def main():
"""Create the model and start the training."""
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
h, w = map(int, args.input_size_target.split(','))
input_size_target = (h, w)
cudnn.enabled = True
from pytorchgo.utils.pytorch_utils import set_gpu
set_gpu(args.gpu)
# Create network
if args.model == 'DeepLab':
logger.info("adopting Deeplabv2 base model..")
model = Res_Deeplab(num_classes=args.num_classes, multi_scale=False)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
new_params = model.state_dict().copy()
for i in saved_state_dict:
# Scale.layer5.conv2d_list.3.weight
i_parts = i.split('.')
# print i_parts
if not args.num_classes == 19 or not i_parts[1] == 'layer5':
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
# print i_parts
model.load_state_dict(new_params)
optimizer = optim.SGD(model.optim_parameters(args),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
elif args.model == "FCN8S":
logger.info("adopting FCN8S base model..")
from pytorchgo.model.MyFCN8s import MyFCN8s
model = MyFCN8s(n_class=NUM_CLASSES)
vgg16 = torchfcn.models.VGG16(pretrained=True)
model.copy_params_from_vgg16(vgg16)
optimizer = optim.SGD(model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
else:
raise ValueError
model.train()
model.cuda()
cudnn.benchmark = True
# init D
model_D1 = FCDiscriminator(num_classes=args.num_classes)
model_D2 = FCDiscriminator(num_classes=args.num_classes)
model_D1.train()
model_D1.cuda()
model_D2.train()
model_D2.cuda()
if SOURCE_DATA == "GTA5":
trainloader = data.DataLoader(GTA5DataSet(
args.data_dir,
args.data_list,
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
trainloader_iter = enumerate(trainloader)
elif SOURCE_DATA == "SYNTHIA":
trainloader = data.DataLoader(SynthiaDataSet(
args.data_dir,
args.data_list,
LABEL_LIST_PATH,
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
trainloader_iter = enumerate(trainloader)
else:
raise ValueError
targetloader = data.DataLoader(cityscapesDataSet(
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size_target,
scale=False,
mirror=args.random_mirror,
mean=IMG_MEAN,
set=args.set),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
targetloader_iter = enumerate(targetloader)
# implement model.optim_parameters(args) to handle different models' lr setting
optimizer.zero_grad()
optimizer_D1 = optim.Adam(model_D1.parameters(),
lr=args.learning_rate_D,
betas=(0.9, 0.99))
optimizer_D1.zero_grad()
optimizer_D2 = optim.Adam(model_D2.parameters(),
lr=args.learning_rate_D,
betas=(0.9, 0.99))
optimizer_D2.zero_grad()
bce_loss = torch.nn.BCEWithLogitsLoss()
interp = nn.Upsample(size=(input_size[1], input_size[0]), mode='bilinear')
interp_target = nn.Upsample(size=(input_size_target[1],
input_size_target[0]),
mode='bilinear')
# labels for adversarial training
source_label = 0
target_label = 1
best_mIoU = 0
model_summary([model, model_D1, model_D2])
optimizer_summary([optimizer, optimizer_D1, optimizer_D2])
for i_iter in tqdm(range(args.num_steps_stop),
total=args.num_steps_stop,
desc="training"):
loss_seg_value1 = 0
loss_adv_target_value1 = 0
loss_D_value1 = 0
loss_seg_value2 = 0
loss_adv_target_value2 = 0
loss_D_value2 = 0
optimizer.zero_grad()
lr = adjust_learning_rate(optimizer, i_iter)
optimizer_D1.zero_grad()
optimizer_D2.zero_grad()
lr_D1 = adjust_learning_rate_D(optimizer_D1, i_iter)
lr_D2 = adjust_learning_rate_D(optimizer_D2, i_iter)
for sub_i in range(args.iter_size):
######################### train G
# don't accumulate grads in D
for param in model_D1.parameters():
param.requires_grad = False
for param in model_D2.parameters():
param.requires_grad = False
# train with source
_, batch = trainloader_iter.next()
images, labels, _, _ = batch
images = Variable(images).cuda()
pred2 = model(images)
pred2 = interp(pred2)
loss_seg2 = loss_calc(pred2, labels)
loss = loss_seg2
# proper normalization
loss = loss / args.iter_size
loss.backward()
loss_seg_value2 += loss_seg2.data.cpu().numpy()[0] / args.iter_size
# train with target
_, batch = targetloader_iter.next()
images, _, _, _ = batch
images = Variable(images).cuda()
pred_target2 = model(images)
pred_target2 = interp_target(pred_target2)
D_out2 = model_D2(F.softmax(pred_target2))
loss_adv_target2 = bce_loss(
D_out2,
Variable(
torch.FloatTensor(
D_out2.data.size()).fill_(source_label)).cuda())
loss = args.lambda_adv_target2 * loss_adv_target2
loss = loss / args.iter_size
loss.backward()
loss_adv_target_value2 += loss_adv_target2.data.cpu().numpy(
)[0] / args.iter_size
################################## train D
# bring back requires_grad
for param in model_D1.parameters():
param.requires_grad = True
for param in model_D2.parameters():
param.requires_grad = True
# train with source
pred2 = pred2.detach()
D_out2 = model_D2(F.softmax(pred2))
loss_D2 = bce_loss(
D_out2,
Variable(
torch.FloatTensor(
D_out2.data.size()).fill_(source_label)).cuda())
loss_D2 = loss_D2 / args.iter_size / 2
loss_D2.backward()
loss_D_value2 += loss_D2.data.cpu().numpy()[0]
# train with target
pred_target2 = pred_target2.detach()
D_out2 = model_D2(F.softmax(pred_target2))
loss_D2 = bce_loss(
D_out2,
Variable(
torch.FloatTensor(
D_out2.data.size()).fill_(target_label)).cuda())
loss_D2 = loss_D2 / args.iter_size / 2
loss_D2.backward()
loss_D_value2 += loss_D2.data.cpu().numpy()[0]
optimizer.step()
optimizer_D1.step()
optimizer_D2.step()
if i_iter % 100 == 0:
logger.info(
'iter = {}/{},loss_seg1 = {:.3f} loss_seg2 = {:.3f} loss_adv1 = {:.3f}, loss_adv2 = {:.3f} loss_D1 = {:.3f} loss_D2 = {:.3f}, lr={:.7f}, lr_D={:.7f}, best miou16= {:.5f}'
.format(i_iter, args.num_steps_stop, loss_seg_value1,
loss_seg_value2, loss_adv_target_value1,
loss_adv_target_value2, loss_D_value1, loss_D_value2,
lr, lr_D1, best_mIoU))
if i_iter % args.save_pred_every == 0 and i_iter != 0:
logger.info("saving snapshot.....")
cur_miou16 = proceed_test(model, input_size)
is_best = True if best_mIoU < cur_miou16 else False
if is_best:
best_mIoU = cur_miou16
torch.save(
{
'iteration': i_iter,
'optim_state_dict': optimizer.state_dict(),
'optim_D1_state_dict': optimizer_D1.state_dict(),
'optim_D2_state_dict': optimizer_D2.state_dict(),
'model_state_dict': model.state_dict(),
'model_D1_state_dict': model_D1.state_dict(),
'model_D2_state_dict': model_D2.state_dict(),
'best_mean_iu': cur_miou16,
}, osp.join(logger.get_logger_dir(), 'checkpoint.pth.tar'))
if is_best:
import shutil
shutil.copy(
osp.join(logger.get_logger_dir(), 'checkpoint.pth.tar'),
osp.join(logger.get_logger_dir(), 'model_best.pth.tar'))
if i_iter >= args.num_steps_stop - 1:
break
def main():
"""Create the model and start the training."""
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
cudnn.enabled = True
gpu = args.gpu
# Create network
if args.model == 'DeepLab':
model = Res_Deeplab(num_classes=args.num_classes)
if args.restore_from[:4] == 'http':
saved_state_dict = model_zoo.load_url(args.restore_from)
else:
saved_state_dict = torch.load(args.restore_from)
model = torch.nn.DataParallel(model, device_ids=device_ids)
model.load_state_dict(saved_state_dict)
# ====the lines below comment by ZQ====
# new_params = model.state_dict().copy()
# for i in saved_state_dict:
# # Scale.layer5.conv2d_list.3.weight
# i_parts = i.split('.')
# # print i_parts
# if not args.num_classes == 19 or not i_parts[1] == 'layer5':
# new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
# # print i_parts
# model.load_state_dict(new_params)
# ====end====
model.train()
model.cuda(args.gpu)
cudnn.benchmark = True
# init D
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
trainloader = data.DataLoader(MixedDataSet(
args.data_dir,
args.data_list,
max_iters=args.num_steps * args.iter_size * args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True)
trainloader_iter = enumerate(trainloader)
# targetloader = data.DataLoader(cityscapesDataSet(args.data_dir_target, args.data_list_target,
# max_iters=args.num_steps * args.iter_size * args.batch_size,
# crop_size=input_size_target,
# scale=False, mirror=args.random_mirror, mean=IMG_MEAN,
# set=args.set),
# batch_size=args.batch_size, shuffle=False, num_workers=args.num_workers,
# pin_memory=True)
#
#
# targetloader_iter = enumerate(targetloader)
# implement model.optim_parameters(args) to handle different models' lr setting
optimizer = optim.SGD(model.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer = nn.DataParallel(optimizer, device_ids=device_ids)
optimizer.module.zero_grad()
# optimizer_D1 = optim.Adam(model_D1.parameters(), lr=args.learning_rate_D, betas=(0.9, 0.99))
# optimizer_D1.zero_grad()
#
# optimizer_D2 = optim.Adam(model_D2.parameters(), lr=args.learning_rate_D, betas=(0.9, 0.99))
# optimizer_D2.zero_grad()
bce_loss = torch.nn.BCEWithLogitsLoss()
interp = nn.Upsample(size=(input_size[1], input_size[0]),
mode='bilinear',
align_corners=True)
# interp_target = nn.Upsample(size=(input_size_target[1], input_size_target[0]), mode='bilinear')
# labels for adversarial training
# source_label = 0
# target_label = 1
loss2_sum_per_epoch = 0
loss2_per_epoch = 0
epoch = 0
loss2_epoch = ''
lbl_list = open(args.data_list, 'r')
lbl_num = len(lbl_list.readlines()) / 2
# lbl_list = os.listdir(args.data_dir+'/labels')
# lbl_num = len(lbl_list)/2
mIoUs = []
i_iters = []
for i_iter in range(args.num_steps):
loss_seg_value1 = 0
# loss_adv_target_value1 = 0
# loss_D_value1 = 0
loss_seg_value2 = 0
# loss_adv_target_value2 = 0
# loss_D_value2 = 0
optimizer.module.zero_grad()
adjust_learning_rate(optimizer, i_iter)
for sub_i in range(args.iter_size):
# train G
# train with source
_, batch = trainloader_iter.__next__()
images, labels, _, img_nam = batch
# print('%s\n' % img_nam[0])
images = Variable(images).cuda(args.gpu)
pred1, pred2 = model(images)
pred1 = interp(pred1)
pred2 = interp(pred2)
loss_seg1 = loss_calc(pred1, labels, args.gpu)
loss_seg2 = loss_calc(pred2, labels, args.gpu)
loss = loss_seg2 + args.lambda_seg * loss_seg1
# proper normalization
loss = loss / args.iter_size
loss.backward()
loss_seg_value1 += loss_seg1.data.cpu().numpy() / args.iter_size
loss_seg_value2 += loss_seg2.data.cpu().numpy() / args.iter_size
# train with target
optimizer.module.step()
# print('exp = {}'.format(args.snapshot_dir))
print('iter = {0:8d}/{1:8d}, loss_seg1 = {2:.3f} loss_seg2 = {3:.3f}'.
format(i_iter, args.num_steps, loss_seg_value1, loss_seg_value2))
if i_iter >= args.num_steps_stop - 1:
print('save model ...')
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'GTA5_' + str(args.num_steps) + '.pth'))
break
if i_iter % args.save_pred_every == 0 and i_iter != 0:
print('taking snapshot ...')
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'GTA5_' + str(i_iter + strat_snap_iter) + '.pth'))
show_pred_sv_dir = pre_sv_dir.format(i_iter)
mIoU = show_val(model.state_dict(), show_pred_sv_dir, gpu)
mIoUs.append(str(round(np.nanmean(mIoU) * 100, 2)))
i_iters.append(i_iter)
print_i = 0
for miou in mIoUs:
print('i{0}: {1}'.format(i_iters[print_i], miou))
print_i = print_i + 1
loss2_sum_per_epoch += loss_seg2.data.cpu().numpy()
if i_iter % lbl_num == 0 and i_iter != 0:
epoch += 1
loss2_per_epoch = loss2_sum_per_epoch / lbl_num
loss2_epoch += 'epoch = {0}, loss_seg2 = {1:.3f} \n'.format(
epoch, loss2_per_epoch)
print(loss2_epoch)
loss2_sum_per_epoch = 0