def main():
torch.multiprocessing.set_start_method("spawn", force=True)
"""Create the model and start the evaluation process."""
args = get_arguments()
os.environ["CUDA_VISIBLE_DEVICES"]=args.gpu
gpus = [int(i) for i in args.gpu.split(',')]
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
deeplab = CorrPM_Model(args.num_classes, args.num_points)
if len(gpus) > 1:
model = DataParallelModel(deeplab)
else:
model = deeplab
if not os.path.exists(args.save_dir):
os.makedirs(args.save_dir)
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
if args.data_name == 'lip':
lip_dataset = LIPDataSet(args.data_dir, VAL_POSE_ANNO_FILE, args.dataset, crop_size=input_size, transform=transform)
num_samples = len(lip_dataset)
valloader = data.DataLoader(lip_dataset, batch_size=args.batch_size * len(gpus),
shuffle=False, num_workers=4, pin_memory=True)
restore_from = args.restore_from
state_dict = model.state_dict().copy()
state_dict_old = torch.load(restore_from)
for key in state_dict.keys():
if key not in state_dict_old.keys():
print(key)
for key, nkey in zip(state_dict_old.keys(), state_dict.keys()):
if key != nkey:
state_dict[key[7:]] = deepcopy(state_dict_old[key])
else:
state_dict[key] = deepcopy(state_dict_old[key])
model.load_state_dict(state_dict)
model.eval()
model.cuda()
parsing_preds, scales, centers = valid(model, valloader, input_size, num_samples, len(gpus))
mIoU = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size, args.dataset)
print(mIoU)
end = datetime.datetime.now()
print(end - start, 'seconds')
print(end)
def main():
"""Create the model and start the training."""
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
writer = SummaryWriter(args.snapshot_dir)
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
cudnn.enabled = True
# cudnn related setting
cudnn.benchmark = True
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.enabled = True
deeplab = Res_Deeplab(num_classes=args.num_classes)
# dump_input = torch.rand((args.batch_size, 3, input_size[0], input_size[1]))
# writer.add_graph(deeplab.cuda(), dump_input.cuda(), verbose=False)
saved_state_dict = torch.load(args.restore_from)
new_params = deeplab.state_dict().copy()
for i in saved_state_dict:
i_parts = i.split('.')
# print(i_parts)
if not i_parts[0] == 'fc':
new_params['.'.join(i_parts[0:])] = saved_state_dict[i]
deeplab.load_state_dict(new_params)
model = DataParallelModel(deeplab)
model.cuda()
criterion = CriterionAll()
criterion = DataParallelCriterion(criterion)
criterion.cuda()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
trainloader = data.DataLoader(LIPDataSet(args.data_dir,
args.dataset,
crop_size=input_size,
transform=transform),
batch_size=args.batch_size * len(gpus),
shuffle=True,
num_workers=2,
pin_memory=True)
#lip_dataset = LIPDataSet(args.data_dir, 'val', crop_size=input_size, transform=transform)
#num_samples = len(lip_dataset)
#valloader = data.DataLoader(lip_dataset, batch_size=args.batch_size * len(gpus),
# shuffle=False, pin_memory=True)
optimizer = optim.SGD(model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer.zero_grad()
total_iters = args.epochs * len(trainloader)
for epoch in range(args.start_epoch, args.epochs):
model.train()
for i_iter, batch in enumerate(trainloader):
i_iter += len(trainloader) * epoch
lr = adjust_learning_rate(optimizer, i_iter, total_iters)
images, labels, edges, _ = batch
labels = labels.long().cuda(non_blocking=True)
edges = edges.long().cuda(non_blocking=True)
preds = model(images)
loss = criterion(preds, [labels, edges])
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 100 == 0:
writer.add_scalar('learning_rate', lr, i_iter)
writer.add_scalar('loss', loss.data.cpu().numpy(), i_iter)
if i_iter % 500 == 0:
images_inv = inv_preprocess(images, args.save_num_images)
labels_colors = decode_parsing(labels,
args.save_num_images,
args.num_classes,
is_pred=False)
edges_colors = decode_parsing(edges,
args.save_num_images,
2,
is_pred=False)
if isinstance(preds, list):
preds = preds[0]
preds_colors = decode_parsing(preds[0][-1],
args.save_num_images,
args.num_classes,
is_pred=True)
pred_edges = decode_parsing(preds[1][-1],
args.save_num_images,
2,
is_pred=True)
img = vutils.make_grid(images_inv,
normalize=False,
scale_each=True)
lab = vutils.make_grid(labels_colors,
normalize=False,
scale_each=True)
pred = vutils.make_grid(preds_colors,
normalize=False,
scale_each=True)
edge = vutils.make_grid(edges_colors,
normalize=False,
scale_each=True)
pred_edge = vutils.make_grid(pred_edges,
normalize=False,
scale_each=True)
writer.add_image('Images/', img, i_iter)
writer.add_image('Labels/', lab, i_iter)
writer.add_image('Preds/', pred, i_iter)
writer.add_image('Edges/', edge, i_iter)
writer.add_image('PredEdges/', pred_edge, i_iter)
print('iter = {} of {} completed, loss = {}'.format(
i_iter, total_iters,
loss.data.cpu().numpy()))
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir, 'LIP_epoch_' + str(epoch) + '.pth'))
#parsing_preds, scales, centers = valid(model, valloader, input_size, num_samples, len(gpus))
#mIoU = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size)
#print(mIoU)
#writer.add_scalars('mIoU', mIoU, epoch)
end = timeit.default_timer()
print(end - start, 'seconds')
def main():
"""start multiprocessing method"""
try:
mp.set_start_method('spawn')
except RuntimeError:
pass
"""Create the model and start the training."""
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
cudnn.enabled = True
# cudnn related setting
cudnn.benchmark = True
torch.backends.cudnn.deterministic = True #False
torch.backends.cudnn.enabled = True
torch.cuda.empty_cache()
deeplab = CorrPM_Model(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
new_params = deeplab.state_dict().copy()
i = 0
print("Now is loading pre-trained res101 model!")
for i in saved_state_dict:
i_parts = i.split('.')
if not i_parts[0] == 'fc':
new_params['.'.join(i_parts[0:])] = saved_state_dict[i]
deeplab.load_state_dict(new_params)
criterion = CriterionPoseEdge()
criterion = DataParallelCriterion(criterion)
criterion.cuda()
snapshot_fname = osp.join(args.snapshot_dir, 'LIP_epoch_')
snapshot_best_fname = osp.join(args.snapshot_dir, 'LIP_best.pth')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
dataset_lip = LIPDataSet(args.data_dir,
args.pose_anno_file,
args.dataset,
crop_size=input_size,
dataset_list=args.dataset_list,
transform=transform)
trainloader = data.DataLoader(dataset_lip,
batch_size=args.batch_size * len(gpus),
shuffle=True,
num_workers=1,
pin_memory=True)
lip_dataset = LIPDataSet(args.data_dir,
VAL_ANNO_FILE,
'val',
crop_size=input_size,
dataset_list=args.dataset_list,
transform=transform)
num_samples = len(lip_dataset)
valloader = data.DataLoader(lip_dataset,
batch_size=args.batch_size * len(gpus),
shuffle=False,
num_workers=0,
pin_memory=True)
optimizer = optim.SGD(deeplab.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
model = DataParallelModel(deeplab)
model.cuda()
optimizer.zero_grad()
total_iters = args.epochs * len(trainloader)
total_iter_per_batch = len(trainloader)
print("total iters:", total_iters)
best_iou = 0
i_iter = 0
temp = time.time()
for epoch in range(args.start_epoch, args.epochs):
model.train()
for i_iter, batch in enumerate(trainloader):
iter_lr = i_iter + epoch * len(trainloader)
lr = adjust_learning_rate(optimizer, iter_lr, total_iters)
images, labels, pose, edge, _ = batch
labels = labels.long().cuda(non_blocking=True)
edge = edge.long().cuda(non_blocking=True)
pose = pose.float().cuda(non_blocking=True)
preds = model(images)
loss = criterion(preds, [labels, edge, pose])
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 500 == 0:
tim = time.time()
print('iter:{}/{},loss:{:.3f},lr:{:.3e},time:{:.1f}'.format(
i_iter, total_iter_per_batch,
loss.data.cpu().numpy(), lr, tim - temp))
temp = tim
h = time.time()
if epoch % 5 == 0:
print("----->Epoch:", epoch)
parsing_preds, scales, centers = valid(model, valloader,
input_size, num_samples,
len(gpus), criterion, args)
if args.dataset_list == '_id.txt':
mIoU = compute_mean_ioU(parsing_preds, scales, centers,
args.num_classes, args.data_dir,
input_size)
miou = mIoU['Mean IU']
is_best_iou = miou > best_iou
best_iou = max(miou, best_iou)
torch.save(model.state_dict(), snapshot_fname + '.pth')
if is_best_iou:
print("Best iou epoch: ", epoch)
shutil.copyfile(snapshot_fname + '.pth', snapshot_best_fname)
end = datetime.datetime.now()
print(end - start, 'seconds')
print(end)
def main():
"""Create the model and start the training."""
print(args)
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
writer = SummaryWriter(args.snapshot_dir)
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
cudnn.enabled = True
# cudnn related setting
cudnn.benchmark = True
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.enabled = True
deeplab = get_cls_net(config=config,
num_classes=args.num_classes,
is_train=True)
model = DataParallelModel(deeplab)
saved_state_dict = torch.load(args.restore_from)
if args.start_epoch > 0:
model = DataParallelModel(deeplab)
model.load_state_dict(saved_state_dict['state_dict'])
else:
new_params = model.state_dict().copy()
state_dict_pretrain = saved_state_dict['state_dict']
for state_name in state_dict_pretrain:
if state_name in new_params:
new_params[state_name] = state_dict_pretrain[state_name]
#print ('LOAD',state_name)
else:
print('NOT LOAD', state_name)
model.load_state_dict(new_params)
print('-------Load Weight', args.restore_from)
model.cuda()
criterion = CriterionAll2()
criterion = DataParallelCriterion(criterion)
criterion.cuda()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
trainloader = data.DataLoader(LIPDataSet(args.data_dir,
args.dataset,
crop_size=input_size,
transform=transform),
batch_size=args.batch_size * len(gpus),
shuffle=True,
num_workers=4,
pin_memory=True)
num_samples = 5000
'''
list_map = []
for part in deeplab.path_list:
list_map = list_map + list(map(id, part.parameters()))
base_params = filter(lambda p: id(p) not in list_map,
deeplab.parameters())
params_list = []
params_list.append({'params': base_params, 'lr':args.learning_rate*0.1})
for part in deeplab.path_list:
params_list.append({'params': part.parameters()})
print ('len(params_list)',len(params_list))
'''
list_map = []
for part in deeplab.path_list:
list_map = list_map + list(map(id, part.parameters()))
base_params = filter(lambda p: id(p) not in list_map, deeplab.parameters())
params_list = []
params_list.append({'params': base_params, 'lr': 1e-6})
for part in deeplab.path_list:
params_list.append({'params': part.parameters()})
print('len(params_list)', len(params_list))
optimizer = torch.optim.SGD(params_list,
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
if args.start_epoch > 0:
optimizer.load_state_dict(saved_state_dict['optimizer'])
print('========Load Optimizer', args.restore_from)
optimizer.zero_grad()
total_iters = args.epochs * len(trainloader)
for epoch in range(args.start_epoch, args.epochs):
model.train()
for i_iter, batch in enumerate(trainloader):
i_iter += len(trainloader) * epoch
#lr = adjust_learning_rate(optimizer, i_iter, total_iters)
lr = adjust_learning_rate_parsing(optimizer, epoch)
images, labels, _ = batch
labels = labels.long().cuda(non_blocking=True)
preds = model(images)
loss = criterion(preds, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 100 == 0:
writer.add_scalar('learning_rate', lr, i_iter)
writer.add_scalar('loss', loss.data.cpu().numpy(), i_iter)
print('epoch = {}, iter = {} of {} completed,lr={}, loss = {}'.
format(epoch, i_iter, total_iters, lr,
loss.data.cpu().numpy()))
if epoch % 2 == 0 or epoch == args.epochs:
time.sleep(10)
save_checkpoint(model, epoch, optimizer)
# parsing_preds, scales, centers = valid(model, valloader, input_size, num_samples, len(gpus))
# mIoU = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size)
# print(mIoU)
# writer.add_scalars('mIoU', mIoU, epoch)
time.sleep(10)
save_checkpoint(model, epoch, optimizer)
end = timeit.default_timer()
print(end - start, 'seconds')
def main():
"""Create the model and start the training."""
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
f = open('./tlip.txt','w')
f.write(str(args)+'\n')
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
cudnn.enabled = True
#cudnn.benchmark = False
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.enabled = True
deeplab = EEN(num_classes=args.num_classes)
# Initialize the model with resnet101-imagenet.pth
saved_state_dict = torch.load(args.restore_from)
new_params = deeplab.state_dict().copy()
for i in saved_state_dict:
i_parts = i.split('.')
if not i_parts[0] == 'fc':
new_params['.'.join(i_parts[0:])] = saved_state_dict[i]
deeplab.load_state_dict(new_params)
# Initialize the model with cihp_11.pth
"""args.start_epoch = 11
res = './scihp/cihp_11.pth'
state_dict = deeplab.state_dict().copy()
state_dict_old = torch.load(res)
for key, nkey in zip(state_dict_old.keys(), state_dict.keys()):
if key != nkey:
state_dict[key[7:]] = deepcopy(state_dict_old[key])
else:
state_dict[key] = deepcopy(state_dict_old[key])
deeplab.load_state_dict(state_dict)"""
#########
model = DataParallelModel(deeplab)
model.cuda()
criterion = CriterionAll()
criterion = DataParallelCriterion(criterion)
criterion.cuda()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
trainloader = data.DataLoader(HumanDataSet(args.data_dir, args.dataset, crop_size=input_size, transform=transform),
batch_size=args.batch_size * len(gpus), shuffle=True, num_workers=2,
pin_memory=True)
optimizer = optim.SGD(
model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
optimizer.zero_grad()
total_iters = args.epochs * len(trainloader)
print(len(trainloader))
for epoch in range(args.start_epoch, args.epochs):
start_time = timeit.default_timer()
model.train()
for i_iter, batch in enumerate(trainloader):
i_iter += len(trainloader) * epoch
lr = adjust_learning_rate(optimizer, i_iter, total_iters)
images, labels, edges, _ = batch
#pdb.set_trace()
labels = labels.long().cuda(non_blocking=True)
edges = edges.long().cuda(non_blocking=True)
preds = model(images)
#pdb.set_trace()
loss = criterion(preds, [labels, edges])
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 100 ==0:
print('iter = {} of {} completed, loss = {}'.format(i_iter, total_iters, loss.data.cpu().numpy()))
f.write('iter = '+str(i_iter)+', loss = '+str(loss.data.cpu().numpy())+', lr = '+str(lr)+'\n')
torch.save(model.state_dict(), osp.join(args.snapshot_dir, 'lip_' + str(epoch) + '.pth'))
end_time = timeit.default_timer()
print('epoch: ', epoch ,', the time is: ',(end_time-start_time))
end = timeit.default_timer()
print(end - start, 'seconds')
f.close()
def main():
"""Create the model and start the training."""
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
writer = SummaryWriter(args.snapshot_dir)
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
cudnn.enabled = True
# cudnn related setting
cudnn.benchmark = True
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.enabled = True
deeplab = Res_Deeplab(num_classes=args.num_classes)
print(type(deeplab))
# dump_input = torch.rand((args.batch_size, 3, input_size[0], input_size[1]))
# writer.add_graph(deeplab.cuda(), dump_input.cuda(), verbose=False)
"""
HOW DOES IT LOAD ONLY RESNET101 AND NOT THE RSTE OF THE NET ?
"""
# UNCOMMENT THE FOLLOWING COMMENTARY TO INITIALYZE THE WEIGHTS
# Load resnet101 weights trained on imagenet and copy it in new_params
saved_state_dict = torch.load(args.restore_from)
new_params = deeplab.state_dict().copy()
# CHECK IF WEIGHTS BELONG OR NOT TO THE MODEL
# belongs = 0
# doesnt_b = 0
# for key in saved_state_dict:
# if key in new_params:
# belongs+=1
# print('key=', key)
# else:
# doesnt_b+=1
# # print('key=', key)
# print('belongs = ', belongs, 'doesnt_b=', doesnt_b)
# print('res101 len',len(saved_state_dict))
# print('new param len',len(new_params))
for i in saved_state_dict:
i_parts = i.split('.')
# print('i_parts:', i_parts)
# exp : i_parts: ['layer2', '3', 'bn2', 'running_mean']
# The deeplab weight modules have diff name than args.restore_from weight modules
if i_parts[0] == 'module' and not i_parts[1] == 'fc' :
if new_params['.'.join(i_parts[1:])].size() == saved_state_dict[i].size():
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
else:
if not i_parts[0] == 'fc':
if new_params['.'.join(i_parts[0:])].size() == saved_state_dict[i].size():
new_params['.'.join(i_parts[0:])] = saved_state_dict[i]
deeplab.load_state_dict(new_params)
# UNCOMMENT UNTIL HERE
model = DataParallelModel(deeplab)
model.cuda()
criterion = CriterionAll()
criterion = DataParallelCriterion(criterion)
criterion.cuda()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
trainloader = data.DataLoader(cartoonDataSet(args.data_dir, args.dataset, crop_size=input_size, transform=transform),
batch_size=args.batch_size * len(gpus), shuffle=True, num_workers=8,
pin_memory=True)
#mIoU for Val set
val_dataset = cartoonDataSet(args.data_dir, 'val', crop_size=input_size, transform=transform)
numVal_samples = len(val_dataset)
valloader = data.DataLoader(val_dataset, batch_size=args.batch_size * len(gpus),
shuffle=False, pin_memory=True)
#mIoU for trainTest set
trainTest_dataset = cartoonDataSet(args.data_dir, 'trainTest', crop_size=input_size, transform=transform)
numTest_samples = len(trainTest_dataset)
testloader = data.DataLoader(trainTest_dataset, batch_size=args.batch_size * len(gpus),
shuffle=False, pin_memory=True)
optimizer = optim.SGD(
model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
optimizer.zero_grad()
# valBatch_idx = 0
total_iters = args.epochs * len(trainloader)
for epoch in range(args.start_epoch, args.epochs):
model.train()
for i_iter, batch in enumerate(trainloader):
i_iter += len(trainloader) * epoch
lr = adjust_learning_rate(optimizer, i_iter, total_iters)
images, labels, _, _ = batch
labels = labels.long().cuda(non_blocking=True)
preds = model(images)
# print('preds size in batch', len(preds))
# print('Size of Segmentation1 tensor output:',preds[0][0].size())
# print('Segmentation2 tensor output:',preds[0][-1].size())
# print('Size of Edge tensor output:',preds[1][-1].size())
loss = criterion(preds, [labels])
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 100 == 0:
writer.add_scalar('learning_rate', lr, i_iter)
writer.add_scalar('loss', loss.data.cpu().numpy(), i_iter)
if i_iter % 500 == 0:
# print('In iter%500 Size of Segmentation2 GT: ', labels.size())
# print('In iter%500 Size of edges GT: ', edges.size())
images_inv = inv_preprocess(images, args.save_num_images)
# print(labels[0])
labels_colors = decode_parsing(labels, args.save_num_images, args.num_classes, is_pred=False)
# if isinstance(preds, list):
# print(len(preds))
# preds = preds[0]
# val_images, _ = valloader[valBatch_idx]
# valBatch_idx += 1
# val_sampler = torch.utils.data.RandomSampler(val_dataset,replacement=True, num_samples=args.batch_size * len(gpus))
# sample_valloader = data.DataLoader(val_dataset, batch_size=args.batch_size * len(gpus),
# shuffle=False, sampler=val_sampler , pin_memory=True)
# val_images, _ = sample_valloader
# preds_val = model(val_images)
# With multiple GPU, preds return a list, therefore we extract the tensor in the list
if len(gpus)>1:
preds= preds[0]
# preds_val = preds_val[0]
# print('In iter%500 Size of Segmentation2 tensor output:',preds[0][0][-1].size())
# preds[0][-1] cause model returns [[seg1, seg2], [edge]]
preds_colors = decode_parsing(preds[0][-1], args.save_num_images, args.num_classes, is_pred=True)
# preds_val_colors = decode_parsing(preds_val[0][-1], args.save_num_images, args.num_classes, is_pred=True)
# print("preds type:",type(preds)) #list
# print("preds shape:", len(preds)) #2
# hello = preds[0][-1]
# print("preds type [0][-1]:",type(hello)) #<class 'torch.Tensor'>
# print("preds len [0][-1]:", len(hello)) #12
# print("preds len [0][-1]:", hello.shape)#torch.Size([12, 8, 96, 96])
# print("preds color's type:",type(preds_colors))#torch.tensor
# print("preds color's shape:",preds_colors.shape) #([2,3,96,96])
# print('IMAGE', images_inv.size())
img = vutils.make_grid(images_inv, normalize=False, scale_each=True)
lab = vutils.make_grid(labels_colors, normalize=False, scale_each=True)
pred = vutils.make_grid(preds_colors, normalize=False, scale_each=True)
# print("preD type:",type(pred)) #<class 'torch.Tensor'>
# print("preD len:", len(pred))# 3
# print("preD shape:", pred.shape)#torch.Size([3, 100, 198])
# 1=head red, 2=body green , 3=left_arm yellow, 4=right_arm blue, 5=left_leg pink
# 6=right_leg skuBlue, 7=tail grey
writer.add_image('Images/', img, i_iter)
writer.add_image('Labels/', lab, i_iter)
writer.add_image('Preds/', pred, i_iter)
print('iter = {} of {} completed, loss = {}'.format(i_iter, total_iters, loss.data.cpu().numpy()))
print('end epoch:', epoch)
if epoch%99 == 0:
torch.save(model.state_dict(), osp.join(args.snapshot_dir, 'DFPnet_epoch_' + str(epoch) + '.pth'))
if epoch%5 == 0 and epoch<500:
# mIou for Val set
parsing_preds, scales, centers = valid(model, valloader, input_size, numVal_samples, len(gpus))
'''
Insert a sample of prediction of a val image on tensorboard
'''
# generqte a rand number between len(parsing_preds)
sample = random.randint(0, len(parsing_preds)-1)
#loader resize and convert to tensor the image
loader = transforms.Compose([
transforms.Resize(input_size),
transforms.ToTensor()
])
# get val segmentation path and open the file
list_path = os.path.join(args.data_dir, 'val' + '_id.txt')
val_id = [i_id.strip() for i_id in open(list_path)]
gt_path = os.path.join(args.data_dir, 'val' + '_segmentations', val_id[sample] + '.png')
gt =Image.open(gt_path)
gt = loader(gt)
#put gt back from 0 to 255
gt = (gt*255).int()
# convert pred from ndarray to PIL image then to tensor
display_preds = Image.fromarray(parsing_preds[sample])
tensor_display_preds = transforms.ToTensor()(display_preds)
#put gt back from 0 to 255
tensor_display_preds = (tensor_display_preds*255).int()
# color them
val_preds_colors = decode_parsing(tensor_display_preds, num_images=1, num_classes=args.num_classes, is_pred=False)
gt_color = decode_parsing(gt, num_images=1, num_classes=args.num_classes, is_pred=False)
# put in grid
pred_val = vutils.make_grid(val_preds_colors, normalize=False, scale_each=True)
gt_val = vutils.make_grid(gt_color, normalize=False, scale_each=True)
writer.add_image('Preds_val/', pred_val, epoch)
writer.add_image('Gt_val/', gt_val, epoch)
mIoUval = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size, 'val')
print('For val set', mIoUval)
writer.add_scalars('mIoUval', mIoUval, epoch)
# mIou for trainTest set
parsing_preds, scales, centers = valid(model, testloader, input_size, numTest_samples, len(gpus))
mIoUtest = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size, 'trainTest')
print('For trainTest set', mIoUtest)
writer.add_scalars('mIoUtest', mIoUtest, epoch)
else:
if epoch%20 == 0 and epoch>=500:
# mIou for Val set
parsing_preds, scales, centers = valid(model, valloader, input_size, numVal_samples, len(gpus))
'''
Insert a sample of prediction of a val image on tensorboard
'''
# generqte a rand number between len(parsing_preds)
sample = random.randint(0, len(parsing_preds)-1)
#loader resize and convert to tensor the image
loader = transforms.Compose([
transforms.Resize(input_size),
transforms.ToTensor()
])
# get val segmentation path and open the file
list_path = os.path.join(args.data_dir, 'val' + '_id.txt')
val_id = [i_id.strip() for i_id in open(list_path)]
gt_path = os.path.join(args.data_dir, 'val' + '_segmentations', val_id[sample] + '.png')
gt =Image.open(gt_path)
gt = loader(gt)
#put gt back from 0 to 255
gt = (gt*255).int()
# convert pred from ndarray to PIL image then to tensor
display_preds = Image.fromarray(parsing_preds[sample])
tensor_display_preds = transforms.ToTensor()(display_preds)
#put gt back from 0 to 255
tensor_display_preds = (tensor_display_preds*255).int()
# color them
val_preds_colors = decode_parsing(tensor_display_preds, num_images=1, num_classes=args.num_classes, is_pred=False)
gt_color = decode_parsing(gt, num_images=1, num_classes=args.num_classes, is_pred=False)
# put in grid
pred_val = vutils.make_grid(val_preds_colors, normalize=False, scale_each=True)
gt_val = vutils.make_grid(gt_color, normalize=False, scale_each=True)
writer.add_image('Preds_val/', pred_val, epoch)
writer.add_image('Gt_val/', gt_val, epoch)
mIoUval = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size, 'val')
print('For val set', mIoUval)
writer.add_scalars('mIoUval', mIoUval, epoch)
# mIou for trainTest set
parsing_preds, scales, centers = valid(model, testloader, input_size, numTest_samples, len(gpus))
mIoUtest = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size, 'trainTest')
print('For trainTest set', mIoUtest)
writer.add_scalars('mIoUtest', mIoUtest, epoch)
end = timeit.default_timer()
print(end - start, 'seconds')
def main():
args = get_arguments()
print(args)
start_epoch = 0
cycle_n = 0
if not os.path.exists(args.log_dir):
os.makedirs(args.log_dir)
with open(os.path.join(args.log_dir, 'args.json'), 'w') as opt_file:
json.dump(vars(args), opt_file)
gpus = [int(i) for i in args.gpu.split(',')]
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
input_size = list(map(int, args.input_size.split(',')))
cudnn.enabled = True
cudnn.benchmark = True
# Model Initialization
AugmentCE2P = networks.init_model(args.arch,
num_classes=args.num_classes,
pretrained=args.imagenet_pretrain)
model = DataParallelModel(AugmentCE2P)
model.cuda()
IMAGE_MEAN = AugmentCE2P.mean
IMAGE_STD = AugmentCE2P.std
INPUT_SPACE = AugmentCE2P.input_space
print('image mean: {}'.format(IMAGE_MEAN))
print('image std: {}'.format(IMAGE_STD))
print('input space:{}'.format(INPUT_SPACE))
restore_from = args.model_restore
if os.path.exists(restore_from):
print('Resume training from {}'.format(restore_from))
checkpoint = torch.load(restore_from)
model.load_state_dict(checkpoint['state_dict'])
start_epoch = checkpoint['epoch']
SCHP_AugmentCE2P = networks.init_model(args.arch,
num_classes=args.num_classes,
pretrained=args.imagenet_pretrain)
schp_model = DataParallelModel(SCHP_AugmentCE2P)
schp_model.cuda()
if os.path.exists(args.schp_restore):
print('Resuming schp checkpoint from {}'.format(args.schp_restore))
schp_checkpoint = torch.load(args.schp_restore)
schp_model_state_dict = schp_checkpoint['state_dict']
cycle_n = schp_checkpoint['cycle_n']
schp_model.load_state_dict(schp_model_state_dict)
# Loss Function
criterion = CriterionAll(lambda_1=args.lambda_s,
lambda_2=args.lambda_e,
lambda_3=args.lambda_c,
num_classes=args.num_classes)
criterion = DataParallelCriterion(criterion)
criterion.cuda()
# Data Loader
if INPUT_SPACE == 'BGR':
print('BGR Transformation')
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=IMAGE_MEAN, std=IMAGE_STD),
])
elif INPUT_SPACE == 'RGB':
print('RGB Transformation')
transform = transforms.Compose([
transforms.ToTensor(),
BGR2RGB_transform(),
transforms.Normalize(mean=IMAGE_MEAN, std=IMAGE_STD),
])
train_dataset = LIPDataSet(args.data_dir,
args.split_name,
crop_size=input_size,
transform=transform)
train_loader = data.DataLoader(train_dataset,
batch_size=args.batch_size * len(gpus),
num_workers=16,
shuffle=True,
pin_memory=True,
drop_last=True)
print('Total training samples: {}'.format(len(train_dataset)))
# Optimizer Initialization
optimizer = optim.SGD(model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
lr_scheduler = SGDRScheduler(optimizer,
total_epoch=args.epochs,
eta_min=args.learning_rate / 100,
warmup_epoch=10,
start_cyclical=args.schp_start,
cyclical_base_lr=args.learning_rate / 2,
cyclical_epoch=args.cycle_epochs)
total_iters = args.epochs * len(train_loader)
start = timeit.default_timer()
for epoch in range(start_epoch, args.epochs):
lr_scheduler.step(epoch=epoch)
lr = lr_scheduler.get_lr()[0]
model.train()
for i_iter, batch in enumerate(train_loader):
i_iter += len(train_loader) * epoch
images, labels, _ = batch
labels = labels.cuda(non_blocking=True)
edges = generate_edge_tensor(labels)
labels = labels.type(torch.cuda.LongTensor)
edges = edges.type(torch.cuda.LongTensor)
preds = model(images)
# Online Self Correction Cycle with Label Refinement
if cycle_n >= 1:
with torch.no_grad():
soft_preds = schp_model(images)
soft_parsing = []
soft_edge = []
for soft_pred in soft_preds:
soft_parsing.append(soft_pred[0][-1])
soft_edge.append(soft_pred[1][-1])
soft_preds = torch.cat(soft_parsing, dim=0)
soft_edges = torch.cat(soft_edge, dim=0)
else:
soft_preds = None
soft_edges = None
loss = criterion(preds, [labels, edges, soft_preds, soft_edges],
cycle_n)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i_iter % 100 == 0:
print('iter = {} of {} completed, lr = {}, loss = {}'.format(
i_iter, total_iters, lr,
loss.data.cpu().numpy()))
if (epoch + 1) % (args.eval_epochs) == 0:
schp.save_checkpoint(
{
'epoch': epoch + 1,
'state_dict': model.state_dict(),
},
False,
args.log_dir,
filename='checkpoint_{}.pth.tar'.format(epoch + 1))
# Self Correction Cycle with Model Aggregation
if (epoch + 1) >= args.schp_start and (
epoch + 1 - args.schp_start) % args.cycle_epochs == 0:
print('Self-correction cycle number {}'.format(cycle_n))
schp.moving_average(schp_model, model, 1.0 / (cycle_n + 1))
cycle_n += 1
schp.bn_re_estimate(train_loader, schp_model)
schp.save_schp_checkpoint(
{
'state_dict': schp_model.state_dict(),
'cycle_n': cycle_n,
},
False,
args.log_dir,
filename='schp_{}_checkpoint.pth.tar'.format(cycle_n))
torch.cuda.empty_cache()
end = timeit.default_timer()
print('epoch = {} of {} completed using {} s'.format(
epoch, args.epochs, (end - start) / (epoch - start_epoch + 1)))
end = timeit.default_timer()
print('Training Finished in {} seconds'.format(end - start))
