches = model.patch_embed.num_patches
num_extra_tokens = model.pos_embed.shape[-2] - num_patches
# height (== width) for the checkpoint position embedding
orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5)
# height (== width) for the new position embedding
new_size = int(num_patches ** 0.5)
# class_token and dist_token are kept unchanged
extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens]
# only the position tokens are interpolated
pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:]
pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
pos_tokens = torch.nn.functional.interpolate(
pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False)
pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2)
new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1)
checkpoint_model['pos_embed'] = new_pos_embed
model.load_state_dict(checkpoint_model, strict=False)
model.to(device)
model_ema = None
if args.model_ema:
# Important to create EMA model after cuda(), DP wrapper, and AMP but before SyncBN and DDP wrapper
model_ema = ModelEma(
model,
decay=args.model_ema_decay,
device='cpu' if args.model_ema_force_cpu else '',
resume='')
model_without_ddp = model
if args.distributed:
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
model_without_ddp = model.module
n_parameters = sum(p.numel() for p in model.parameters() if p.requires_grad)
print('number of params:', n_parameters)
linear_scaled_lr = args.lr * args.batch_size * utils.get_world_size() / 512.0
args.lr = linear_scaled_lr
optimizer = create_optimizer(args, model_without_ddp)
loss_scaler = NativeScaler()
lr_scheduler, _ = create_scheduler(args, optimizer)
criterion = LabelSmoothingCrossEntropy()
if mixup_active:
# smoothing is handled with mixup label transform
criterion = SoftTargetCrossEntropy()
elif args.smoothing:
criterion = LabelSmoothingCrossEntropy(smoothing=args.smoothing)
else:
criterion = torch.nn.CrossEntropyLoss()
teacher_model = None
if args.distillation_type != 'none':
assert args.teacher_path, 'need to specify teacher-path when using distillation'
print(f"Creating teacher model: {args.teacher_model}")
teacher_model = create_model(
args.teacher_model,
pretrained=False,
num_classes=args.nb_classes,
global_pool='avg',
)
if args.teacher_path.startswith('https'):
checkpoint = torch.hub.load_state_dict_from_url(
args.teacher_path, map_location='cpu', check_hash=True)
else:
checkpoint = torch.load(args.teacher_path, map_location='cpu')
teacher_model.load_state_dict(checkpoint['model'])
teacher_model.to(device)
teacher_model.eval()
# wrap the criterion in our custom DistillationLoss, which
# just dispatches to the original criterion if args.distillation_type is 'none'
criterion = DistillationLoss(
criterion, teacher_model, args.distillation_type, args.distillation_alpha, args.distillation_tau
)
output_dir = Path(args.output_dir)
if args.resume:
if args.resume.startswith('https'):
checkpoint = torch.hub.load_state_dict_from_url(
args.resume, map_location='cpu', check_hash=True)
else:
checkpoint = torch.load(args.resume, map_location='cpu')
model_without_ddp.load_state_dict(checkpoint['model'])
if not args.eval and 'optimizer' in checkpoint and 'lr_scheduler' in checkpoint and 'epoch' in checkpoint:
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
args.start_epoch = checkpoint['epoch'] + 1
if args.model_ema:
utils._load_checkpoint_for_ema(model_ema, checkpoint['model_ema'])
if 'scaler' in checkpoint:
loss_scaler.load_state_dict(checkpoint['scaler'])
if args.eval:
test_stats = evaluate(data_loader_val, model, device)
print(f"Accuracy of the network on the {len(dataset_val)} test images: {test_stats['acc1']:.1f}%")
return
print(f"Start training for {args.epochs} epochs")
start_time = time.time()
max_accuracy = 0.0
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
data_loader_train.sampler.set_epoch(epoch)
train_stats = train_one_epoch(
model, criterion, data_loader_train,
optimizer, device, epoch, loss_scaler,
args.clip_grad, model_ema, mixup_fn,
set_training_mode=args.finetune == '' # keep in eval mode during finetuning
)
lr_scheduler.step(epoch)
if args.output_dir:
checkpoint_paths = [output_dir / 'checkpoint.pth']
for checkpoint_path in checkpoint_paths:
utils.save_on_master({
'model': model_without_ddp.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch,
'model_ema': get_state_dict(model_ema),
'scaler': loss_scaler.state_dict(),
'args': args,
}, checkpoint_path)
test_stats = evaluate(data_loader_val, model, device)
print(f"Accuracy of the network on the {len(dataset_val)} test images: {test_stats['acc1']:.1f}%")
if max_accuracy < test_stats["acc1"]:
max_accuracy = test_stats["acc1"]
if args.output_dir:
checkpoint_paths = [output_dir / 'best_checkpoint.pth']
for checkpoint_path in checkpoint_paths:
utils.save_on_master({
'model': model_without_ddp.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch,
'model_ema': get_state_dict(model_ema),
'scaler': loss_scaler.state_dict(),
'args': args,
}, checkpoint_path)
print(f'Max accuracy: {max_accuracy:.2f}%')
log_stats = {**{f'train_{k}': v for k, v in train_stats.items()},
**{f'test_{k}': v for k, v in test_stats.items()},
'epoch': epoch,
'n_parameters': n_parameters}
if args.output_dir and utils.is_main_process():
with (output_dir / "log.txt").open("a") as f:
f.write(json.dumps(log_stats) + "\n")
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))