def training_step(batch):
nonlocal batches_accumulated
if batches_accumulated == 0:
optimizers.zero_grad()
output_dict = model(batch['input'], batch['instance_target'])
output_dict['classifier_target'] = batch['classifier_target']
loss_dict = criterion(output_dict)
top1, top5 = utils.accuracy(output_dict['classifier_output'].data,
output_dict['classifier_target'].data,
topk=(1, 5))
loss_dict['loss'].backward()
batches_accumulated += 1
if batches_accumulated == args.gradient_accum:
mag = {}
for (name, p) in model.named_parameters():
mag[name] = p.grad.norm().item()
optimizers.step()
batches_accumulated = 0
return_dict = OD()
for key in ['cross_entropy', 'margin', 'loss']:
if key in loss_dict:
return_dict[key] = loss_dict[key].item()
return_dict['beta'] = beta.item()
return_dict['top1'] = top1
return_dict['top5'] = top5
return return_dict
def validation_step(batch):
with torch.no_grad():
output_dict = model(batch['input'])
target = batch['classifier_target']
xloss = criterion(output_dict['classifier_output'], target)
top1, top5 = utils.accuracy(output_dict['classifier_output'], target, topk=(1, 5))
return OD([
('cross_entropy', xloss.item()),
('top1', top1),
('top5', top5),
])
def training_step(batch):
optimizers.zero_grad()
output_dict = model(batch['input'])
loss = criterion(output_dict['classifier_output'], batch['classifier_target'])
top1, top5 = utils.accuracy(output_dict['classifier_output'].data, batch['classifier_target'].data, topk=(1, 5))
p.grad = torch.autograd.grad(loss, p)[0] # partial backward
optimizers.step()
return OD([
('cross_entropy', loss.item()),
('p', p.item()),
('top1', top1),
('top5', top5),
])
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
print('arguments:')
print(argstr)
argfile = osp.join(osp.join(args.expdir), 'evaluate_args.yaml')
args.cuda = not args.no_cuda
if not args.dry:
utils.ifmakedirs(args.expdir)
logging.print_file(argstr, argfile)
collate_fn = dict(
collate_fn=list_collate) if args.input_crop == 'rect' else {}
transforms = get_transforms(input_size=args.input_size,
crop=(args.input_crop == 'square'),
need=('val', ))
if args.dataset.startswith('imagenet'):
dataset = IdDataset(
IN1K(args.imagenet_path,
args.dataset[len('imagenet-'):],
transform=transforms['val']))
mode = "classification"
else:
raise NotImplementedError
loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=args.shuffle,
pin_memory=True,
**collate_fn)
model = get_multigrain(args.backbone,
include_sampling=False,
pretrained_backbone=args.pretrained_backbone)
p = model.pool.p
checkpoints = utils.CheckpointHandler(args.expdir)
if checkpoints.exists(args.resume_epoch, args.resume_from):
epoch = checkpoints.resume(model,
resume_epoch=args.resume_epoch,
resume_from=args.resume_from,
return_extra=False)
else:
raise ValueError('Checkpoint ' + args.resume_from + ' not found')
if args.pooling_exponent is not None: # overwrite stored pooling exponent
p.data.fill_(args.init_pooling_exponent)
print("Multigrain model with {} backbone and p={} pooling:".format(
args.backbone, p.item()))
print(model)
if args.cuda:
model = utils.cuda(model)
model.eval() # freeze batch normalization
print("Evaluating", args.dataset)
metrics_history = OD()
metrics = defaultdict(utils.HistoryMeter)
embeddings = []
index = None
tic()
for i, batch in enumerate(loader):
with torch.no_grad():
if args.cuda:
batch = utils.cuda(batch)
metrics["data_time"].update(1000 * toc())
tic()
output_dict = model(batch['input'])
if mode == "classification":
target = batch['classifier_target']
top1, top5 = utils.accuracy(output_dict['classifier_output'],
target,
topk=(1, 5))
metrics["val_top1"].update(top1)
metrics["val_top5"].update(top5)
elif mode == "retrieval":
if index is None: index = faiss.IndexFlatL2(descriptors.size(1))
descriptors = output_dict['normalized_embedding']
for e in descriptors.cpu():
index.append(e)
metrics["batch_time"].update(1000 * toc())
tic()
print(
logging.str_metrics(metrics,
iter=i,
num_iters=len(loader),
epoch=epoch,
num_epochs=epoch))
print(logging.str_metrics(metrics, epoch=epoch, num_epochs=1))
for k in metrics:
metrics[k] = metrics[k].avg
toc()
metrics_history[epoch] = metrics
checkpoints.save_metrics(metrics_history)