def main():
opt = TestOptions()
args = opt.initialize()
if not os.path.exists(args.save):
os.makedirs(args.save)
model = CreateModel(args)
model.eval()
model.cuda()
targetloader = CreateTrgDataLoader(args)
for index, batch in enumerate(targetloader):
if index % 100 == 0:
print '%d processd' % index
image, _, name = batch
output = model(Variable(image).cuda())
output = nn.functional.upsample(output, (1024, 2048), mode='bilinear', align_corners=True).cpu().data[0].numpy()
output = output.transpose(1,2,0)
output_nomask = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output_nomask)
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('/')[-1]
output_nomask.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
compute_mIoU(args.gt_dir, args.save, args.devkit_dir, args.restore_from)
def main():
testing_entropy = 0
args = parse_args()
if not os.path.exists(args.save):
os.makedirs(args.save)
args.init_weights = root_base+'/snapshots/' + args.model_name
model = CreateModel(args)
model.eval()
model.cuda()
targetloader = CreateTrgDataLoader(args)
for index, batch in tqdm.tqdm(enumerate(targetloader)):
image, _, name,_ = batch
output = model(Variable(image).cuda())
output = nn.functional.softmax(output, dim=1)
testing_entropy += self_entropy(roll_axis(output.cpu().data[0].numpy()))
output = nn.functional.upsample(output, (1024, 2048), mode='bilinear', align_corners=True).cpu().data[0].numpy()
#output = np.multiply(output,priors)
output = output.transpose(1,2,0)
output_nomask = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output_nomask)
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('/')[-1]
output_nomask.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
mIou_ = compute_mIoU(args.gt_dir, args.save, args.devkit_dir, '')
def main():
opt = TestOptions()
args = opt.initialize()
if not os.path.exists(args.save):
os.makedirs(args.save)
maxiou = 0
root = args.restore_from
for i in range(1, 51):
#args.restore_from = './snapshots/gta2city_vgg/gta5_{0:d}'.format(i*2000)
args.restore_from = root + '_{0:d}'.format(i * 2000)
model = CreateModel(args)
print(args.restore_from)
model.eval()
model.cuda()
targetloader = CreateTrgDataLoader(args)
for index, batch in enumerate(targetloader):
if index % 100 == 0:
print '%d processd' % index
image, _, name = batch
output1, output2 = model(Variable(image).cuda())
output = output1 + output2
output = nn.functional.softmax(output, dim=1)
output = nn.functional.upsample(
output, (1024, 2048), mode='bilinear',
align_corners=True).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output_nomask = np.asarray(np.argmax(output, axis=2),
dtype=np.uint8)
output_col = colorize_mask(output_nomask)
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('/')[-1]
output_nomask.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' %
(args.save, name.split('.')[0]))
iou = compute_mIoU(args.gt_dir, args.save, args.devkit_dir,
args.restore_from)
#print(save_path)
if iou > maxiou:
maxiou = iou
best_model = args.restore_from
print('The best model is {:s}, the best IOU is {:f}'.format(
best_model, maxiou))
def main():
opt = TestOptions()
args = opt.initialize()
if args.target == 'deepglobe':
size = 612
elif args.target == 'deepglobe224':
size = 224
elif args.target == 'worldview' or args.target == 'worldviewFI' or args.target == 'worldviewGR' or args.target == 'worldviewFIc' or args.target == 'worldviewc':
size = 512
elif args.target == 'sentinel' or args.target == 'sentinelFI' or args.target == 'sentinelGR' or args.target == 'sentinelc':
size = 224
if args.target == 'pleiades' or args.target == 'pleiadesFI' or args.target == 'pleiadesGR':
size = 448
if not os.path.exists(args.save):
os.makedirs(args.save)
model = CreateModel(args)
model.eval()
model.cuda()
targetloader = CreateTrgDataLoader(args)
for index, batch in enumerate(targetloader):
if index % 100 == 0:
print('%d processd' % index)
image, _, name = batch
output = model(Variable(image).cuda())
output = nn.functional.softmax(output, dim=1)
output = nn.functional.upsample(
output, (size, size), mode='bilinear',
align_corners=True).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output_nomask = np.asarray(np.argmax(output, axis=2), dtype=np.uint8)
output_col = colorize_mask(output_nomask)
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('/')[-1]
if args.target == 'deepglobe' or args.target == 'deepglobe224':
output_nomask.save('%s/%s.png' %
(args.save, os.path.splitext(name)[0]))
else:
output_nomask.save('%s/%s.png' % (args.save, name))
output_col.save('%s/%s_color.png' % (args.save, name.split('.')[0]))
compute_mIoU(args.gt_dir, args.save, args.target, args.devkit_dir,
args.restore_from)
def main():
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time': Timer()}
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
targetloader = CreateActTrgDataLoader(args, 'train')
targetloader_iter = iter(targetloader)
testloader = CreateActTrgDataLoader(args, 'test')
model, optimizer = CreateModel(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
train_writer = tensorboardX.SummaryWriter(
os.path.join(args.snapshot_dir, "logs"))
bce_loss = torch.nn.BCEWithLogitsLoss()
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
loss = ['loss_trg', 'eval_loss']
_t['iter time'].tic()
best_loss_eval = None
best_step = 0
eval_loss = np.array([0])
for i in range(start_iter, args.num_steps):
model.train()
model.module.adjust_learning_rate(args, optimizer, i)
optimizer.zero_grad()
try:
trg_img, trg_lbl, _, paths = next(targetloader_iter)
except StopIteration:
targetloader_iter = iter(targetloader)
trg_img, trg_lbl, _, paths = next(targetloader_iter)
trg_score, loss_trg = model(trg_img, lbl=trg_lbl)
loss_trg = loss_trg
loss_trg.mean().backward()
optimizer.step()
if (i + 1) % args.save_pred_every == 0:
with torch.no_grad():
model.eval()
eval_loss = 0
for test_img, test_lbl, _, _ in testloader:
test_score, loss_test = model(test_img, lbl=test_lbl)
eval_loss += loss_test.mean().item() * test_img.size(0)
eval_loss /= len(testloader.dataset)
if best_loss_eval == None or eval_loss < best_loss_eval:
best_loss_eval = eval_loss
best_step = i + 1
print('taking snapshot ... eval_loss: {}'.format(eval_loss))
torch.save(
model.module.state_dict(),
os.path.join(args.snapshot_dir,
str(i + 1) + '.pth'))
eval_loss = np.array([eval_loss])
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print('[it %d][src loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_trg.mean().data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff))
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()
for m in loss:
train_writer.add_scalar(m, eval(m).mean(), i + 1)
def main():
#load parameters######################################################################
opt = TrainOptions()
args = opt.initialize()
#create timer##########################################################################
_t = {'iter time' : Timer()}
#create logs##########################################################################
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
#Load data#############################################################################
sourceloader, targetloader = CreateSrcDataLoader(args), CreateTrgDataLoader(args)
targetloader_iter, sourceloader_iter = iter(targetloader), iter(sourceloader)
#Load deeplab+ optimizer###############################################################
model, optimizer = CreateModel(args)
#Load Descriminator+ optimizer#########################################################
model_D, optimizer_D = CreateDiscriminator(args)
#start training###############################################################################################
start_iter = 0
#restore checkoint##############################################################################
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
#start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[2])
#Tensorboard####################################################################################
train_writer = tensorboardX.SummaryWriter(os.path.join(args.snapshot_dir, "logs", model_name))
bce_loss = torch.nn.BCEWithLogitsLoss()
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D.train()
model_D.cuda()
loss = ['loss_seg_src', 'loss_seg_trg', 'loss_D_trg_fake', 'loss_D_src_real', 'loss_D_trg_real']
_t['iter time'].tic()
for i in range(start_iter, args.num_steps):
model.adjust_learning_rate(args, optimizer, i)
model_D.adjust_learning_rate(args, optimizer_D, i)
optimizer.zero_grad()
optimizer_D.zero_grad()
for param in model_D.parameters():
param.requires_grad = False
src_img, src_lbl, _, _ = sourceloader_iter.next()
src_img, src_lbl = Variable(src_img).cuda(), Variable(src_lbl.long()).cuda()
src_seg_score = model(src_img, lbl=src_lbl) # M(S),Ys
loss_seg_src = model.loss # Lseg(M(S),Ys)
loss_seg_src.backward()
if args.data_label_folder_target is not None:
trg_img, trg_lbl, _, _ = targetloader_iter.next()
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(trg_lbl.long()).cuda()
trg_seg_score = model(trg_img, lbl=trg_lbl)
loss_seg_trg = model.loss
else:
trg_img, _, name = targetloader_iter.next()
trg_img = Variable(trg_img).cuda()
trg_seg_score = model(trg_img) # M(T)
loss_seg_trg = 0
outD_trg = model_D(F.softmax(trg_seg_score), 0)
loss_D_trg_fake = model_D.loss
loss_trg = args.lambda_adv_target * loss_D_trg_fake + loss_seg_trg
loss_trg.backward()
for param in model_D.parameters():
param.requires_grad = True
src_seg_score, trg_seg_score = src_seg_score.detach(), trg_seg_score.detach()
outD_src = model_D(F.softmax(src_seg_score), 0) # D(M(S), source)
loss_D_src_real = model_D.loss / 2
loss_D_src_real.backward()
outD_trg = model_D(F.softmax(trg_seg_score), 1) # D(M(T), target)
loss_D_trg_real = model_D.loss / 2
loss_D_trg_real.backward()
optimizer.step()
optimizer_D.step()
for m in loss:
train_writer.add_scalar(m, eval(m), i+1)
if (i+1) % args.save_pred_every == 0:
print('taking snapshot ...')
torch.save(model.state_dict(), os.path.join(args.snapshot_dir, '%s_' %(args.source) +str(i+1)+'.pth' ))
torch.save(model_D.state_dict(), os.path.join(args.snapshot_dir, '%s_' %(args.source) +str(i+1)+'_D.pth' ))
if (i+1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print('[it %d][src seg loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff))
if i + 1 > args.num_steps_stop:
print ('finish training')
break
_t['iter time'].tic()
def main():
# torch.manual_seed(1234)
# torch.cuda.manual_seed(1234)
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time' : Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateSrcDataLoader(args), CreateTrgDataLoader(args)
targetloader_iter, sourceloader_iter = iter(targetloader), iter(sourceloader)
model, optimizer = CreateModel(args)
model_D, optimizer_D = CreateDiscriminator(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
train_writer = tensorboardX.SummaryWriter(os.path.join(args.snapshot_dir, "logs", model_name))
bce_loss = torch.nn.BCEWithLogitsLoss()
cent_loss=ConditionalEntropyLoss()
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D.train()
model_D.cuda()
loss = ['loss_seg_src', 'loss_seg_trg', 'loss_D_trg_fake', 'loss_D_src_real', 'loss_D_trg_real']
_t['iter time'].tic()
pbar = tqdm(range(start_iter,args.num_steps_stop))
#for i in range(start_iter, args.num_steps):
for i in pbar:
model.adjust_learning_rate(args, optimizer, i)
model_D.adjust_learning_rate(args, optimizer_D, i)
optimizer.zero_grad()
optimizer_D.zero_grad()
for param in model_D.parameters():
param.requires_grad = False
src_img, src_lbl, _, _ = sourceloader_iter.next()
src_img, src_lbl = Variable(src_img).cuda(), Variable(src_lbl.long()).cuda()
src_seg_score = model(src_img)
loss_seg_src = CrossEntropy2d(src_seg_score, src_lbl)
#loss_seg_src = model.loss
loss_seg_src.backward()
if args.data_label_folder_target is not None:
trg_img, trg_lbl, _, _ = targetloader_iter.next()
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(trg_lbl.long()).cuda()
trg_seg_score = model(trg_img)
loss_seg_trg = model.loss
else:
trg_img, _, name = targetloader_iter.next()
trg_img = Variable(trg_img).cuda()
trg_seg_score = model(trg_img)
#ipdb.set_trace()
loss_seg_trg= cent_loss(trg_seg_score)
#loss_seg_trg= entropy_loss(F.softmax(trg_seg_score))
#loss_seg_trg = 0
outD_trg = model_D(F.softmax(trg_seg_score))
loss_D_trg_fake = bce_loss(outD_trg, Variable(torch.FloatTensor(outD_trg.data.size()).fill_(0)).cuda())
#loss_D_trg_fake = model_D.loss
loss_trg = args.lambda_adv_target * (loss_D_trg_fake + loss_seg_trg)
loss_trg.backward()
for param in model_D.parameters():
param.requires_grad = True
src_seg_score, trg_seg_score = src_seg_score.detach(), trg_seg_score.detach()
outD_src = model_D(F.softmax(src_seg_score))
loss_D_src_real = bce_loss(outD_src, Variable(torch.FloatTensor(outD_src.data.size()).fill_(0)).cuda())/ 2
#loss_D_src_real = model_D.loss / 2
loss_D_src_real.backward()
outD_trg = model_D(F.softmax(trg_seg_score))
loss_D_trg_real = bce_loss(outD_trg, Variable(torch.FloatTensor(outD_trg.data.size()).fill_(1)).cuda())/ 2
#loss_D_trg_real = model_D.loss / 2
loss_D_trg_real.backward()
d_loss=loss_D_src_real.data+ loss_D_trg_real.data
optimizer.step()
optimizer_D.step()
for m in loss:
train_writer.add_scalar(m, eval(m), i+1)
if (i+1) % args.save_pred_every == 0:
print 'taking snapshot ...'
torch.save(model.state_dict(), os.path.join(args.snapshot_dir, '%s_' %(args.source) +str(i+1)+'.pth' ))
torch.save(model_D.state_dict(), os.path.join(args.snapshot_dir, '%s_' %(args.source) +str(i+1)+'_D.pth' ))
if (i+1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print '[it %d][src seg loss %.4f][adv loss %.4f][d loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data, loss_D_trg_fake.data,d_loss,optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff)
if i + 1 > args.num_steps_stop:
print 'finish training'
break
_t['iter time'].tic()
def main():
# torch.manual_seed(1234)
# torch.cuda.manual_seed(1234)
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time': Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateSrcDataLoader(
args), CreateTrgDataLoader(args)
targetloader_iter, sourceloader_iter = iter(targetloader), iter(
sourceloader)
model, optimizer = CreateModel(args)
model_D, optimizer_D = CreateDiscriminator(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
train_writer = tensorboardX.SummaryWriter(
os.path.join(args.snapshot_dir, "logs", model_name))
bce_loss = torch.nn.BCEWithLogitsLoss()
l1_loss = torch.nn.L1Loss()
cos_loss = torch.nn.CosineSimilarity(dim=0, eps=1e-06)
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D.train()
model_D.cuda()
loss = [
'loss_seg_src', 'loss_seg_trg', 'loss_D_trg_fake', 'loss_D_src_real',
'loss_D_trg_real'
]
_t['iter time'].tic()
pbar = tqdm(range(start_iter, args.num_steps_stop))
#for i in range(start_iter, args.num_steps):
for i in pbar:
model.adjust_learning_rate(args, optimizer, i)
model_D.adjust_learning_rate(args, optimizer_D, i)
optimizer.zero_grad()
optimizer_D.zero_grad()
for param in model_D.parameters():
param.requires_grad = False
src_img, src_lbl, _, _ = sourceloader_iter.next()
src_img, src_lbl = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda()
src_seg_score, src_seg_score2 = model(src_img)
loss_seg_src1 = CrossEntropy2d(src_seg_score, src_lbl)
loss_seg_src2 = CrossEntropy2d(src_seg_score2, src_lbl)
loss_seg_src = loss_seg_src1 + loss_seg_src2
loss_seg_src.backward()
if args.data_label_folder_target is not None:
trg_img, trg_lbl, _, _ = targetloader_iter.next()
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(
trg_lbl.long()).cuda()
trg_seg_score = model(trg_img)
loss_seg_trg = model.loss
else:
trg_img, _, name = targetloader_iter.next()
trg_img = Variable(trg_img).cuda()
trg_seg_score, trg_seg_score2 = model(trg_img)
loss_seg_trg = 0
outD_trg = model_D(F.softmax(trg_seg_score))
outD_trg2 = model_D(F.softmax(trg_seg_score2))
loss_D_trg_fake1 = bce_loss(
outD_trg,
Variable(torch.FloatTensor(outD_trg.data.size()).fill_(0)).cuda())
loss_D_trg_fake2 = bce_loss(
outD_trg2,
Variable(torch.FloatTensor(outD_trg2.data.size()).fill_(0)).cuda())
loss_D_trg_fake = loss_D_trg_fake1 + loss_D_trg_fake2
loss_agree = l1_loss(F.softmax(trg_seg_score),
F.softmax(trg_seg_score2))
loss_trg = args.lambda_adv_target * loss_D_trg_fake + loss_seg_trg + loss_agree
loss_trg.backward()
#Weight Discrepancy Loss
W5 = None
W6 = None
if args.model == 'DeepLab2':
for (w5, w6) in zip(model.layer5.parameters(),
model.layer6.parameters()):
if W5 is None and W6 is None:
W5 = w5.view(-1)
W6 = w6.view(-1)
else:
W5 = torch.cat((W5, w5.view(-1)), 0)
W6 = torch.cat((W6, w6.view(-1)), 0)
#ipdb.set_trace()
#loss_weight = (torch.matmul(W5, W6) / (torch.norm(W5) * torch.norm(W6)) + 1) # +1 is for a positive loss
# loss_weight = loss_weight * damping * 2
loss_weight = args.weight_div * (cos_loss(W5, W6) + 1)
loss_weight.backward()
for param in model_D.parameters():
param.requires_grad = True
src_seg_score, trg_seg_score = src_seg_score.detach(
), trg_seg_score.detach()
src_seg_score2, trg_seg_score2 = src_seg_score2.detach(
), trg_seg_score2.detach()
outD_src = model_D(F.softmax(src_seg_score))
loss_D_src_real1 = bce_loss(
outD_src,
Variable(torch.FloatTensor(
outD_src.data.size()).fill_(0)).cuda()) / 2
outD_src2 = model_D(F.softmax(src_seg_score2))
loss_D_src_real2 = bce_loss(
outD_src2,
Variable(torch.FloatTensor(
outD_src2.data.size()).fill_(0)).cuda()) / 2
loss_D_src_real = loss_D_src_real1 + loss_D_src_real2
loss_D_src_real.backward()
outD_trg = model_D(F.softmax(trg_seg_score))
loss_D_trg_real1 = bce_loss(
outD_trg,
Variable(torch.FloatTensor(
outD_trg.data.size()).fill_(1)).cuda()) / 2
outD_trg2 = model_D(F.softmax(trg_seg_score2))
loss_D_trg_real2 = bce_loss(
outD_trg2,
Variable(torch.FloatTensor(
outD_trg2.data.size()).fill_(1)).cuda()) / 2
loss_D_trg_real = loss_D_trg_real1 + loss_D_trg_real2
loss_D_trg_real.backward()
d_loss = loss_D_src_real.data + loss_D_trg_real.data
optimizer.step()
optimizer_D.step()
for m in loss:
train_writer.add_scalar(m, eval(m), i + 1)
if (i + 1) % args.save_pred_every == 0:
print 'taking snapshot ...'
torch.save(
model.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '.pth'))
torch.save(
model_D.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '_D.pth'))
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print '[it %d][src seg loss %.4f][adv loss %.4f][d loss %.4f][agree loss %.4f][div loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data, loss_D_trg_fake.data,d_loss,loss_agree.data,loss_weight.data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff)
if i + 1 > args.num_steps_stop:
print 'finish training'
break
_t['iter time'].tic()
def main():
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time': Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateSrcDataLoader(
args), CreateTrgDataLoader(args)
targetloader_iter, sourceloader_iter = iter(targetloader), iter(
sourceloader)
model, optimizer = CreateModel(args)
model_D1, optimizer_D1 = CreateDiscriminator(args, 1)
model_D2, optimizer_D2 = CreateDiscriminator(args, 2)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
#train_writer = tensorboardX.SummaryWriter(os.path.join(args.snapshot_dir, "logs", model_name))
bce_loss = torch.nn.BCEWithLogitsLoss()
interp_target = nn.Upsample(size=(1024, 1024),
mode='bilinear',
align_corners=True)
interp_source = nn.Upsample(size=(1024, 1024),
mode='bilinear',
align_corners=True)
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D1.train()
model_D1.cuda()
model_D2.train()
model_D2.cuda()
weight_loss = WeightedBCEWithLogitsLoss()
loss = [
'loss_seg_src', 'loss_seg_trg', 'loss_D_trg_fake', 'loss_D_src_real',
'loss_D_trg_real'
]
_t['iter time'].tic()
load_selected_samples = args.load_selected_samples
if load_selected_samples is None:
total_num = args.total_number
else:
clean_ids = [i_id.strip() for i_id in open(load_selected_samples)]
total_num = len(clean_ids)
remember_rate = args.remember_rate
loss_list, name_list, dice_list = [], [], []
print('total_num:', total_num)
predict_sum_disc = 0
predict_sum_cup = 0
noise_sum_disc = 0
noise_sum_cup = 0
threshold = 0.4
for i in range(start_iter, start_iter + total_num):
model.adjust_learning_rate(args, optimizer, i)
model_D1.adjust_learning_rate(args, optimizer_D1, i)
model_D2.adjust_learning_rate(args, optimizer_D2, i)
optimizer.zero_grad()
optimizer_D1.zero_grad()
optimizer_D2.zero_grad()
##train G
for param in model_D1.parameters():
param.requires_grad = False
for param in model_D2.parameters():
param.requires_grad = False
#import pdb;pdb.set_trace()
try:
src_img, src_lbl, weight_map, name = sourceloader_iter.next()
except StopIteration:
sourceloader_iter = iter(sourceloader)
src_img, src_lbl, weight_map, name = sourceloader_iter.next()
src_img, src_lbl, weight_map = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda(), Variable(weight_map.long()).cuda()
src_seg_score1, src_seg_score2, src_seg_score3, src_seg_score4 = model(
src_img, lbl=src_lbl, weight=None)
loss_seg_src = model.loss
loss_seg_src.backward()
loss_list.append(loss_seg_src)
name_list.append(name)
print(i, name)
#import pdb;pdb.set_trace()
output = nn.functional.softmax(src_seg_score2, dim=1)
output = nn.functional.upsample(
output, (2056, 2124), mode='bilinear',
align_corners=True).cpu().data[0].numpy()
output = output.transpose(1, 2, 0) # (1634,1634,3)
output_mask = np.asarray(np.argmax(output, axis=2),
dtype=np.uint8) # (1644,1634) unique:[0,1,2]
predict_disc_dice, predict_cup_dice = calculate_dice(
args.data_dir, output_mask, name)
print('===>predict disc_dice:' + str(round(predict_disc_dice, 3)) +
'\t' + 'cup_dice:' + str(round(predict_cup_dice, 3)))
#import pdb;pdb.set_trace()
label = torch.unsqueeze(src_lbl, 0)
label = nn.functional.upsample(
label.float(),
size=(2056, 2124),
mode='bilinear',
align_corners=True).cpu().data[0].numpy().squeeze()
noise_disc_dice, noise_cup_dice = calculate_dice(
args.data_dir, label, name)
print('===>noise-included disc_dice:' +
str(round(noise_disc_dice, 3)) + '\t' + 'cup_dice:' +
str(round(noise_cup_dice, 3)))
predict_sum_disc += predict_disc_dice
predict_sum_cup += predict_cup_dice
noise_sum_disc += noise_disc_dice
noise_sum_cup += noise_cup_dice
#import pdb;pdb.set_trace()
if load_selected_samples is not None:
if (2 - predict_disc_dice - predict_cup_dice) > threshold:
src_seg_score1, src_seg_score2, src_seg_score3, src_seg_score4 = model(
src_img, lbl=src_lbl, weight=weight_map)
weightloss = 0.05 * model.loss
print('weightloss:', weightloss)
weightloss.backward()
if args.data_label_folder_target is not None:
trg_img, trg_lbl, _, _ = targetloader_iter.next()
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(
trg_lbl.long()).cuda()
trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = model(
trg_img, lbl=trg_lbl)
loss_seg_trg = model.loss
else:
trg_img, _, _ = targetloader_iter.next()
trg_img = Variable(trg_img).cuda()
trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = model(
trg_img)
loss_seg_trg = 0
outD1_trg = model_D1(F.softmax(trg_seg_score1), 0)
outD2_trg = model_D2(F.softmax(trg_seg_score2), 0)
#import pdb;pdb.set_trace()
outD1_trg = interp_target(outD1_trg)
outD2_trg = interp_target(outD2_trg)
if i > 9001:
#import pdb;pdb.set_trace()
weight_map1 = prob_2_entropy(F.softmax(trg_seg_score1))
weight_map2 = prob_2_entropy(F.softmax(trg_seg_score2))
loss_D1_trg_fake = weight_loss(
outD1_trg,
Variable(torch.FloatTensor(
outD1_trg.data.size()).fill_(0)).cuda(), weight_map1, 0.3,
1)
loss_D2_trg_fake = weight_loss(
outD2_trg,
Variable(torch.FloatTensor(
outD2_trg.data.size()).fill_(0)).cuda(), weight_map2, 0.3,
1)
else:
loss_D1_trg_fake = model_D1.loss
loss_D2_trg_fake = model_D2.loss
#loss_D_trg_fake = model_D1.loss*0.2 + model_D2.loss
loss_D_trg_fake = loss_D1_trg_fake * 0.2 + loss_D2_trg_fake
loss_trg = args.lambda_adv_target * loss_D_trg_fake + loss_seg_trg
loss_trg.backward()
###train D
for param in model_D1.parameters():
param.requires_grad = True
for param in model_D2.parameters():
param.requires_grad = True
src_seg_score1, src_seg_score2, src_seg_score3, src_seg_score4, trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = src_seg_score1.detach(
), src_seg_score2.detach(), src_seg_score3.detach(
), src_seg_score4.detach(), trg_seg_score1.detach(
), trg_seg_score2.detach(), trg_seg_score3.detach(
), trg_seg_score4.detach()
outD1_src = model_D1(F.softmax(src_seg_score1), 0)
outD2_src = model_D2(F.softmax(src_seg_score2), 0)
loss_D1_src_real = model_D1.loss / 2
loss_D1_src_real.backward()
loss_D2_src_real = model_D2.loss / 2
loss_D2_src_real.backward()
loss_D_src_real = loss_D1_src_real + loss_D2_src_real
outD1_trg = model_D1(F.softmax(trg_seg_score1), 1)
outD2_trg = model_D2(F.softmax(trg_seg_score2), 1)
outD1_trg = interp_target(outD1_trg)
outD2_trg = interp_target(outD2_trg)
if i > 9001:
weight_map1 = prob_2_entropy(F.softmax(trg_seg_score1))
weight_map2 = prob_2_entropy(F.softmax(trg_seg_score2))
loss_D1_trg_real = weight_loss(
outD1_trg,
Variable(torch.FloatTensor(
outD1_trg.data.size()).fill_(1)).cuda(), weight_map1, 0.3,
1) / 2
loss_D2_trg_real = weight_loss(
outD2_trg,
Variable(torch.FloatTensor(
outD2_trg.data.size()).fill_(1)).cuda(), weight_map2, 0.3,
1) / 2
else:
loss_D1_trg_real = model_D1.loss / 2
loss_D2_trg_real = model_D2.loss / 2
loss_D1_trg_real.backward()
loss_D2_trg_real.backward()
loss_D_trg_real = loss_D1_trg_real + loss_D2_trg_real
optimizer.step()
optimizer_D1.step()
optimizer_D2.step()
# for m in loss:
# train_writer.add_scalar(m, eval(m), i+1)
if (i + 1 == start_iter +
total_num) and load_selected_samples is not None:
print('taking snapshot ', args.snapshot_dir,
args.source + '_' + str(total_num))
torch.save(
model.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(total_num) + '.pth'))
torch.save(
model_D1.state_dict(),
os.path.join(
args.snapshot_dir,
'%s_' % (args.source) + str(total_num) + '_D1.pth'))
torch.save(
model_D2.state_dict(),
os.path.join(
args.snapshot_dir,
'%s_' % (args.source) + str(total_num) + '_D2.pth'))
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print ('[it %d][src seg loss %.4f][trg loss %.4f][trg seg loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data,loss_trg.data, loss_seg_trg.data,optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff))
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()
if i + 1 == start_iter + total_num and load_selected_samples is None:
ind_sorted = np.argsort(loss_list)
loss_sorted = np.array(loss_list)[ind_sorted]
num_remember = int(remember_rate * len(loss_sorted))
clean_ind_update = ind_sorted[:num_remember]
clean_name_update = np.array(name_list)[clean_ind_update]
#import pdb;pdb.set_trace()
#dice = np.array(dice_list)[clean_ind_update]
noise_ind_sorted = np.argsort(-np.array(loss_list))
noise_loss_sorted = np.array(loss_list)[noise_ind_sorted]
noise_num_remember = int(remember_rate * len(noise_loss_sorted))
noise_ind_update = noise_ind_sorted[:noise_num_remember]
noise_name_update = np.array(name_list)[noise_ind_update]
with open(os.path.join(args.save_selected_samples), "w") as f:
for i in range(len(clean_name_update)):
#f.write(str(clean_name_update[i][0]) +'\t'+ str(dice[:,0][i]) + '\t'+ str(dice[:,1][i]) +'\n')
f.write(str(clean_name_update[i][0]) + '\n')
with open(os.path.join(args.noise_selected_samples), "w") as g:
for j in range(len(noise_name_update)):
g.write(str(noise_name_update[j][0]) + '\n')
print(args.save_selected_samples, 'Sample selection finished!')
break
print('\n predict disc_coef = {0:.4f}, cup_coef = {1:.4f}'.format(
predict_sum_disc / total_num, predict_sum_cup / total_num))
print('\n noise-included disc_coef = {0:.4f}, cup_coef = {1:.4f}'.format(
noise_sum_disc / total_num, noise_sum_cup / total_num))
def main():
opt = TrainOptions() # loading train options(arg parser)
args = opt.initialize() # get arguments
os.environ["CUDA_VISIBLE_DEVICES"] = args.GPU
_t = {'iter time': Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args) # print set options
sourceloader, targetloader = CreateSrcDataLoader(
args), CreateTrgDataLoader(args)
sourceloader_iter, targetloader_iter = iter(sourceloader), iter(
targetloader)
model, optimizer = CreateModel(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
# losses to log
loss = ['loss_seg_src', 'loss_seg_trg']
loss_train = 0.0
loss_val = 0.0
loss_train_list = []
loss_val_list = []
mean_img = torch.zeros(1, 1)
class_weights = Variable(CS_weights).cuda()
_t['iter time'].tic()
for i in range(start_iter, args.num_steps):
model.adjust_learning_rate(args, optimizer, i) # adjust learning rate
optimizer.zero_grad() # zero grad
src_img, src_lbl, _, _ = sourceloader_iter.next() # new batch source
trg_img, trg_lbl, _, _ = targetloader_iter.next() # new batch target
scr_img_copy = src_img.clone()
if mean_img.shape[-1] < 2:
B, C, H, W = src_img.shape
mean_img = IMG_MEAN.repeat(B, 1, H, W)
#-------------------------------------------------------------------#
# 1. source to target, target to target
src_in_trg = FDA_source_to_target(src_img, trg_img,
L=args.LB) # src_lbl
trg_in_trg = trg_img
# 2. subtract mean
src_img = src_in_trg.clone() - mean_img # src, src_lbl
trg_img = trg_in_trg.clone() - mean_img # trg, trg_lbl
#-------------------------------------------------------------------#
# evaluate and update params #####
src_img, src_lbl = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda() # to gpu
src_seg_score = model(src_img,
lbl=src_lbl,
weight=class_weights,
ita=args.ita) # forward pass
loss_seg_src = model.loss_seg # get loss
loss_ent_src = model.loss_ent
# get target loss, only entropy for backpro
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(
trg_lbl.long()).cuda() # to gpu
trg_seg_score = model(trg_img,
lbl=trg_lbl,
weight=class_weights,
ita=args.ita) # forward pass
loss_seg_trg = model.loss_seg # get loss
loss_ent_trg = model.loss_ent
triger_ent = 0.0
if i > args.switch2entropy:
triger_ent = 1.0
loss_all = loss_seg_src + triger_ent * args.entW * loss_ent_trg # loss of seg on src, and ent on s and t
loss_all.backward()
optimizer.step()
loss_train += loss_seg_src.detach().cpu().numpy()
loss_val += loss_seg_trg.detach().cpu().numpy()
if (i + 1) % args.save_pred_every == 0:
print('taking snapshot ...')
torch.save(
model.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '.pth'))
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print('[it %d][src seg loss %.4f][trg seg loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data, loss_seg_trg.data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff) )
sio.savemat(args.tempdata, {
'src_img': src_img.cpu().numpy(),
'trg_img': trg_img.cpu().numpy()
})
loss_train /= args.print_freq
loss_val /= args.print_freq
loss_train_list.append(loss_train)
loss_val_list.append(loss_val)
sio.savemat(args.matname, {
'loss_train': loss_train_list,
'loss_val': loss_val_list
})
loss_train = 0.0
loss_val = 0.0
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()
def main():
opt = TestOptions()
args = opt.initialize()
os.environ["CUDA_VISIBLE_DEVICES"] = args.GPU
if not os.path.exists(args.save):
os.makedirs(args.save)
# 3 models are used because MBT method is used.
args.restore_from = args.restore_opt1
model1 = CreateModel(args)
model1.eval()
model1.cuda()
args.restore_from = args.restore_opt2
model2 = CreateModel(args)
model2.eval()
model2.cuda()
args.restore_from = args.restore_opt3
model3 = CreateModel(args)
model3.eval()
model3.cuda()
targetloader = CreateTrgDataLoader(args)
# change the mean for different dataset other than CS
IMG_MEAN = np.array((104.00698793, 116.66876762, 122.67891434),
dtype=np.float32)
IMG_MEAN = torch.reshape(torch.from_numpy(IMG_MEAN), (1, 3, 1, 1))
mean_img = torch.zeros(1, 1)
# ------------------------------------------------- #
# compute scores and save them
with torch.no_grad():
for index, batch in enumerate(targetloader):
if index % 100 == 0:
print('%d processd' % index)
image, _, name = batch # 1. get image
# create mean image
if mean_img.shape[-1] < 2:
B, C, H, W = image.shape
# 2. get mean image
mean_img = IMG_MEAN.repeat(B, 1, H, W)
image = image.clone() - mean_img # 3, image - mean_img
image = Variable(image).cuda()
# forward
output1 = model1(image)
output1 = nn.functional.softmax(output1, dim=1)
output2 = model2(image)
output2 = nn.functional.softmax(output2, dim=1)
output3 = model3(image)
output3 = nn.functional.softmax(output3, dim=1)
a, b = 0.3333, 0.3333
output = a * output1 + b * output2 + (1.0 - a - b) * output3
output = nn.functional.interpolate(
output, (1024, 2048), mode='bilinear',
align_corners=True).cpu().data[0].numpy()
#output = nn.functional.upsample( output, (1024, 2048), mode='bilinear', align_corners=True).cpu().data[0].numpy()
output = output.transpose(1, 2, 0)
output_nomask = np.asarray(np.argmax(output, axis=2),
dtype=np.uint8)
output_col = colorize_mask(output_nomask)
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('/')[-1]
output_nomask.save('%s/%s' % (args.save, name))
output_col.save('%s/%s_color.png' %
(args.save, name.split('.')[0]))
# scores computed and saved
# ------------------------------------------------- #
compute_mIoU(args.gt_dir, args.save, args.devkit_dir, args.restore_from)
def main():
opt = TrainOptions()
args = opt.initialize()
os.environ["CUDA_VISIBLE_DEVICES"] = args.GPU
_t = {'iter time': Timer()}
opt.print_options(args)
train_data = cityscapesLoader(args.data_dir,
split='train',
is_transform=True)
train_loader = data.DataLoader(train_data, batch_size=args.batch_size)
val_data = cityscapesLoader(args.data_dir, split='val', is_transform=True)
val_loader = data.DataLoader(val_data, batch_size=1)
model, optim = CreateModel(args)
criterion = nn.CrossEntropyLoss(ignore_index=255)
wandb.login(key=args.wandb_key)
start_iter = 0
valid_loss_min = np.Inf
if args.restore is True:
model, optim, start_iter, valid_loss_min = load_ckp(
args.checkpoint_path, model, optim)
wandb.init(project="DL-SegSem", resume='allow', id=args.wandb_id)
else:
wandb.init(project="DL-SegSem")
wandb.config.update(args)
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
_t['iter time'].tic()
for epoch in range(start_iter + 1, args.epochs):
epoch_loss = 0.0
for step, batch_data in enumerate(train_loader):
# Get the inputs and labels
inputs = batch_data[0].to('cuda')
labels = batch_data[1].to('cuda').long()
# Forward propagation
outputs = model(inputs)
# Loss computation
loss = criterion(outputs, labels)
print("Epoch:", epoch, "| Step:", step, "| Loss:", loss.item())
# Backpropagation
optim.zero_grad()
loss.backward()
optim.step()
# Keep track of loss for current epoch
epoch_loss += loss.item()
val_data = evaulate(model, val_loader)
val_loss = val_data['Loss']
if epoch % args.print_freq == 0:
_t['iter time'].toc(average=False)
print("Epoch number:", epoch, "| Training Loss=",
epoch_loss / len(train_loader), "| Valiadtion Loss= ",
val_loss, "| Mean IOU (val)=", val_data['Mean IOU'], "(",
_t['iter time'].diff, "seconds )")
_t['iter time'].tic()
checkpoint = {
'epoch': epoch,
'valid_loss_min': valid_loss_min,
'state_dict': model.state_dict(),
'optimizer': optim.state_dict(),
}
save_ckp(checkpoint, False, args.checkpoint_path, args.best_model_path)
wandb.log({
"Training Loss": epoch_loss / len(train_loader),
"Validation Loss": val_loss,
"Mean IoU": val_data['Mean IOU'],
"Predictions": val_data['Predictions']
})
if val_loss <= valid_loss_min:
print(
'Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...'
.format(valid_loss_min, val_loss))
# save checkpoint as best model
save_ckp(checkpoint, True, args.checkpoint_path,
args.best_model_path)
valid_loss_min = val_loss
def main():
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time': Timer()}
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateActSrcDataLoader(
args), CreateActTrgDataLoader(args, 'train')
testloader = CreateActTrgDataLoader(args, 'test')
targetloader_iter, sourceloader_iter = iter(targetloader), iter(
sourceloader)
model, optimizer = CreateModel(args)
model_D, optimizer_D = CreateDiscriminator(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
train_writer = tensorboardX.SummaryWriter(
os.path.join(args.snapshot_dir, "logs"))
bce_loss = torch.nn.BCEWithLogitsLoss()
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D.train()
model_D.cuda()
loss = [
'loss_src', 'loss_trg', 'loss_D_trg_fake', 'loss_D_src_real',
'loss_D_trg_real', 'eval_loss'
]
_t['iter time'].tic()
best_loss_eval = None
best_step = 0
eval_loss = np.array([0])
for i in range(start_iter, args.num_steps):
model.module.adjust_learning_rate(args, optimizer, i)
model_D.module.adjust_learning_rate(args, optimizer_D, i)
optimizer.zero_grad()
optimizer_D.zero_grad()
for param in model_D.parameters():
param.requires_grad = False
try:
src_img, src_lbl, _, _ = next(sourceloader_iter)
except StopIteration:
sourceloader_iter = iter(sourceloader)
src_img, src_lbl, _, _ = next(sourceloader_iter)
src_img, src_lbl = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda()
src_score, loss_src = model(src_img, lbl=src_lbl)
loss_src.mean().backward()
try:
trg_img, trg_lbl, _, _ = next(targetloader_iter)
except StopIteration:
targetloader_iter = iter(targetloader)
trg_img, trg_lbl, _, _ = next(targetloader_iter)
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(
trg_lbl.long()).cuda()
trg_score, loss_trg = model(trg_img, lbl=trg_lbl)
outD_trg, loss_D_trg_fake = model_D(F.softmax(trg_score, dim=1),
0) # do not apply softmax
loss_trg = args.lambda_adv_target * loss_D_trg_fake + loss_trg
loss_trg.mean().backward()
for param in model_D.parameters():
param.requires_grad = True
src_score, trg_score = src_score.detach(), trg_score.detach()
outD_src, model_D_loss = model_D(F.softmax(src_score, dim=1),
0) # do not apply softmax
loss_D_src_real = model_D_loss / 2
loss_D_src_real.mean().backward()
outD_trg, model_D_loss = model_D(F.softmax(trg_score, dim=1),
1) # do not apply softmax
loss_D_trg_real = model_D_loss / 2
loss_D_trg_real.mean().backward()
optimizer.step()
optimizer_D.step()
for m in loss:
train_writer.add_scalar(m, eval(m).mean(), i + 1)
if (i + 1) % args.save_pred_every == 0:
with torch.no_grad():
model.eval()
eval_loss = 0
for test_img, test_lbl, _, _ in testloader:
test_score, loss_test = model(test_img, lbl=test_lbl)
eval_loss += loss_test.mean().item() * test_img.size(0)
eval_loss /= len(testloader.dataset)
if best_loss_eval == None or eval_loss < best_loss_eval:
best_loss_eval = eval_loss
best_step = i + 1
print('taking snapshot ... eval_loss: {}'.format(eval_loss))
torch.save(
model.module.state_dict(),
os.path.join(args.snapshot_dir,
str(i + 1) + '.pth'))
eval_loss = np.array([eval_loss])
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print('[it %d][src loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_src.mean().data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff))
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()
def main():
opt = TestOptions()
args = opt.initialize()
if not os.path.exists(args.save):
os.makedirs(args.save)
model = CreateModel(args)
model.eval()
model.cuda()
targetloader = CreateTrgDataLoader(args)
id_to_trainid = {2: 0, 1: 128, 0: 255}
for index, batch in enumerate(targetloader):
if index % 10 == 0:
print('%d processd' % index)
image, _, name = batch
_, output, _, _ = model(Variable(image).cuda()) #[1,3,129,129]
#import pdb;pdb.set_trace()
output = nn.functional.softmax(output, dim=1)
output = nn.functional.upsample(
output, (1634, 1634), mode='bilinear',
align_corners=True).cpu().data[0].numpy()
output = output.transpose(1, 2, 0) #(1634,1634,3)
'''
output_crop = output[14:526, 626:1138, 0:2]
np.save("/extracephonline/medai_data2/zhengdzhang/eyes/qikan/cai/output_crop_1.npy", output_crop)
#crop_img = Image.fromarray(output_crop)
#crop_img.save("/extracephonline/medai_data2/zhengdzhang/eyes/qikan/cai/crop_img.png")
'''
output_nomask = np.asarray(np.argmax(output, axis=2),
dtype=np.uint8) #(1644,1634) unique:[0,1,2]
cup_mask = get_bool(output_nomask, 0)
disc_mask = get_bool(output_nomask, 0) + get_bool(output_nomask, 1)
disc_mask = disc_mask.astype(np.uint8)
cup_mask = cup_mask.astype(np.uint8)
for i in range(5):
disc_mask = scipy.signal.medfilt2d(disc_mask, 19)
cup_mask = scipy.signal.medfilt2d(cup_mask, 19)
disc_mask = morphology.binary_erosion(disc_mask,
morphology.diamond(7)).astype(
np.uint8) # return 0,1
cup_mask = morphology.binary_erosion(cup_mask,
morphology.diamond(7)).astype(
np.uint8) # return 0,1
disc_mask = get_largest_fillhole(disc_mask)
cup_mask = get_largest_fillhole(cup_mask)
disc_mask = morphology.binary_dilation(disc_mask,
morphology.diamond(7)).astype(
np.uint8) # return 0,1
cup_mask = morphology.binary_dilation(cup_mask,
morphology.diamond(7)).astype(
np.uint8) # return 0,1
disc_mask = get_largest_fillhole(disc_mask).astype(
np.uint8) # return 0,1
cup_mask = get_largest_fillhole(cup_mask).astype(np.uint8)
output_nomask = disc_mask + cup_mask
output_col = np.ones(output_nomask.shape, dtype=np.float32)
for k, v in id_to_trainid.items():
output_col[output_nomask == k] = v
output_col = Image.fromarray(output_col.astype(np.uint8))
output_nomask = Image.fromarray(output_nomask)
name = name[0].split('.')[0] + '.png'
output_nomask.save('%s/%s' % (args.save, name))
output_col.save('%s/color_%s' % (args.save, name))
disc_dice, cup_dice = calculate_dice(args.gt_dir, args.save,
args.devkit_dir)
print('===> disc_dice:' + str(round(disc_dice, 3)) + '\t' + 'cup_dice:' +
str(round(cup_dice, 3)))
def main():
opt = TrainOptions()
args = opt.initialize()
_t = {'iter time': Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateSrcDataLoader(
args), CreateTrgDataLoader(args)
targetloader_iter, sourceloader_iter = iter(targetloader), iter(
sourceloader)
model, optimizer = CreateModel(args)
model_D1, optimizer_D1 = CreateDiscriminator(args, 1)
model_D2, optimizer_D2 = CreateDiscriminator(args, 2)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
train_writer = tensorboardX.SummaryWriter(
os.path.join(args.snapshot_dir, "logs", model_name))
bce_loss = torch.nn.BCEWithLogitsLoss()
interp_target = nn.Upsample(size=(1024, 1024),
mode='bilinear',
align_corners=True)
interp_source = nn.Upsample(size=(1024, 1024),
mode='bilinear',
align_corners=True)
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
model_D1.train()
model_D1.cuda()
model_D2.train()
model_D2.cuda()
weight_loss = WeightedBCEWithLogitsLoss()
weight_map_loss = WeightMapLoss()
loss = [
'loss_seg_src', 'loss_seg_trg', 'loss_D_trg_fake', 'loss_D_src_real',
'loss_D_trg_real'
]
_t['iter time'].tic()
for i in range(start_iter, args.num_steps):
print(i)
model.adjust_learning_rate(args, optimizer, i)
model_D1.adjust_learning_rate(args, optimizer_D1, i)
model_D2.adjust_learning_rate(args, optimizer_D2, i)
optimizer.zero_grad()
optimizer_D1.zero_grad()
optimizer_D2.zero_grad()
##train G
for param in model_D1.parameters():
param.requires_grad = False
for param in model_D2.parameters():
param.requires_grad = False
try:
src_img, src_lbl, weight_map, _ = sourceloader_iter.next()
except StopIteration:
sourceloader_iter = iter(sourceloader)
src_img, src_lbl, weight_map, _ = sourceloader_iter.next()
src_img, src_lbl, weight_map = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda(), Variable(weight_map.long()).cuda()
src_seg_score1, src_seg_score2, src_seg_score3, src_seg_score4 = model(
src_img, lbl=src_lbl, weight=weight_map)
#import pdb;pdb.set_trace()
#WeightLoss1 = weight_map_loss(src_seg_score1, src_lbl, weight_map)
#WeightLoss2 = weight_map_loss(src_seg_score2, src_lbl, weight_map)
loss_seg_src = model.loss
#print('WeightLoss2, WeightLoss1:', WeightLoss2.data, WeightLoss1.data)
loss_seg_src.backward()
if args.data_label_folder_target is not None:
trg_img, trg_lbl, _, name = targetloader_iter.next()
trg_img, trg_lbl = Variable(trg_img).cuda(), Variable(
trg_lbl.long()).cuda()
trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = model(
trg_img, lbl=trg_lbl)
loss_seg_trg = model.loss
else:
trg_img, _, name = targetloader_iter.next()
trg_img = Variable(trg_img).cuda()
trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = model(
trg_img)
loss_seg_trg = 0
outD1_trg = model_D1(F.softmax(trg_seg_score1), 0)
outD2_trg = model_D2(F.softmax(trg_seg_score2), 0)
#import pdb;pdb.set_trace()
outD1_trg = interp_target(outD1_trg) #[1, 1, 1024, 1024]
outD2_trg = interp_target(outD2_trg)
'''
if i > 9001:
#import pdb;pdb.set_trace()
weight_map1 = prob_2_entropy(F.softmax(trg_seg_score1)) #[1, 1, 1024, 1024]
weight_map2 = prob_2_entropy(F.softmax(trg_seg_score2)) #[1, 1, 1024, 1024]
loss_D1_trg_fake = weight_loss(outD1_trg, Variable(torch.FloatTensor(outD1_trg.data.size()).fill_(0)).cuda(), weight_map1, 0.3, 1)
loss_D2_trg_fake = weight_loss(outD2_trg, Variable(torch.FloatTensor(outD2_trg.data.size()).fill_(0)).cuda(), weight_map2, 0.3, 1)
else:
loss_D1_trg_fake = model_D1.loss
loss_D2_trg_fake = model_D2.loss
loss_D_trg_fake = loss_D1_trg_fake*0.2 + loss_D2_trg_fake
'''
loss_D_trg_fake = model_D1.loss * 0.2 + model_D2.loss
loss_trg = args.lambda_adv_target * loss_D_trg_fake + loss_seg_trg
loss_trg.backward()
###train D
for param in model_D1.parameters():
param.requires_grad = True
for param in model_D2.parameters():
param.requires_grad = True
src_seg_score1, src_seg_score2, src_seg_score3, src_seg_score4, trg_seg_score1, trg_seg_score2, trg_seg_score3, trg_seg_score4 = src_seg_score1.detach(
), src_seg_score2.detach(), src_seg_score3.detach(
), src_seg_score4.detach(), trg_seg_score1.detach(
), trg_seg_score2.detach(), trg_seg_score3.detach(
), trg_seg_score4.detach()
outD1_src = model_D1(F.softmax(src_seg_score1), 0)
outD2_src = model_D2(F.softmax(src_seg_score2), 0)
loss_D1_src_real = model_D1.loss / 2
loss_D1_src_real.backward()
loss_D2_src_real = model_D2.loss / 2
loss_D2_src_real.backward()
loss_D_src_real = loss_D1_src_real + loss_D2_src_real
outD1_trg = model_D1(F.softmax(trg_seg_score1), 1)
outD2_trg = model_D2(F.softmax(trg_seg_score2), 1)
outD1_trg = interp_target(outD1_trg)
outD2_trg = interp_target(outD2_trg)
if i > 9001:
weight_map1 = prob_2_entropy(F.softmax(trg_seg_score1))
weight_map2 = prob_2_entropy(F.softmax(trg_seg_score2))
loss_D1_trg_real = weight_loss(
outD1_trg,
Variable(torch.FloatTensor(
outD1_trg.data.size()).fill_(1)).cuda(), weight_map1, 0.3,
1) / 2
loss_D2_trg_real = weight_loss(
outD2_trg,
Variable(torch.FloatTensor(
outD2_trg.data.size()).fill_(1)).cuda(), weight_map2, 0.3,
1) / 2
else:
loss_D1_trg_real = model_D1.loss / 2
loss_D2_trg_real = model_D2.loss / 2
loss_D1_trg_real.backward()
loss_D2_trg_real.backward()
loss_D_trg_real = loss_D1_trg_real + loss_D2_trg_real
optimizer.step()
optimizer_D1.step()
optimizer_D2.step()
for m in loss:
train_writer.add_scalar(m, eval(m), i + 1)
if (i + 1) % args.save_pred_every == 0:
print('taking snapshot ...')
torch.save(
model.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '.pth'))
torch.save(
model_D1.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '_D1.pth'))
torch.save(
model_D2.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '_D2.pth'))
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print ('[it %d][src seg loss %.4f][trg seg loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data,loss_seg_trg.data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff))
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()
def main():
opt = TrainOptions()
args = opt.initialize()
os.environ["CUDA_VISIBLE_DEVICES"] = args.GPU
_t = {'iter time': Timer()}
model_name = args.source + '_to_' + args.target
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
os.makedirs(os.path.join(args.snapshot_dir, 'logs'))
opt.print_options(args)
sourceloader, targetloader = CreateSrcDataLoader(
args), CreateTrgDataLoader(args)
sourceloader_iter, targetloader_iter = iter(sourceloader), iter(
targetloader)
pseudotrgloader = CreatePseudoTrgLoader(args)
pseudoloader_iter = iter(pseudotrgloader)
model, optimizer = CreateModel(args)
start_iter = 0
if args.restore_from is not None:
start_iter = int(args.restore_from.rsplit('/', 1)[1].rsplit('_')[1])
if args.restore_optim_from is not None:
optimizer.load_state_dict(torch.load(args.restore_optim_from))
for state in optimizer.state.values():
for k, v in state.items():
if isinstance(v, torch.Tensor):
state[k] = v.cuda()
cudnn.enabled = True
cudnn.benchmark = True
model.train()
model.cuda()
wandb.watch(model, log='gradient', log_freq=1)
# losses to log
loss = ['loss_seg_src', 'loss_seg_psu']
loss_train = 0.0
loss_val = 0.0
loss_pseudo = 0.0
loss_train_list = []
loss_val_list = []
loss_pseudo_list = []
mean_img = torch.zeros(1, 1)
class_weights = Variable(CS_weights).cuda()
_t['iter time'].tic()
for i in range(start_iter, args.num_steps):
model.adjust_learning_rate(args, optimizer, i) # adjust learning rate
optimizer.zero_grad() # zero grad
src_img, src_lbl, _, _ = sourceloader_iter.next() # new batch source
trg_img, trg_lbl, _, _ = targetloader_iter.next() # new batch target
psu_img, psu_lbl, _, _ = pseudoloader_iter.next()
scr_img_copy = src_img.clone()
if mean_img.shape[-1] < 2:
B, C, H, W = src_img.shape
mean_img = IMG_MEAN.repeat(B, 1, H, W)
#-------------------------------------------------------------------#
# 1. source to target, target to target
src_in_trg = FDA_source_to_target(src_img, trg_img,
L=args.LB) # src_lbl
trg_in_trg = trg_img
# 2. subtract mean
src_img = src_in_trg.clone() - mean_img # src_1, trg_1, src_lbl
trg_img = trg_in_trg.clone() - mean_img # trg_1, trg_0, trg_lbl
psu_img = psu_img.clone() - mean_img
#-------------------------------------------------------------------#
# evaluate and update params #####
src_img, src_lbl = Variable(src_img).cuda(), Variable(
src_lbl.long()).cuda() # to gpu
src_seg_score = model(src_img,
lbl=src_lbl,
weight=class_weights,
ita=args.ita) # forward pass
loss_seg_src = model.loss_seg # get loss
loss_ent_src = model.loss_ent
# use pseudo label as supervision
psu_img, psu_lbl = Variable(psu_img).cuda(), Variable(
psu_lbl.long()).cuda()
psu_seg_score = model(psu_img,
lbl=psu_lbl,
weight=class_weights,
ita=args.ita)
loss_seg_psu = model.loss_seg
loss_ent_psu = model.loss_ent
loss_all = loss_seg_src + (loss_seg_psu + args.entW * loss_ent_psu
) # loss of seg on src, and ent on s and t
loss_all.backward()
optimizer.step()
loss_train += loss_seg_src.detach().cpu().numpy()
loss_val += loss_seg_psu.detach().cpu().numpy()
if (i + 1) % args.save_pred_every == 0:
print('taking snapshot ...')
torch.save(
model.state_dict(),
os.path.join(args.snapshot_dir,
'%s_' % (args.source) + str(i + 1) + '.pth'))
torch.save(
optimizer.state_dict(),
os.path.join(args.snapshot_dir_optim,
'%s_' % (args.source) + '.pth'))
wandb.log({
"src seg loss": loss_seg_src.data,
"psu seg loss": loss_seg_psu.data,
"learnign rate": optimizer.param_groups[0]['lr'] * 10000
})
if (i + 1) % args.print_freq == 0:
_t['iter time'].toc(average=False)
print('[it %d][src seg loss %.4f][psu seg loss %.4f][lr %.4f][%.2fs]' % \
(i + 1, loss_seg_src.data, loss_seg_psu.data, optimizer.param_groups[0]['lr']*10000, _t['iter time'].diff) )
sio.savemat(args.tempdata, {
'src_img': src_img.cpu().numpy(),
'trg_img': trg_img.cpu().numpy()
})
loss_train /= args.print_freq
loss_val /= args.print_freq
loss_train_list.append(loss_train)
loss_val_list.append(loss_val)
sio.savemat(args.matname, {
'loss_train': loss_train_list,
'loss_val': loss_val_list
})
loss_train = 0.0
loss_val = 0.0
if i + 1 > args.num_steps_stop:
print('finish training')
break
_t['iter time'].tic()