def loop(loader, step, epoch, prefix=''): # Training or validation loop
metrics = defaultdict(utils.HistoryMeter if prefix ==
'train_' else utils.AverageMeter)
tic()
for i, batch in enumerate(loader):
if args.cuda:
batch = utils.cuda(batch)
data_time = 1000 * toc()
tic()
step_metrics = step(batch)
step_metrics['data_time'] = data_time
step_metrics['batch_time'] = 1000 * toc()
tic()
for (k, v) in step_metrics.items():
metrics[prefix + k].update(v, len(batch['input']))
print(
logging.str_metrics(metrics,
iter=i,
num_iters=len(loader),
epoch=epoch,
num_epochs=1))
print(logging.str_metrics(metrics, epoch=epoch, num_epochs=1))
toc()
if prefix == 'val_':
return OD((k, v.avg) for (k, v) in metrics.items())
return OD((k, v.hist) for (k, v) in metrics.items())
def loop(loader, step, epoch, prefix=''): # Training or validation loop
metrics = defaultdict(utils.HistoryMeter if prefix == 'train_' else utils.AverageMeter)
tic()
for i, batch in enumerate(loader):
if prefix == 'train_':
lr = args.learning_rate * (1 - i / len(loader)) ** args.learning_rate_decay_power
optimizers['p'].param_groups[0]['lr'] = lr
if args.cuda:
batch = utils.cuda(batch)
data_time = 1000 * toc();
tic()
step_metrics = step(batch)
step_metrics['data_time'] = data_time
step_metrics['batch_time'] = 1000 * toc();
tic()
for (k, v) in step_metrics.items():
metrics[prefix + k].update(v, len(batch['input']))
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=epoch))
toc()
if prefix == 'val_':
# ipdb.set_trace()
return OD((k, v.avg) for (k, v) in metrics.items())
return OD((k, v.hist) for (k, v) in metrics.items())
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)
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
print('arguments:')
print(argstr)
argfile = osp.join(osp.join(args.expdir), 'whiten_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', ),
backbone=args.backbone)
dataset = ListDataset(args.whiten_path, args.whiten_list,
transforms['val'])
if args.num_whiten_images != -1:
dataset = Subset(dataset, list(range(args.num_whiten_images)))
loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True,
**collate_fn)
model = get_multigrain(args.backbone,
include_sampling=False,
pretrained_backbone=args.pretrained_backbone)
if args.cuda:
model = utils.cuda(model)
p = model.pool.p
checkpoints = utils.CheckpointHandler(args.expdir)
if checkpoints.exists(args.resume_epoch, args.resume_from):
resume_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.pooling_exponent)
print("Multigrain model with {} backbone and p={} pooling:".format(
args.backbone, p.item()))
print(model)
model.init_whitening()
model.eval()
print("Computing embeddings...")
embeddings = []
for i, batch in enumerate(loader):
if i % (len(loader) / 100) < 1:
print("{}/{} ({}%)".format(i, len(loader),
int(i // (len(loader) / 100))))
with torch.no_grad():
if args.cuda:
batch = utils.cuda(batch)
embeddings.append(model(batch)['embedding'].cpu())
embeddings = torch.cat(embeddings)
if args.no_include_last:
embeddings = embeddings[:, :-1]
print("Computing whitening...")
m, P = get_whiten(embeddings)
if args.no_include_last:
# add an preserved channel to the PCA
m = torch.cat((m, torch.tensor([0.0])), 0)
D = P.size(0)
P = torch.cat((P, torch.zeros(1, D)), 0)
P = torch.cat((P, torch.cat(
(torch.zeros(D, 1), torch.tensor([1.0])), 1)), 1)
model.integrate_whitening(m, P)
if not args.dry:
checkpoints.save(model, resume_epoch if resume_epoch != -1 else 0)
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
print('arguments:')
print(argstr)
argfile = osp.join(osp.join(args.expdir), 'finetune_p_args.yaml')
if osp.isfile(argfile):
oldargs = yaml.load(open(argfile))
if oldargs != args.__dict__:
print('WARNING: Changed configuration keys compared to stored experiment')
utils.arguments.compare_dicts(oldargs, args.__dict__, verbose=True)
args.cuda = not args.no_cuda
args.validate_first = not args.no_validate_first
args.validate = not args.no_validate
if not args.dry:
utils.ifmakedirs(args.expdir)
logging.print_file(argstr, argfile)
transforms = get_transforms(IN1K, args.input_size, crop=(args.input_crop == 'square'), need=('val',),
backbone=args.backbone)
datas = {}
for split in ('train', 'val'):
datas[split] = IdDataset(IN1K(args.imagenet_path, split, transform=transforms['val']))
loaders = {}
collate_fn = dict(collate_fn=list_collate) if args.input_crop == 'rect' else {}
selected = []
count = Counter()
# following code: extract args.images_per_class pictures per class in training dataset
for i, label in enumerate(datas['train'].dataset.labels):
if count[label] < args.images_per_class:
selected.append(i)
count[label] += 1
datas['train'].dataset = Subset(datas['train'].dataset, selected)
loaders['train'] = DataLoader(datas['train'], batch_size=args.batch_size, shuffle=True,
num_workers=args.workers, pin_memory=True, **collate_fn)
loaders['val'] = DataLoader(datas['val'], batch_size=args.batch_size, shuffle=args.shuffle_val,
num_workers=args.workers, pin_memory=True, **collate_fn)
model = get_multigrain(args.backbone, include_sampling=False,
pretrained_backbone=args.pretrained_backbone, learn_p=True)
criterion = torch.nn.CrossEntropyLoss()
if args.cuda:
criterion = utils.cuda(criterion)
model = utils.cuda(model)
optimizers = OD()
p = model.pool.p
# SGD(self, params, lr=required, momentum=0, dampening=0, weight_decay=0, nesterov=False)
optimizers['p'] = SGD([p], lr=args.learning_rate, momentum=args.momentum)
optimizers = MultiOptim(optimizers)
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 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),
])
metrics_history = OD()
checkpoints = utils.CheckpointHandler(args.expdir)
if checkpoints.exists(args.resume_epoch, args.resume_from):
epoch = checkpoints.resume(model, metrics_history=metrics_history,
resume_epoch=args.resume_epoch, resume_from=args.resume_from)
else:
raise ValueError('Checkpoint ' + args.resume_from + ' not found')
if args.init_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)
def loop(loader, step, epoch, prefix=''): # Training or validation loop
metrics = defaultdict(utils.HistoryMeter if prefix == 'train_' else utils.AverageMeter)
tic()
for i, batch in enumerate(loader):
if prefix == 'train_':
lr = args.learning_rate * (1 - i / len(loader)) ** args.learning_rate_decay_power
optimizers['p'].param_groups[0]['lr'] = lr
if args.cuda:
batch = utils.cuda(batch)
data_time = 1000 * toc();
tic()
step_metrics = step(batch)
step_metrics['data_time'] = data_time
step_metrics['batch_time'] = 1000 * toc();
tic()
for (k, v) in step_metrics.items():
metrics[prefix + k].update(v, len(batch['input']))
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=epoch))
toc()
if prefix == 'val_':
# ipdb.set_trace()
return OD((k, v.avg) for (k, v) in metrics.items())
return OD((k, v.hist) for (k, v) in metrics.items())
if args.validate_first and 0 not in metrics_history:
model.eval()
metrics_history[epoch[0]] = loop(loaders['val'], validation_step, epoch, 'val_')
checkpoints.save_metrics(metrics_history)
model.eval() # freeze batch normalization
metrics = loop(loaders['train'], training_step, epoch, 'train_')
metrics['last_p'] = p.item()
if args.validate:
model.eval()
# ipdb.set_trace()
metrics.update(loop(loaders['val'], validation_step, epoch[0] + 1, 'val_'))
metrics_history[epoch[0] + 1] = metrics
if not args.dry:
utils.make_plots(metrics_history, args.expdir)
checkpoints.save(model, epoch[0] + 1, optimizers, metrics_history)
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
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=my_collate) if args.input_crop == 'rect' else {}
transforms = get_transforms(input_size=args.input_size, \
crop=(args.input_crop == 'square'), need=('val',),
backbone=args.backbone)
if args.dataset.startswith('imagenet'):
dataset = IdDataset(
IN1K(args.imagenet_path,
args.dataset[len('imagenet-'):],
transform=transforms['val']))
mode = "classification"
else:
dataset = IdDataset(
meizi_dataset(root=args.meizi_path, transform=transforms['val']))
mode = "retrieval"
loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=args.shuffle,
pin_memory=True,
**collate_fn)
import torchvision.datasets as datasets
val_loader = torch.utils.data.DataLoader(FidDataset(
datasets.ImageFolder(args.meizi_path, transforms['val'])),
batch_size=args.batch_size,
shuffle=args.shuffle,
num_workers=args.workers,
pin_memory=True,
**collate_fn)
# ipdb.set_trace()
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.pooling_exponent)
model = utils.cuda(model)
print("Multigrain model with {} backbone and p={} pooling:".format(
args.backbone, p.item()))
#print(model)
#temp = torch.stack(temp, dim=0)
if True:
#
gpuDeviceIds = [1]
device = torch.device('cuda:{}'.format(gpuDeviceIds[0]) if torch.cuda.
is_available() else 'cpu')
# device = torch.device('cuda:{}'.format('0,1,2,3') if torch.cuda.is_available() else 'cpu')
model = torch.nn.DataParallel(model, device_ids=gpuDeviceIds)
model.to(device)
# model.eval()
else:
# only use one gpu
model.cuda()
model.eval()
metrics_history = OD()
metrics = defaultdict(utils.HistoryMeter)
tic()
start_id = 0
imageCount = len(dataset)
Dim = 2048
xb = MmapVectorUtils.Open(args.embeddingFilePath,
True,
shape=(imageCount, Dim + 2))
# dataloader_iter = iter(loader)
# data, target, fid = next(dataloader_iter)
multiGpu = True
# dataloader_iter = iter(loader)
# print("val_loader lens", len(loader))
# length = len(loader)
# for step in tqdm(range(length)):
# try:
# dict_temp = next(dataloader_iter)
# data = dict_temp['input']
# classifier_target = dict_temp['classifier_target']
# vid = dict_temp['vid']
# frame_id = dict_temp['frame_id']
# instance_target = dict_temp['instance_target']
# batch = utils.cuda(data)
# data = batch.to(device) if True else data.cuda()
# data = data.to(device) if multiGpu else data.cuda()
# output = model(data)
# output = output['normalized_embedding']
# cpuOutput = output.cpu().detach().numpy()
# if not np.all(np.isfinite(cpuOutput)):
# print("Return infinit results in step ", step)
# continue
# yield target, fid, cpuOutput
# except Exception as e:
# print("error when prossess dataloader_iter, step ", step)
# print('Error:', e)
for i, batch in enumerate(loader):
#try:
batch_vid = batch['vid']
batch_fid = batch['frame_id']
with torch.no_grad():
#if args.cuda:
if True:
batch = utils.cuda(batch)
metrics["data_time"].update(1000 * toc())
tic()
batch_input_conv = torch.stack(batch['input'], dim=0)
batch_input_conv = batch_input_conv.to(
device) if True else batch_input_conv.cuda()
output_dict = model(batch_input_conv)
# data = batch.to(device) if True else data.cuda()
# output = model(data)
# cpuOutput = output.cpu().detach().numpy()
# data = data.to(self.device) if self.multiGpu else data.cuda()
# output = model(data)
# output = output['normalized_embedding']
# cpuOutput = output.cpu().detach().numpy()
# output_dict = model(batch['input'])
# output_dict = output_dict.cpu().detach().numpy()
# metrics["data_time"].update(1000 * toc());
# tic()
if mode == "classification":
# target = batch['classifier_target']
# top1, top5 = utils.accuracy(output_dict['classifier_output'], target, topk=(1, 5))
# metrics["val_top1"].update(top1, n=len(batch['input']))
# metrics["val_top5"].update(top5, n=len(batch['input']))
raise ValueError('only focus on retrival')
elif mode == "retrieval":
descriptors = output_dict['normalized_embedding']
n, dim = descriptors.shape
end_id = n + start_id
end_id = min(imageCount, end_id)
n = end_id - start_id
xb[start_id:end_id, 0:1] = np.array(batch_vid).reshape(n, 1)
xb[start_id:end_id, 1:2] = np.array(batch_fid).reshape(n, 1)
xb[start_id:end_id, 2:] = descriptors[0:n].cpu().numpy()
start_id += n
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
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
print('arguments:')
print(argstr)
argfile = osp.join(args.expdir, 'train_args.yaml')
if osp.isfile(argfile):
oldargs = yaml.load(open(argfile))
if oldargs is not None and oldargs != args.__dict__:
print(
'WARNING: Changed configuration keys compared to stored experiment'
)
utils.arguments.compare_dicts(oldargs, args.__dict__, verbose=True)
args.cuda = not args.no_cuda
args.validate_first = not args.no_validate_first
if not args.dry:
utils.ifmakedirs(args.expdir)
logging.print_file(argstr, argfile)
transforms = get_transforms(IN1K, args.input_size, args.augmentation)
datas = {}
for split in ('train', 'val'):
imload = preloader(args.imagenet_path, args.preload_dir_imagenet
) if args.preload_dir_imagenet else default_loader
datas[split] = IdDataset(
IN1K(args.imagenet_path,
split,
transform=transforms[split],
loader=imload))
loaders = {}
loaders['train'] = DataLoader(datas['train'],
batch_sampler=RASampler(
len(datas['train']),
args.batch_size,
args.repeated_augmentations,
args.epoch_len_factor,
shuffle=True,
drop_last=False),
num_workers=args.workers,
pin_memory=True)
loaders['val'] = DataLoader(datas['val'],
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
model = get_multigrain(args.backbone,
p=args.pooling_exponent,
include_sampling=not args.global_sampling,
pretrained_backbone=args.pretrained_backbone)
print("Multigrain model with {} backbone and p={} pooling:".format(
args.backbone, args.pooling_exponent))
print(model)
cross_entropy = torch.nn.CrossEntropyLoss()
cross_entropy_criterion = (cross_entropy, ('classifier_output',
'classifier_target'),
args.classif_weight)
if args.global_sampling:
margin = SampledMarginLoss(margin_args=dict(beta_init=args.beta_init))
beta = margin.margin.beta
margin_criterion = (margin, ('normalized_embedding',
'instance_target'),
1.0 - args.classif_weight)
else:
margin = MarginLoss(args.beta_init)
beta = margin.beta
margin_criterion = (margin,
('anchor_embeddings', 'negative_embeddings',
'positive_embeddings'), 1.0 - args.classif_weight)
extra = {'beta': beta}
criterion = MultiCriterion(dict(cross_entropy=cross_entropy_criterion,
margin=margin_criterion),
skip_zeros=(args.repeated_augmentations == 1))
if args.cuda:
criterion = utils.cuda(criterion)
model = utils.cuda(model)
optimizers = OD()
optimizers['backbone'] = SGD(model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizers['margin_beta'] = SGD([beta],
lr=args.learning_rate * args.beta_lr,
momentum=args.momentum)
optimizers = MultiOptim(optimizers)
optimizers.set_base_lr()
if args.cuda:
model = nn.DataParallel(model)
def set_learning_rate(epoch):
factor = 1.0
for (drop, gamma) in zip(args.lr_drops_epochs, args.lr_drops_factors):
if epoch > drop:
factor *= gamma
optimizers.lr_multiply(factor)
batches_accumulated = 0
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 = cross_entropy(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),
])
metrics_history = OD()
checkpoints = utils.CheckpointHandler(args.expdir, args.save_every)
if checkpoints.exists(args.resume_epoch, args.resume_from):
begin_epoch, loaded_extra = checkpoints.resume(model, optimizers,
metrics_history,
args.resume_epoch,
args.resume_from)
if 'beta' in loaded_extra:
beta.data.copy_(loaded_extra['beta'])
else:
print('(re)initialized beta to {}'.format(beta.item()))
else:
raise ValueError('Checkpoint ' + args.resume_from + ' not found')
def loop(loader, step, epoch, prefix=''): # Training or validation loop
metrics = defaultdict(utils.AverageMeter)
tic()
for i, batch in enumerate(loader):
if args.cuda:
batch = utils.cuda(batch)
data_time = 1000 * toc()
tic()
step_metrics = step(batch)
step_metrics['data_time'] = data_time
step_metrics['batch_time'] = 1000 * toc()
tic()
for (k, v) in step_metrics.items():
metrics[prefix + k].update(v, len(batch['input']))
print(
logging.str_metrics(metrics,
iter=i,
num_iters=len(loader),
epoch=epoch,
num_epochs=args.epochs))
print(logging.str_metrics(metrics, epoch=epoch,
num_epochs=args.epochs))
toc()
return OD((k, v.avg) for (k, v) in metrics.items())
if args.validate_first and begin_epoch == 0 and 0 not in metrics_history:
model.eval()
metrics_history[0] = loop(loaders['val'], validation_step, begin_epoch,
'val_')
checkpoints.save_metrics(metrics_history)
for epoch in range(begin_epoch, args.epochs):
set_learning_rate(epoch)
batches_accumulated = 0
model.train()
metrics = loop(loaders['train'], training_step, epoch, 'train_')
model.eval()
metrics.update(loop(loaders['val'], validation_step, epoch, 'val_'))
metrics_history[epoch + 1] = metrics
if not args.dry:
utils.make_plots(metrics_history, args.expdir)
checkpoints.save(model, epoch + 1, optimizers, metrics_history,
extra)
def run(args):
argstr = yaml.dump(args.__dict__, default_flow_style=False)
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=my_collate) if args.input_crop == 'rect' else {}
transforms = get_transforms(input_size=args.input_size, \
crop=(args.input_crop == 'square'), need=('val',),
backbone=args.backbone)
if args.dataset.startswith('imagenet'):
dataset = IdDataset(IN1K(args.imagenet_path, args.dataset[len('imagenet-'):],
transform=transforms['val']))
mode = "classification"
else:
dataset = IdDataset(meizi_dataset(root=args.meizi_path, transform=transforms['val'], starts=args.starts))
mode = "retrieval"
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.pooling_exponent)
print("Multigrain model with {} backbone and p={} pooling:".format(args.backbone, p.item()))
# print(model)
if True:
model = utils.cuda(model)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
model.eval() # freeze batch normalization
metrics_history = OD()
metrics = defaultdict(utils.HistoryMeter)
index = None
tic()
start_id = 0
imageCount = len(dataset)
Dim = 2048
xb = MmapVectorUtils.Open(args.embeddingFilePath, True, shape=(imageCount, Dim + 2))
for i, batch in enumerate(loader):
# ipdb.set_trace()
#try:
batch_vid = batch['vid']
batch_fid = batch['frame_id']
with torch.no_grad():
#if args.cuda:
if True:
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, n=len(batch['input']))
# metrics["val_top5"].update(top5, n=len(batch['input']))
raise ValueError('only focus on retrival')
elif mode == "retrieval":
descriptors = output_dict['normalized_embedding']
n, dim = descriptors.shape
end_id = n + start_id
end_id = min(imageCount, end_id)
n = end_id - start_id
xb[start_id:end_id, 0:1] = np.array(batch_vid).reshape(n,1)
xb[start_id:end_id, 1:2] = np.array(batch_fid).reshape(n,1)
xb[start_id:end_id, 2:] = descriptors[0:n].cpu().numpy()
start_id += n
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