def main(train_args):
path = "/mnt/iusers01/eee01/mchiwml4/dataset/cityscapes/"
transform = transforms.Compose([transforms.Normalize(mean, std)])
train_joint_transform = jointtransform.Compose([
jointtransform.Resize((1024, 512)),
jointtransform.RandomHorizontallyFlip(),
jointtransform.ToTensor()
])
val_joint_transform = jointtransform.Compose([jointtransform.ToTensor()])
train_dataset = DataLoader(Loaddata(path,
split="train",
transform=transform,
joint_transform=train_joint_transform),
batch_size=1,
shuffle=True,
num_workers=4)
valid_dataset = DataLoader(Loaddata(path,
split="val",
transform=transform,
joint_transform=val_joint_transform),
batch_size=1,
shuffle=False,
num_workers=4)
label_num = 19
model = deeplab_v2.Deeplab_Resnet(label_num)
model = model.cuda()
weight = torch.Tensor(class_weight).cuda()
criterion = CrossEntropyLoss2d(weight=weight).cuda()
lr_ = train_args.lr
optimizer = optim.SGD([{
'params': get_1x_lr_params(model),
'lr': lr_
}, {
'params': get_10x_lr_params(model),
'lr': lr_
}],
momentum=train_args.momentum,
weight_decay=train_args.weight_decay)
if train_args.load_param is not None:
model.load_state_dict(torch.load(train_args.load_param))
if train_args.load_optim is not None:
optimizer.load_state_dict(torch.load(train_args.load_optim))
max_epochs = train_args.epoch_num
train_model(model, criterion, optimizer, lr_, max_epochs, train_dataset,
valid_dataset)
def main(train_args):
path = "~/dataset/cityscapes"
transform = transforms.Compose([transforms.Normalize(mean, std)])
train_joint_transform = jointtransform.Compose(
[jointtransform.RandomCrop(800),
jointtransform.ToTensor()])
val_joint_transform = jointtransform.Compose([jointtransform.ToTensor()])
train_dataset = DataLoader(Loaddata(path,
split="train",
transform=transform,
joint_transform=train_joint_transform),
batch_size=1,
shuffle=True,
num_workers=4)
valid_dataset = DataLoader(Loaddata(path,
split="val",
transform=transform,
joint_transform=val_joint_transform),
batch_size=1,
shuffle=False,
num_workers=4)
label_num = 19
model = gcnmodel.GCN(label_num)
model = model.cuda()
weight = torch.Tensor(class_weight).cuda()
criterion = CrossEntropyLoss2d(weight=weight).cuda()
lr_ = train_args.lr
optimizer = optim.SGD(model.parameters(),
lr=lr_,
momentum=train_args.momentum,
weight_decay=train_args.weight_decay)
if train_args.load_param is not None:
model.load_state_dict(torch.load(train_args.load_param))
if train_args.load_optim is not None:
optimizer.load_state_dict(torch.load(train_args.load_optim))
max_epochs = train_args.epoch_num
savefolder = train_args.save_folder
batch_size = train_args.batch_size
train_model(model, batch_size, criterion, optimizer, lr_, max_epochs,
train_dataset, valid_dataset, savefolder)
def main(train_args):
trainset = "/mnt/iusers01/eee01/mchiwml4/CamVid/train"
validset = "/mnt/iusers01/eee01/mchiwml4/CamVid/val"
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize(mean, std)])
train_joint_transform = jointtransform.Compose(
[jointtransform.RandomHorizontallyFlip()])
train_dataset = DataLoader(Loaddata(trainset,
transform=transform,
target_transform=MaskToTensor(),
joint_transform=train_joint_transform),
batch_size=train_args.batch_size,
shuffle=True,
num_workers=8)
valid_dataset = DataLoader(Loaddata(validset,
transform=transform,
target_transform=MaskToTensor()),
batch_size=1,
shuffle=True,
num_workers=8)
label_num = 11
model = ducmodel.ResNetDUCHDC(label_num)
model = model.cuda()
weight = torch.Tensor(class_weight).cuda()
criterion = CrossEntropyLoss2d(weight=weight).cuda()
lr_ = train_args.lr
optimizer = optim.SGD([{
'params': get_1x_lr_params(model),
'lr': lr_
}, {
'params': get_10x_lr_params(model),
'lr': lr_ * 10
}],
momentum=train_args.momentum,
weight_decay=train_args.weight_decay)
# optimizer.param_groups[0]['lr'] = lr_
# optimizer.param_groups[1]['lr'] = lr_*10
if train_args.load_param is not None:
model.load_state_dict(torch.load(train_args.load_param))
if train_args.load_optim is not None:
optimizer.load_state_dict(torch.load(train_args.load_optim))
max_epochs = train_args.epoch_num
savefolder = train_args.save_folder
train_model(model, criterion, optimizer, lr_, max_epochs, train_dataset,
valid_dataset, savefolder)
def main(train_args):
trainset = "/mnt/iusers01/eee01/mchiwml4/CamVid/train"
validset = "/mnt/iusers01/eee01/mchiwml4/CamVid/val"
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize(mean, std)])
train_joint_transform = jointtransform.Compose(
[jointtransform.RandomHorizontallyFlip()])
train_dataset = DataLoader(Loaddata(trainset,
transform=transform,
target_transform=MaskToTensor(),
joint_transform=train_joint_transform),
batch_size=train_args.batch_size,
shuffle=True,
num_workers=8)
valid_dataset = DataLoader(Loaddata(validset,
transform=transform,
target_transform=MaskToTensor()),
batch_size=1,
shuffle=True,
num_workers=8)
label_num = 11
model = linknetmodel.linknet(label_num)
model = model.cuda()
weight = torch.Tensor(class_weight).cuda()
criterion = CrossEntropyLoss2d(weight=weight).cuda()
lr_ = train_args.lr
optimizer = optim.RMSprop(model.parameters(),
lr=lr_,
momentum=train_args.momentum,
weight_decay=train_args.weight_decay)
if train_args.load_param is not None:
model.load_state_dict(torch.load(train_args.load_param))
if train_args.load_optim is not None:
optimizer.load_state_dict(torch.load(train_args.load_optim))
max_epochs = train_args.epoch_num
train_model(model, criterion, optimizer, lr_, max_epochs, train_dataset,
valid_dataset)
from utils import check_mkdir
import os
import datetime
from tensorboardX import SummaryWriter
trainset="/mnt/iusers01/eee01/mchiwml4/CamVid/train"
validset="/mnt/iusers01/eee01/mchiwml4/CamVid/val"
testset="/mnt/iusers01/eee01/mchiwml4/CamVid/test"
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean, std)
])
train_joint_transform = jointtransform.Compose([
jointtransform.RandomHorizontallyFlip()
])
train_dataset = DataLoader(
Loaddata(trainset, transform=transform, target_transform=MaskToTensor(), joint_transform=train_joint_transform),
batch_size=4, shuffle=True, num_workers=8)
valid_dataset = DataLoader(
Loaddata(validset, transform=transform, target_transform=MaskToTensor()),
batch_size=1, shuffle=True, num_workers=8)
train_size = len(Loaddata(trainset))
valid_size = len(Loaddata(validset))
def get_1x_lr_params(model):
b = []
class CrossEntropyLoss2d(nn.Module):
def __init__(self, weight=None, size_average=True):
super(CrossEntropyLoss2d, self).__init__()
self.nll_loss = nn.NLLLoss2d(weight, size_average, ignore_index=255)
def forward(self, inputs, targets):
return self.nll_loss(F.log_softmax(inputs, dim=1), targets)
path = "/mnt/iusers01/eee01/mchiwml4/dataset/cityscapes/"
transform = transforms.Compose([transforms.Normalize(mean, std)])
train_joint_transform = jointtransform.Compose([
jointtransform.Resize((1024, 512)),
jointtransform.RandomHorizontallyFlip(),
jointtransform.ToTensor()
])
train_dataset = DataLoader(Loaddata(path,
split="train",
transform=transform,
joint_transform=train_joint_transform),
batch_size=2,
shuffle=True,
num_workers=4)
label_num = 19
model = linknetmodel.linknet(label_num)
model = model.cuda()
weight = torch.Tensor(class_weight).cuda()
