def checkpoint(self, ts=None, best=False):
if ts is None:
ts = self.ts
filename = ts + 'checkpoint.pth.tar'
filename_best = ts + 'best_checkpoint.pth.tar'
state = {
'state_dicts': [model.state_dict() for model in self.model_list],
'epoch':
self.epoch + 1 if not self.args.evaluate else None,
'optimizers':
[optimizer.state_dict() for optimizer in self.optimizer_list],
'losses':
self.epoch_losses if not self.args.evaluate else None,
'performance_evolution':
self.test_acc_logger.get_data(),
'args':
self.loaded_args if self.args.evaluate else self.args,
'ts':
self.ts,
'result_dict':
self.result_dict
}
save_checkpoint(state, osp.join(self.args.save_experiment, filename))
if best:
save_checkpoint(state,
osp.join(self.args.save_experiment, filename_best))
print("Saved model checkpoint at " + filename)
if best:
print("Also saved as best checkpoint. ")
def run(self):
start_time = time.time()
train_time = 0
best_epoch = 0
best_acc = self._eval_epoch(epoch=0)
# === Train
for epoch in range(1, self.args.max_epoch + 1):
self.lr = self.optimizer.param_groups[0]['lr']
self.writer.add_scalar('Learning rate', self.lr, global_step=epoch)
epoch_time_start = time.time()
self._train_epoch(epoch)
train_time += round(time.time() - epoch_time_start)
# === Evaluation
if epoch == 1 or epoch == self.args.max_epoch or epoch % self.args.eval_per_epoch == 0:
acc = self._eval_epoch(epoch)
is_best = acc > best_acc
if is_best:
best_acc = acc
best_epoch = epoch
if is_best or epoch % self.args.save_per_epoch == 0:
state = {
'encoder_state_dict': self.encoder.state_dict(),
'decoder_state_dict': self.decoder.state_dict(),
'acc': acc,
'epoch': epoch,
}
file_path = os.path.join(
self.args.save_dir, self.dataset, 'pretrain', self.args.encoder,
'ckp_ep' + str(epoch) + '.ckp')
save_checkpoint(state, is_best, file_path)
print('==> Test best accuracy {:.2%}, achieved at epoch {}'.format(
best_acc, best_epoch))
torch.cuda.empty_cache()
elapsed = str(datetime.timedelta(seconds=round(time.time() - start_time)))
train_time = str(datetime.timedelta(seconds=train_time))
print('Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}'.format(elapsed, train_time))
print("==========\nArgs:{}\n==========".format(self.args))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu:
use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
train_dataset = data_manager.init_dataset(root=args.root,
name='json',
phase='train')
valid_dataset = data_manager.init_dataset(root=args.root,
name='json',
phase='valid')
test_dataset = data_manager.init_dataset(root=args.root,
name='json',
phase='test')
test_mask = test_dataset.mask
pin_memory = True if use_gpu else False
trainloader = DataLoader(JsonDataset(train_dataset),
num_workers=4,
batch_size=args.train_batch,
pin_memory=pin_memory,
drop_last=True)
validloader = DataLoader(JsonDataset(valid_dataset),
num_workers=4,
batch_size=args.test_batch,
pin_memory=pin_memory,
drop_last=True)
testloader = DataLoader(JsonDataset(test_dataset),
num_workers=4,
batch_size=args.test_batch,
pin_memory=pin_memory,
drop_last=True)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch, use_gpu=use_gpu)
print("Model size: {:.3f} M".format(count_num_param(model)))
model.init_weights()
criterion_label = LabelLoss()
optimizer = init_optim(args.optim, model.parameters(), args.lr,
args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
start_epoch = args.start_epoch
if args.load_weights:
# load pretrained weights but ignore layers that don't match in size
print("Loading pretrained weights from '{}'".format(args.load_weights))
checkpoint = torch.load(args.load_weights)
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {
k: v
for k, v in pretrain_dict.items()
if k in model_dict and model_dict[k].size() == v.size()
}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
if args.resume:
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}".format(start_epoch))
# if use_gpu:
# str_ids = args.gpu_devices.split(',')
# gpu_ids = []
# for str_id in str_ids:
# id = int(str_id)
# if id >= 0:
# gpu_ids.append(id)
# model = nn.DataParallel(model, gpu_ids)
device = torch.device(
'cuda' if use_gpu and torch.cuda.is_available() else 'cpu')
model.to(device)
if args.evaluate:
print("Evaluate only")
start_evaluate_time = time.time()
test_thetas = evaluate(model, testloader, use_gpu, args.test_batch,
test_mask)
# test_thetas = evaluate(model, validloader, use_gpu, args.test_batch, test_mask)
evaluate_time = time.time() - start_evaluate_time
print('Evaluate: {} secs'.format(evaluate_time))
with open("auto_sample.csv", "r") as csvfiler:
with open("test_thetas.csv", "w") as csvfilew:
reader = csv.reader(csvfiler)
for item in reader:
if reader.line_num == 1:
writer = csv.writer(csvfilew)
writer.writerow(['test_id', 'result'])
continue
writer = csv.writer(csvfilew)
writer.writerow(
[item[0],
str(test_thetas[reader.line_num - 2])])
# writer.writerows(map(lambda x: [x], test_thetas))
return
start_time = time.time()
train_time = 0
best_label_loss = np.inf
best_epoch = 0
#
# print("==> Test")
# label_loss = test(model, validloader, criterion_label, use_gpu, args.test_batch)
# print("test label loss RMES() is {}".format(label_loss))
#
# print("==> Start training")
for epoch in range(start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion_label, optimizer, trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
# save model every epoch
if (epoch + 1) % args.save_step == 0:
print("==> Now save epoch {} \'s model".format(epoch + 1))
# if use_gpu:
# state_dict = model.state_dict() # module.
# else:
state_dict = model.state_dict()
save_checkpoint({
'state_dict': state_dict,
'epoch': epoch
}, False, osp.join(args.save_dir, 'checkpoint_latest.pth'))
# test model every eval_step
if (epoch + 1) > args.start_eval and args.eval_step > 0 and (epoch + 1) % args.eval_step == 0 or \
(epoch + 1) == args.max_epoch:
print("==> Test")
label_loss = test(model, validloader, criterion_label, use_gpu,
args.test_batch)
is_best = label_loss < best_label_loss
if is_best:
best_label_loss = label_loss
best_epoch = epoch + 1
# if use_gpu:
# state_dict = model.state_dict()
# else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'label_loss': label_loss,
'epoch': epoch,
}, is_best,
osp.join(args.save_dir, 'checkpoint_ep' + str(epoch + 1) +
'.pth')) # .pth.tar
print("==> Best Label Loss {:.3}, achieved at epoch {}".format(
best_label_loss, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu: use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_imgreid_dataset(
root=args.root, name=args.dataset, split_id=args.split_id,
cuhk03_labeled=args.cuhk03_labeled, cuhk03_classic_split=args.cuhk03_classic_split,
use_lmdb=args.use_lmdb,
)
transform_train = T.Compose([
T.Random2DTranslation(args.height, args.width),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
transform_test = T.Compose([
T.Resize((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
trainloader = DataLoader(
ImageDataset(dataset.train, transform=transform_train,
use_lmdb=args.use_lmdb, lmdb_path=dataset.train_lmdb_path),
batch_size=args.train_batch, shuffle=True, num_workers=args.workers,
pin_memory=pin_memory, drop_last=True,
)
queryloader = DataLoader(
ImageDataset(dataset.query, transform=transform_test,
use_lmdb=args.use_lmdb, lmdb_path=dataset.query_lmdb_path),
batch_size=args.test_batch, shuffle=False, num_workers=args.workers,
pin_memory=pin_memory, drop_last=False,
)
galleryloader = DataLoader(
ImageDataset(dataset.gallery, transform=transform_test,
use_lmdb=args.use_lmdb, lmdb_path=dataset.gallery_lmdb_path),
batch_size=args.test_batch, shuffle=False, num_workers=args.workers,
pin_memory=pin_memory, drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch, num_classes=dataset.num_train_pids, loss={'xent'}, use_gpu=use_gpu)
print("Model size: {:.3f} M".format(count_num_param(model)))
criterion = CrossEntropyLabelSmooth(num_classes=dataset.num_train_pids, use_gpu=use_gpu)
optimizer = init_optim(args.optim, model.parameters(), args.lr, args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.stepsize, gamma=args.gamma)
start_epoch = args.start_epoch
if args.fixbase_epoch > 0:
if hasattr(model, 'classifier') and isinstance(model.classifier, nn.Module):
optimizer_tmp = init_optim(args.optim, model.classifier.parameters(), args.fixbase_lr, args.weight_decay)
else:
print("Warn: model has no attribute 'classifier' and fixbase_epoch is reset to 0")
args.fixbase_epoch = 0
if args.load_weights:
# load pretrained weights but ignore layers that don't match in size
print("Loading pretrained weights from '{}'".format(args.load_weights))
checkpoint = torch.load(args.load_weights)
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {k: v for k, v in pretrain_dict.items() if k in model_dict and model_dict[k].size() == v.size()}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
if args.resume:
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(start_epoch, rank1))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
test(model, queryloader, galleryloader, use_gpu)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
if args.fixbase_epoch > 0:
print("Train classifier for {} epochs while keeping base network frozen".format(args.fixbase_epoch))
for epoch in range(args.fixbase_epoch):
start_train_time = time.time()
train(epoch, model, criterion, optimizer_tmp, trainloader, use_gpu, freeze_bn=True)
train_time += round(time.time() - start_train_time)
del optimizer_tmp
print("Now open all layers for training")
for epoch in range(start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion, optimizer, trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch+1) > args.start_eval and args.eval_step > 0 and (epoch+1) % args.eval_step == 0 or (epoch+1) == args.max_epoch:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint({
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch+1) + '.pth.tar'))
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print("Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu: use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_vidreid_dataset(root=args.root,
name=args.dataset)
transform_train = T.Compose([
T.Random2DTranslation(args.height, args.width),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
transform_test = T.Compose([
T.Resize((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
# decompose tracklets into images for image-based training
new_train = []
for img_paths, pid, camid in dataset.train:
for img_path in img_paths:
new_train.append((img_path, pid, camid))
trainloader = DataLoader(
ImageDataset(new_train, transform=transform_train),
sampler=RandomIdentitySampler(new_train,
num_instances=args.num_instances),
batch_size=args.train_batch,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=True,
)
queryloader = DataLoader(
VideoDataset(dataset.query,
seq_len=args.seq_len,
sample='evenly',
transform=transform_test),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
galleryloader = DataLoader(
VideoDataset(dataset.gallery,
seq_len=args.seq_len,
sample='evenly',
transform=transform_test),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dataset.num_train_pids,
loss={'xent', 'htri'})
print("Model size: {:.3f} M".format(count_num_param(model)))
criterion_xent = CrossEntropyLabelSmooth(
num_classes=dataset.num_train_pids, use_gpu=use_gpu)
criterion_htri = TripletLoss(margin=args.margin)
optimizer = init_optim(args.optim, model.parameters(), args.lr,
args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
start_epoch = args.start_epoch
if args.resume:
print("Loading checkpoint from '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
test(model, queryloader, galleryloader, args.pool, use_gpu)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
for epoch in range(start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion_xent, criterion_htri, optimizer,
trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch + 1) > args.start_eval and args.eval_step > 0 and (
epoch + 1) % args.eval_step == 0 or (epoch +
1) == args.max_epoch:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, args.pool, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(
best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu: use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_imgreid_dataset(
root=args.root,
name=args.dataset,
split_id=args.split_id,
cuhk03_labeled=args.cuhk03_labeled,
cuhk03_classic_split=args.cuhk03_classic_split,
use_lmdb=args.use_lmdb,
)
transform_train = T.Compose([
T.Random2DTranslation(args.height, args.width),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
transform_test = T.Compose([
T.Resize((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
trainloader = DataLoader(
ImageDataset(dataset.train,
transform=transform_train,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.train_lmdb_path),
sampler=RandomIdentitySampler(dataset.train,
num_instances=args.num_instances),
batch_size=args.train_batch,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=True,
)
queryloader = DataLoader(
ImageDataset(dataset.query,
transform=transform_test,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.train_lmdb_path),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
galleryloader = DataLoader(
ImageDataset(dataset.gallery,
transform=transform_test,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.train_lmdb_path),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dataset.num_train_pids,
loss={'xent', 'htri'})
print("Model size: {:.3f} M".format(count_num_param(model)))
criterion_xent = CrossEntropyLabelSmooth(
num_classes=dataset.num_train_pids, use_gpu=use_gpu)
criterion_htri = TripletLoss(margin=args.margin)
optimizer = init_optim(args.optim, model.parameters(), args.lr,
args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
if args.load_weights:
# load pretrained weights but ignore layers that don't match in size
if check_isfile(args.load_weights):
checkpoint = torch.load(args.load_weights)
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {
k: v
for k, v in pretrain_dict.items()
if k in model_dict and model_dict[k].size() == v.size()
}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
print("Loaded pretrained weights from '{}'".format(
args.load_weights))
if args.resume:
if check_isfile(args.resume):
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
args.start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(
args.start_epoch, rank1))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
distmat = test(model,
queryloader,
galleryloader,
use_gpu,
return_distmat=True)
if args.vis_ranked_res:
visualize_ranked_results(
distmat,
dataset,
save_dir=osp.join(args.save_dir, 'ranked_results'),
topk=20,
)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
for epoch in range(args.start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion_xent, criterion_htri, optimizer,
trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch + 1) > args.start_eval and args.eval_step > 0 and (
epoch + 1) % args.eval_step == 0 or (epoch +
1) == args.max_epoch:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(
best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu: use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_imgreid_dataset(
root=args.root,
name=args.dataset,
split_id=args.split_id,
cuhk03_labeled=args.cuhk03_labeled,
cuhk03_classic_split=args.cuhk03_classic_split,
use_lmdb=args.use_lmdb,
)
transform_train = T.Compose([
T.Random2DTranslation(args.height, args.width),
# T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
transform_test = T.Compose([
T.Resize((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
trainset = ImageDataset(dataset.train,
transform=transform_train,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.train_lmdb_path)
trainloader = DataLoader(
trainset,
batch_size=args.train_batch,
shuffle=True,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=True,
)
queryset = ImageDataset(dataset.query,
transform=transform_test,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.query_lmdb_path)
queryloader = DataLoader(
queryset,
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
galleryset = ImageDataset(dataset.gallery,
transform=transform_test,
use_lmdb=args.use_lmdb,
lmdb_path=dataset.gallery_lmdb_path)
galleryloader = DataLoader(
galleryset,
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dataset.num_train_pids,
loss={'xent'},
use_gpu=use_gpu)
print("Model size: {:.3f} M".format(count_num_param(model)))
# summary(model, (3, 160, 64))
criterion = CrossEntropyLabelSmooth(num_classes=dataset.num_train_pids,
use_gpu=use_gpu)
optimizer = init_optim(args.optim, model.parameters(), args.lr,
args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
start_epoch = args.start_epoch
if args.fixbase_epoch > 0:
if hasattr(model, 'classifier') and isinstance(model.classifier,
nn.Module):
optimizer_tmp = init_optim(args.optim,
model.classifier.parameters(),
args.fixbase_lr, args.weight_decay)
else:
print(
"Warn: model has no attribute 'classifier' and fixbase_epoch is reset to 0"
)
args.fixbase_epoch = 0
if args.load_weights:
# load pretrained weights but ignore layers that don't match in size
print("Loading pretrained weights from '{}'".format(args.load_weights))
if torch.cuda.is_available():
checkpoint = torch.load(args.load_weights)
else:
checkpoint = torch.load(args.load_weights, map_location='cpu')
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {
k: v
for k, v in pretrain_dict.items()
if k in model_dict and model_dict[k].size() == v.size()
}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
if args.resume:
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(start_epoch, rank1))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
test(model, queryloader, galleryloader, use_gpu)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
if args.fixbase_epoch > 0:
print(
"Train classifier for {} epochs while keeping base network frozen".
format(args.fixbase_epoch))
for epoch in range(args.fixbase_epoch):
start_train_time = time.time()
train(epoch,
model,
criterion,
optimizer_tmp,
trainloader,
use_gpu,
freeze_bn=True)
train_time += round(time.time() - start_train_time)
del optimizer_tmp
print("Now open all layers for training")
for epoch in range(start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion, optimizer, trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch + 1) > args.start_eval and args.eval_step > 0 and (
epoch + 1) % args.eval_step == 0 or (epoch +
1) == args.max_epoch:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
'''
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint({
'state_dict': state_dict,
'epoch': epoch,
}, True, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch+1) + '.pth.tar'))
'''
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(
best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'), mode='a')
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'), mode='a')
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_imgreid_dataset(name=args.dataset,
dataset_dir=args.root,
fore_dir=args.fore_dir)
transform_train = ST.Compose([
ST.Scale((args.height, args.width), interpolation=3),
ST.RandomHorizontalFlip(),
ST.ToTensor(),
ST.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
ST.RandomErasing(0.5)
])
transform_test = ST.Compose([
ST.Scale((args.height, args.width), interpolation=3),
ST.ToTensor(),
ST.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
trainloader = DataLoader(
ImageDataset_hardSplit_seg(dataset.train, transform=transform_train),
sampler=RandomIdentitySampler(dataset.train,
num_instances=args.num_instances),
batch_size=args.train_batch,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=True,
)
queryloader = DataLoader(
ImageDataset(dataset.query, transform=transform_test),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
galleryloader = DataLoader(
ImageDataset(dataset.gallery, transform=transform_test),
batch_size=args.test_batch,
shuffle=False,
num_workers=args.workers,
pin_memory=pin_memory,
drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dataset.num_train_pids)
print(model)
criterion_xent = CrossEntropyLabelSmooth(use_gpu=use_gpu)
criterion_htri = TripletLoss()
criterion_mask = MaskLoss()
criterion_split = HardSplitLoss()
criterion_cluster = ClusterLoss()
optimizer = init_optim(args.optim, model.parameters(), args.lr,
args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
if args.resume:
if check_isfile(args.resume):
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
args.start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(
args.start_epoch, rank1))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
test(model, queryloader, galleryloader, use_gpu)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
for epoch in range(args.start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion_xent, criterion_htri, criterion_mask,
criterion_split, criterion_cluster, optimizer, trainloader,
use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch + 1) > args.start_eval and (
epoch + 1) % args.eval_step == 0 or epoch == 0:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(
best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
print("==========\nArgs:{}\n==========".format(args))
def _train_session(self, session, use_centroid=False):
# assert session in range(0, 9)
print('Training session {}'.format(session))
self.cur_session = session
if session > 0:
self.memory.del_noisy_slots()
memory_vals = self.memory.m_vals.cpu().numpy()
memory_vals_counter = Counter(memory_vals)
print('memory val:', len(memory_vals_counter), memory_vals_counter.most_common())
# === Data
print('Preparing data {} with session {}...'.format(self.dataset, session))
train_loader, eval_loader = self.get_dataloader(session)
if session == 0:
# train_loader, eval_loader = self.data_manager.get_dataloaders()
max_epoch = self.args.max_epoch_sess0
m_replays = None
else:
# if self.dataset == 'miniImageNet':
# train_loader = self.data_manager.get_dataloaders(session=session, is_fewshot=True)
# eval_loader = self.data_manager.get_dataloaders(session=session, is_fewshot=False)
# elif self.dataset == 'cifar100' or 'cub-200' or 'casia-face':
# train_loader, eval_loader = self.data_manager.get_dataloaders(
# session=session, is_fewshot=True)
# else:
# raise NotImplementedError
# Memory replay data
m_keys, m_targets = self._get_nonempty_memory_slots()
# m_keys = m_keys.unsqueeze(-1).unsqueeze(-1).repeat(1, 1, 3, 3) # [nonempty, key_dim, 3, 3]
m_replays = (m_keys, m_targets)
max_epoch = 20 # Todo
print('Num of batches of train loader:', len(train_loader))
self.eval_dataloaders.append(eval_loader)
start_time = time.time()
train_time = 0
best_epoch = 0
# best_acc = self._eval_epoch(epoch=0, eval_loader=eval_loader)
best_acc = -1
best_state = None
# === Train
for epoch in range(1, max_epoch + 1):
if session == 0:
if epoch == 1:
adjust_lr(self.optimizer_all, 1e-3)
if epoch > 10:
adjust_lr(self.optimizer_all, 1e-4)
else:
if epoch == 1:
adjust_lr(self.optimizer_all, 1e-4)
if epoch > 15:
adjust_lr(self.optimizer_all, 1e-5)
cur_lr = self.optimizer_all.param_groups[0]['lr']
self.writer.add_scalar('Learning rate', cur_lr, global_step=epoch)
epoch_time_start = time.time()
self._train_epoch(epoch, cur_lr, train_loader, m_replays)
train_time += round(time.time() - epoch_time_start)
# === Eval on current session's dataloader only
if epoch == self.args.max_epoch_sess0 or epoch % self.args.eval_per_epoch == 0:
if use_centroid:
self.memory.upd_centroids()
acc = self._eval_epoch(epoch, eval_loader, use_centroid=use_centroid)
# === Save checkpoint
is_best = acc > best_acc
if is_best or epoch == 2 or epoch % self.args.save_per_epoch == 0:
state = {
'encoder_state_dict': self.encoder.state_dict(),
'memory_state_dict': self.memory.state_dict(),
'decoder_state_dict': self.decoder.state_dict(),
'acc': acc,
'session': session,
'epoch': epoch,
}
file_path = osp.join(
self.args.save_dir, self.dataset, 'incr', self.args.encoder,
'session' + str(session), 'ckp_ep' + str(epoch) + '.ckp')
if epoch == 2:
pass
# save_checkpoint(state, False, file_path)
else:
save_checkpoint(state, is_best, file_path)
if is_best:
best_acc = acc
best_epoch = epoch
best_state = copy.deepcopy(state)
print('==> Test best accuracy {:.2%}, achieved at epoch {}'.format(
best_acc, best_epoch))
torch.cuda.empty_cache()
# Load best checkpoint
self.encoder.load_state_dict(best_state['encoder_state_dict'])
self.memory.load_state_dict(best_state['memory_state_dict'])
self.decoder.load_state_dict(best_state['decoder_state_dict'])
elapsed = str(datetime.timedelta(seconds=round(time.time() - start_time)))
train_time = str(datetime.timedelta(seconds=train_time))
print('Session {} finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}'.format(
session, elapsed, train_time))
# print("==========\nArgs:{}\n==========".format(self.args))
memory_vals = self.memory.m_vals.cpu().numpy()
memory_vals_counter = Counter(memory_vals)
print('memory val:', len(memory_vals_counter), memory_vals_counter.most_common())
def main():
torch.manual_seed(1)
os.environ['CUDA_VISIBLE_DEVICES'] = config.gpu_devices
use_gpu = torch.cuda.is_available()
sys.stdout = Logger(config.save_dir, config.checkpoint_suffix,
config.evaluate)
print("\n==========\nArgs:")
config.print_parameter()
print("==========\n")
if use_gpu:
print("Currently using GPU {}".format(config.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(1)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(config.dataset))
dataset = data_manager.init_imgreid_dataset(name=config.dataset,
root=config.data_root)
transform_train = T.Compose([
T.Random2DTranslation(config.height, config.width),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=data_mean, std=data_std),
])
transform_test = T.Compose([
T.Resize((config.height, config.width)),
T.ToTensor(),
T.Normalize(mean=data_mean, std=data_std),
])
pin_memory = True if use_gpu else False
# train_batch_sampler = BalancedBatchSampler(dataset.train, n_classes=8, n_samples=8)
# train_batch_sampler = CCLBatchSampler(dataset.train, n_classes=n_classes, n_samples=n_samples)
# train_batch_sampler = CCLBatchSamplerV2(dataset.train, n_classes=n_classes, pos_samp_cnt=pos_samp_cnt,
# neg_samp_cnt=neg_samp_cnt, each_cls_max_cnt=each_cls_max_cnt)
train_batch_sampler = ClassSampler(dataset.train,
sample_cls_cnt=config.sample_cls_cnt,
each_cls_cnt=config.each_cls_cnt)
# trainloader = DataLoader(
# ImageDataset(dataset.train, transform=transform_train),
# batch_sampler=train_batch_sampler, batch_size=args.train_batch,
# shuffle=True, num_workers=args.workers, pin_memory=pin_memory, drop_last=True
# )
trainloader = DataLoader(ImageDatasetWCL(dataset,
data_type='train',
merge_h=256,
merge_w=256,
mean_std=[data_mean, data_std]),
batch_sampler=train_batch_sampler,
num_workers=config.workers,
pin_memory=pin_memory)
queryloader = DataLoader(
ImageDatasetWCL(dataset.query,
data_type='query',
merge_h=256,
merge_w=256,
mean_std=[data_mean, data_std]),
batch_size=config.test_batch,
shuffle=False,
num_workers=config.workers,
pin_memory=pin_memory,
drop_last=False,
)
galleryloader = DataLoader(
ImageDatasetWCL(dataset.gallery,
data_type='gallery',
merge_h=256,
merge_w=256,
mean_std=[data_mean, data_std]),
batch_size=config.test_batch,
shuffle=False,
num_workers=config.workers,
pin_memory=pin_memory,
drop_last=False,
)
if config.dataset == 'vehicleid':
train_query_loader = None
train_gallery_loader = None
else:
train_query_loader = DataLoader(
ImageDatasetWCL(dataset.train_query,
data_type='train_query',
merge_h=256,
merge_w=256,
mean_std=[data_mean, data_std]),
batch_size=config.test_batch,
shuffle=False,
num_workers=config.workers,
pin_memory=pin_memory,
drop_last=False,
)
train_gallery_loader = DataLoader(
ImageDatasetWCL(dataset.train_gallery,
data_type='train_gallery',
merge_h=256,
merge_w=256,
mean_std=[data_mean, data_std]),
batch_size=config.test_batch,
shuffle=False,
num_workers=config.workers,
pin_memory=pin_memory,
drop_last=False,
)
print("Initializing model: {}".format(config.arch))
model = init_model(name=config.arch,
num_classes=dataset.num_train_pids,
loss_type=config.loss_type)
print("Model size: {:.3f} M".format(count_num_param(model)))
if config.loss_type == 'xent':
criterion = [nn.CrossEntropyLoss(), nn.CrossEntropyLoss()]
elif config.loss_type == 'xent_triplet':
criterion = XentTripletLoss(
margin=config.margin,
triplet_selector=RandomNegativeTripletSelector(
margin=config.margin),
each_cls_cnt=config.each_cls_cnt,
n_class=config.sample_cls_cnt)
elif config.loss_type == 'xent_tripletv2':
criterion = XentTripletLossV2(
margin=config.margin,
triplet_selector=RandomNegativeTripletSelectorV2(
margin=config.margin),
each_cls_cnt=config.each_cls_cnt,
n_class=config.sample_cls_cnt)
# criterion = XentTripletLossV2(margin=0.04, triplet_selector=RandomNegativeTripletSelectorV2(margin=0.04),
# each_cls_cnt=config.each_cls_cnt, n_class=config.sample_cls_cnt)
# criterion = XentGroupTripletLossV2(margin=0.8, triplet_selector=AllTripletSelector(margin=0.8),
# each_cls_cnt=config.each_cls_cnt, n_class=config.sample_cls_cnt)
else:
raise KeyError("Unsupported loss: {}".format(config.loss_type))
optimizer = init_optim(config.optim, model.parameters(), config.lr,
config.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=config.stepsize,
gamma=config.gamma)
if config.resume is not None:
if check_isfile(config.resume):
checkpoint = torch.load(config.resume)
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {
k: v
for k, v in pretrain_dict.items()
if k in model_dict and model_dict[k].size() == v.size()
}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
config.start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
if 'mAP' in checkpoint:
mAP = checkpoint['mAP']
else:
mAP = 0
print("Loaded checkpoint from '{}'".format(config.resume))
print("- start_epoch: {}\n- rank1: {}\n- mAP: {}".format(
config.start_epoch, rank1, mAP))
if use_gpu:
model = nn.DataParallel(model).cuda()
if config.evaluate:
print("Evaluate only")
test_model(model, queryloader, galleryloader, train_query_loader,
train_gallery_loader, use_gpu, config.test_batch,
config.loss_type, config.euclidean_distance_loss)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_map = 0
best_epoch = 0
for epoch in range(config.start_epoch, config.max_epoch):
print("==> Start training")
start_train_time = time.time()
scheduler.step()
print('epoch:', epoch, 'lr:', scheduler.get_lr())
train(epoch, model, criterion, optimizer, trainloader,
config.loss_type, config.print_freq)
train_time += round(time.time() - start_train_time)
if epoch >= config.start_eval and config.eval_step > 0 and epoch % config.eval_step == 0 \
or epoch == config.max_epoch:
print("==> Test")
rank1, mAP = test_model(model, queryloader, galleryloader,
train_query_loader, train_gallery_loader,
use_gpu, config.test_batch,
config.loss_type,
config.euclidean_distance_loss)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_map = mAP
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'mAP': mAP,
'epoch': epoch + 1,
},
is_best,
use_gpu_suo=False,
fpath=osp.join(
config.save_dir, 'checkpoint_ep' + str(epoch + 1) +
config.checkpoint_suffix + '.pth.tar'))
print("==> Best Rank-1 {:.2%}, mAP {:.2%}, achieved at epoch {}".format(
best_rank1, best_map, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print(
"Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".
format(elapsed, train_time))
def main():
torch.manual_seed(args.seed)
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu: use_gpu = False
if not args.evaluate:
sys.stdout = Logger(osp.join(args.save_dir, 'log_train.txt'))
else:
sys.stdout = Logger(osp.join(args.save_dir, 'log_test.txt'))
print("==========\nArgs:{}\n==========".format(args))
if use_gpu:
print("Currently using GPU {}".format(args.gpu_devices))
cudnn.benchmark = True
torch.cuda.manual_seed_all(args.seed)
else:
print("Currently using CPU (GPU is highly recommended)")
print("Initializing dataset {}".format(args.dataset))
dataset = data_manager.init_vidreid_dataset(root=args.root, name=args.dataset)
transform_train = T.Compose([
T.Random2DTranslation(args.height, args.width),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
transform_test = T.Compose([
T.Resize((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
pin_memory = True if use_gpu else False
# decompose tracklets into images for image-based training
new_train = []
for img_paths, pid, camid in dataset.train:
for img_path in img_paths:
new_train.append((img_path, pid, camid))
trainloader = DataLoader(
ImageDataset(new_train, transform=transform_train),
sampler=RandomIdentitySampler(new_train, num_instances=args.num_instances),
batch_size=args.train_batch, num_workers=args.workers,
pin_memory=pin_memory, drop_last=True,
)
queryloader = DataLoader(
VideoDataset(dataset.query, seq_len=args.seq_len, sample='evenly', transform=transform_test),
batch_size=args.test_batch, shuffle=False, num_workers=args.workers,
pin_memory=pin_memory, drop_last=False,
)
galleryloader = DataLoader(
VideoDataset(dataset.gallery, seq_len=args.seq_len, sample='evenly', transform=transform_test),
batch_size=args.test_batch, shuffle=False, num_workers=args.workers,
pin_memory=pin_memory, drop_last=False,
)
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch, num_classes=dataset.num_train_pids, loss={'xent', 'htri'})
print("Model size: {:.3f} M".format(count_num_param(model)))
criterion_xent = CrossEntropyLabelSmooth(num_classes=dataset.num_train_pids, use_gpu=use_gpu)
criterion_htri = TripletLoss(margin=args.margin)
optimizer = init_optim(args.optim, model.parameters(), args.lr, args.weight_decay)
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.stepsize, gamma=args.gamma)
start_epoch = args.start_epoch
if args.load_weights:
# load pretrained weights but ignore layers that don't match in size
print("Loading pretrained weights from '{}'".format(args.load_weights))
checkpoint = torch.load(args.load_weights)
pretrain_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrain_dict = {k: v for k, v in pretrain_dict.items() if k in model_dict and model_dict[k].size() == v.size()}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
if args.resume:
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
rank1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(start_epoch, rank1))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
test(model, queryloader, galleryloader, args.pool, use_gpu)
return
start_time = time.time()
train_time = 0
best_rank1 = -np.inf
best_epoch = 0
print("==> Start training")
for epoch in range(start_epoch, args.max_epoch):
start_train_time = time.time()
train(epoch, model, criterion_xent, criterion_htri, optimizer, trainloader, use_gpu)
train_time += round(time.time() - start_train_time)
scheduler.step()
if (epoch+1) > args.start_eval and args.eval_step > 0 and (epoch+1) % args.eval_step == 0 or (epoch+1) == args.max_epoch:
print("==> Test")
rank1 = test(model, queryloader, galleryloader, args.pool, use_gpu)
is_best = rank1 > best_rank1
if is_best:
best_rank1 = rank1
best_epoch = epoch + 1
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint({
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, is_best, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch+1) + '.pth.tar'))
print("==> Best Rank-1 {:.1%}, achieved at epoch {}".format(best_rank1, best_epoch))
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
train_time = str(datetime.timedelta(seconds=train_time))
print("Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.".format(elapsed, train_time))
