for i in range(1, len(bbb)):
imidx = imidx + "." + bbb[i]
tra_lbl_name_list.append(data_dir + tra_label_dir + imidx + label_ext)
print("---")
print("train images: ", len(tra_img_name_list))
print("train labels: ", len(tra_lbl_name_list))
print("---")
train_num = len(tra_img_name_list)
salobj_dataset = SalObjDataset(img_name_list=tra_img_name_list,
lbl_name_list=tra_lbl_name_list,
transform=transforms.Compose([
RescaleT(320),
RandomCrop(288),
ToTensorLab(flag=0)
]))
salobj_dataloader = DataLoader(salobj_dataset,
batch_size=batch_size_train,
shuffle=True,
num_workers=1)
net = U2NET(3, 1)
if torch.cuda.is_available():
net.cuda()
net = nn.DataParallel(net)
# ------- 4. define optimizer --------
print("---define optimizer...")
optimizer = optim.Adam(net.parameters(),
lr=0.001,
vgg_model = VGGNet(freeze_max=False)
net = FCN8s(vgg_model)
checkpoint = torch.load('baseline.pth')
net.load_state_dict(checkpoint['model_state_dict'])
device = torch.device('cuda:0') if torch.cuda.is_available() else torch.device(
'cpu')
net.to(device)
# train dataloader
scale = Rescale(int(1.5 * 230))
crop = RandomCrop(224)
rotate = RandomRotate(20.0)
norm = Normalize()
tupled = ToTupleTensor()
tupled_with_roi_align = ToRoIAlignTensor()
composed_for_tracking = transforms.Compose(
[Rescale(224), norm, tupled_with_roi_align])
dataset = SISSDataset(num_slices=153,
num_scans=2,
root_dir=Path.cwd().parents[0],
transform=composed_for_tracking,
train=True)
dataloader = torch.utils.data.DataLoader(dataset,
def main():
# ------- 2. set the directory of training dataset --------
model_name = 'u2net' #'u2netp'
data_dir = 'C:\datasets'
tra_image_dir = '\DUTS\DUTS-TR\DUTS-TR-Image\\'
tra_label_dir = '\DUTS\DUTS-TR\DUTS-TR-Mask\\'
image_ext = '.jpg'
label_ext = '.png'
model_dir = './saved_models/' + model_name + '/'
epoch_num = 100000
batch_size_train = 4
batch_size_val = 1
train_num = 0
val_num = 0
tra_img_name_list = glob.glob(data_dir + tra_image_dir + '*')
print(tra_img_name_list)
tra_lbl_name_list = []
for img_path in tra_img_name_list:
img_name = img_path.split("\\")[-1]
aaa = img_name.split(".")
bbb = aaa[0:-1]
#去除后缀的图片名
imidx = bbb[0]
# print(imidx)
for i in range(1, len(bbb)):
imidx = imidx + "." + bbb[i]
print(imidx, "**********")
tra_lbl_name_list.append(data_dir + tra_label_dir + imidx + label_ext)
print("---")
print("train images: ", len(tra_img_name_list))
print("train labels: ", len(tra_lbl_name_list))
print("---")
train_num = len(tra_img_name_list)
salobj_dataset = SalObjDataset(img_name_list=tra_img_name_list,
lbl_name_list=tra_lbl_name_list,
transform=transforms.Compose([
RescaleT(320),
RandomCrop(288),
ToTensorLab(flag=0)
]))
salobj_dataloader = DataLoader(salobj_dataset,
batch_size=batch_size_train,
shuffle=True,
num_workers=1)
# ------- 3. define model --------
# define the net
if (model_name == 'u2net'):
net = U2NET(3, 1)
elif (model_name == 'u2netp'):
net = U2NETP(3, 1)
if torch.cuda.is_available():
net.cuda()
# ------- 4. define optimizer --------
print("---define optimizer...")
optimizer = optim.Adam(net.parameters(),
lr=0.001,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=0)
net.pool34.parameters()
# ------- 5. training process --------
print("---start training...")
ite_num = 0
running_loss = 0.0
running_tar_loss = 0.0
ite_num4val = 0
save_frq = 2000 # save the model every 2000 iterations
for epoch in range(0, epoch_num):
net.train()
for i, data in enumerate(salobj_dataloader):
ite_num = ite_num + 1
ite_num4val = ite_num4val + 1
inputs, labels = data['image'], data['label']
inputs = inputs.type(torch.FloatTensor)
labels = labels.type(torch.FloatTensor)
# wrap them in Variable
if torch.cuda.is_available():
# A = nn.Parameter(inputs,requires_grad=True)
inputs_v, labels_v = Variable(inputs.cuda(),
requires_grad=False), Variable(
labels.cuda(),
requires_grad=False)
else:
inputs_v, labels_v = Variable(
inputs, requires_grad=False), Variable(labels,
requires_grad=False)
# y zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
d0, d1, d2, d3, d4, d5, d6 = net(inputs_v)
loss2, loss = muti_bce_loss_fusion(d0, d1, d2, d3, d4, d5, d6,
labels_v)
loss.backward()
optimizer.step()
# # print statistics
running_loss += loss.item()
running_tar_loss += loss2.item()
# delete temporary outputs and loss
del d0, d1, d2, d3, d4, d5, d6, loss2, loss
print(
"[epoch: %3d/%3d, batch: %5d/%5d, ite: %d] train loss: %3f, tar: %3f "
% (epoch + 1, epoch_num,
(i + 1) * batch_size_train, train_num, ite_num,
running_loss / ite_num4val, running_tar_loss / ite_num4val))
if ite_num % save_frq == 0:
# torch.save(net.state_dict(), model_dir + model_name+"_bce_itr_%d_train_%3f_tar_%3f.pth" % (ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val))
running_loss = 0.0
running_tar_loss = 0.0
net.train() # resume train
ite_num4val = 0