def main():
global args
torch.manual_seed(args.seed)
if not args.use_avai_gpus:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu:
use_gpu = False
log_name = 'log_test.txt' if args.evaluate else 'log_train.txt'
sys.stderr = sys.stdout = Logger(osp.join(args.save_dir, log_name))
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, however, GPU is highly recommended")
print("Initializing image data manager")
dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args))
trainloader, testloader_dict = dm.return_dataloaders()
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dm.num_train_pids,
loss={'xent'},
use_gpu=use_gpu,
args=vars(args))
print(model)
print("Model size: {:.3f} M".format(count_num_param(model)))
criterion = get_criterion(dm.num_train_pids, use_gpu, args)
regularizer = get_regularizer(vars(args))
optimizer = init_optimizer(model.parameters(), **optimizer_kwargs(args))
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=args.stepsize,
gamma=args.gamma)
if args.load_weights and check_isfile(args.load_weights):
# load pretrained weights but ignore layers that don't match in size
try:
checkpoint = torch.load(args.load_weights)
except Exception as e:
print(e)
checkpoint = torch.load(args.load_weights,
map_location={'cuda:0': '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)
print("Loaded pretrained weights from '{}'".format(args.load_weights))
if args.resume and check_isfile(args.resume):
checkpoint = torch.load(args.resume)
state = model.state_dict()
state.update(checkpoint['state_dict'])
model.load_state_dict(state)
# args.start_epoch = checkpoint['epoch'] + 1
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(args.start_epoch,
checkpoint['rank1']))
if use_gpu:
model = nn.DataParallel(model).cuda()
if args.evaluate:
print("Evaluate only")
for name in args.target_names:
print("Evaluating {} ...".format(name))
queryloader = testloader_dict[name]['query'], testloader_dict[
name]['query_flip']
galleryloader = testloader_dict[name]['gallery'], testloader_dict[
name]['gallery_flip']
distmat = test(model,
queryloader,
galleryloader,
use_gpu,
return_distmat=True,
name=name)
from scipy import io as s_io
fname = 'ABD-Net-' + name + '.mat'
root_A = './distmat'
if not os.path.exists(root_A):
os.makedirs(root_A)
fname = os.path.join(root_A, fname)
s_io.savemat(fname, {'distmat': distmat})
if args.visualize_ranks:
visualize_ranked_results(distmat,
dm.return_testdataset_by_name(name),
save_dir=osp.join(
args.save_dir, 'ranked_results',
name),
topk=20)
return
start_time = time.time()
ranklogger = RankLogger(args.source_names, args.target_names)
train_time = 0
print("==> Start training")
if args.fixbase_epoch > 0:
oldenv = os.environ.get('sa', '')
os.environ['sa'] = ''
print(
"Train {} for {} epochs while keeping other layers frozen".format(
args.open_layers, args.fixbase_epoch))
initial_optim_state = optimizer.state_dict()
for epoch in range(args.fixbase_epoch):
start_train_time = time.time()
train(epoch,
model,
criterion,
regularizer,
optimizer,
trainloader,
use_gpu,
fixbase=True)
train_time += round(time.time() - start_train_time)
print("Done. All layers are open to train for {} epochs".format(
args.max_epoch))
optimizer.load_state_dict(initial_optim_state)
os.environ['sa'] = oldenv
max_r1 = 0
for epoch in range(args.start_epoch, args.max_epoch):
start_train_time = time.time()
print(epoch)
print(criterion)
train(epoch,
model,
criterion,
regularizer,
optimizer,
trainloader,
use_gpu,
fixbase=False)
train_time += round(time.time() - start_train_time)
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
save_checkpoint(
{
'state_dict': state_dict,
'rank1': 0,
'epoch': epoch,
}, False,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
scheduler.step()
if (epoch + 1) > args.start_eval and args.eval_freq > 0 and (
epoch + 1) % args.eval_freq == 0 or (epoch +
1) == args.max_epoch:
print("==> Test")
for name in args.target_names:
print("Evaluating {} ...".format(name))
queryloader = testloader_dict[name]['query'], testloader_dict[
name]['query_flip']
galleryloader = testloader_dict[name][
'gallery'], testloader_dict[name]['gallery_flip']
rank1 = test(model,
queryloader,
galleryloader,
use_gpu,
name=name)
ranklogger.write(name, epoch + 1, rank1)
if use_gpu:
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
if max_r1 < rank1:
print('Save!', max_r1, rank1)
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
}, False, osp.join(args.save_dir,
'checkpoint_best.pth.tar'))
max_r1 = rank1
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))
ranklogger.show_summary()
def main():
global use_apex
global args
torch.manual_seed(args.seed)
if not args.use_avai_gpus:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu:
use_gpu = False
log_name = 'log_test.txt' if args.evaluate else 'log_train.txt'
sys.stderr = sys.stdout = Logger(osp.join(args.save_dir, log_name))
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, however, GPU is highly recommended")
print("Initializing image data manager")
dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args))
trainloader, testloader_dict = dm.return_dataloaders()
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch,
num_classes=dm.num_train_pids,
loss={'xent'},
use_gpu=use_gpu,
args=vars(args))
print(model)
print("Model size: {:.3f} M".format(count_num_param(model)))
if use_gpu:
print("using gpu")
model = model.cuda()
print("criterion===>")
criterion = get_criterion(dm.num_train_pids, use_gpu, args)
print(criterion)
print("regularizer===>")
regularizer = get_regularizer(vars(args))
print(regularizer)
print("optimizer===>")
optimizer = init_optimizer(model.parameters(), **optimizer_kwargs(args))
print(optimizer)
print("scheduler===>")
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
'max',
factor=0.1,
patience=5,
verbose=True)
print(scheduler)
if args.load_weights and check_isfile(args.load_weights):
# load pretrained weights but ignore layers that don't match in size
try:
checkpoint = torch.load(args.load_weights)
except Exception as e:
print(e)
checkpoint = torch.load(args.load_weights,
map_location={'cuda:0': '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)
print("Loaded pretrained weights from '{}'".format(args.load_weights))
max_r1 = 0
if args.resume and check_isfile(args.resume):
checkpoint = torch.load(args.resume)
state = model.state_dict()
state.update(checkpoint['state_dict'])
model.load_state_dict(state)
optimizer.load_state_dict(checkpoint['optimizer'])
args.start_epoch = checkpoint['epoch'] + 1
max_r1 = checkpoint['rank1']
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(args.start_epoch,
checkpoint['rank1']))
if use_apex:
print("using apex")
model, optimizer = amp.initialize(model, optimizer, opt_level="O0")
if args.evaluate:
print("Evaluate only")
for name in args.target_names:
print("Evaluating {} ...".format(name))
queryloader = testloader_dict[name]['query'], testloader_dict[
name]['query_flip']
galleryloader = testloader_dict[name]['gallery'], testloader_dict[
name]['gallery_flip']
distmat = test(model,
queryloader,
galleryloader,
use_gpu,
return_distmat=True)
if args.visualize_ranks:
visualize_ranked_results(distmat,
dm.return_testdataset_by_name(name),
save_dir=osp.join(
args.save_dir, 'ranked_results',
name),
topk=20)
return
start_time = time.time()
ranklogger = RankLogger(args.source_names, args.target_names)
train_time = 0
print("==> Start training")
if args.fixbase_epoch > 0:
oldenv = os.environ.get('sa', '')
os.environ['sa'] = ''
print(
"Train {} for {} epochs while keeping other layers frozen".format(
args.open_layers, args.fixbase_epoch))
initial_optim_state = optimizer.state_dict()
for epoch in range(args.fixbase_epoch):
start_train_time = time.time()
train(epoch,
model,
criterion,
regularizer,
optimizer,
trainloader,
use_gpu,
fixbase=True)
train_time += round(time.time() - start_train_time)
print("Done. All layers are open to train for {} epochs".format(
args.max_epoch))
optimizer.load_state_dict(initial_optim_state)
os.environ['sa'] = oldenv
for epoch in range(args.start_epoch, args.max_epoch):
auto_reset_learning_rate(optimizer, args)
print(
f"===========================start epoch {epoch + 1} {now()}==========================================="
)
print(f"lr:{optimizer.param_groups[0]['lr']}")
loss = train(epoch,
model,
criterion,
regularizer,
optimizer,
trainloader,
use_gpu,
fixbase=False)
train_time += round(time.time() - start_train_time)
state_dict = model.state_dict()
rank1 = 0
if (epoch + 1) > args.start_eval and args.eval_freq > 0 and (
epoch + 1) % args.eval_freq == 0 or (epoch +
1) == args.max_epoch:
print("==> Test")
for name in args.target_names:
print("Evaluating {} ...".format(name))
queryloader = testloader_dict[name]['query'], testloader_dict[
name]['query_flip']
galleryloader = testloader_dict[name][
'gallery'], testloader_dict[name]['gallery_flip']
rank1 = test(model, queryloader, galleryloader, use_gpu)
ranklogger.write(name, epoch + 1, rank1)
if max_r1 < rank1:
print('Save!', max_r1, rank1)
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
'optimizer': optimizer.state_dict(),
}, False, osp.join(args.save_dir,
'checkpoint_best.pth.tar'))
max_r1 = rank1
save_checkpoint(
{
'state_dict': state_dict,
'rank1': rank1,
'epoch': epoch,
'optimizer': optimizer.state_dict(),
}, False,
osp.join(args.save_dir,
'checkpoint_ep' + str(epoch + 1) + '.pth.tar'))
scheduler.step(rank1)
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))
ranklogger.show_summary()
def main():
global args, dropout_optimizer
torch.manual_seed(args.seed)
if not args.use_avai_gpus:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
use_gpu = torch.cuda.is_available()
if args.use_cpu:
use_gpu = False
log_name = 'log_test.txt' if args.evaluate else 'log_train.txt'
sys.stderr = sys.stdout = Logger(osp.join(args.save_dir, log_name))
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, however, GPU is highly recommended")
print("Initializing image data manager")
dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args))
trainloader, testloader_dict = dm.return_dataloaders()
print("Initializing model: {}".format(args.arch))
model = models.init_model(name=args.arch, num_classes=dm.num_train_pids, loss={'xent'}, use_gpu=use_gpu,
dropout_optimizer=dropout_optimizer)
print(model)
print("Model size: {:.3f} M".format(count_num_param(model)))
# criterion = WrappedCrossEntropyLoss(num_classes=dm.num_train_pids, use_gpu=use_gpu, label_smooth=args.label_smooth)
criterion, fix_criterion, switch_criterion, htri_param_controller = get_criterions(dm.num_train_pids, use_gpu, args)
regularizer, reg_param_controller = get_regularizer(args.regularizer)
optimizer = init_optimizer(model.parameters(), **optimizer_kwargs(args))
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.stepsize, gamma=args.gamma)
if args.load_weights and check_isfile(args.load_weights):
# load pretrained weights but ignore layers that don't match in size
try:
checkpoint = torch.load(args.load_weights)
except Exception as e:
print(e)
checkpoint = torch.load(args.load_weights, map_location={'cuda:0': 'cpu'})
# dropout_optimizer.set_p(checkpoint.get('dropout_p', 0))
# print(list(checkpoint.keys()), checkpoint['dropout_p'])
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 and check_isfile(args.resume):
checkpoint = torch.load(args.resume)
state = model.state_dict()
state.update(checkpoint['state_dict'])
model.load_state_dict(state)
# args.start_epoch = checkpoint['epoch'] + 1
print("Loaded checkpoint from '{}'".format(args.resume))
print("- start_epoch: {}\n- rank1: {}".format(args.start_epoch, checkpoint['rank1']))
if use_gpu:
model = nn.DataParallel(model, device_ids=list(range(len(args.gpu_devices.split(','))))).cuda()
extract_train_info(model, trainloader)
