# Define trasnforms
common_transforms = [
transform_utils.RandomHorizontalFlip(0.5),
transform_utils.RandomVerticalFlip(0.5)
]
#img_transforms = [transforms.ColorJitter()]
# Define network
net = model_def.SmallSegNet(input_channels, img_size)
# Define dataloaders
train_root = os.path.join(data_root, "train")
val_root = os.path.join(data_root, "val")
train_dset = model_def.SegmentationDataset(train_root,
list_common_trans=common_transforms,
list_img_trans=None)
val_dset = model_def.SegmentationDataset(val_root)
train_dset_loader = utils.data.DataLoader(train_dset,
batch_size=BATCH_SIZE,
shuffle=True)
val_dset_loader = utils.data.DataLoader(val_dset,
batch_size=BATCH_SIZE,
shuffle=True)
dset_loader_dict = {'train': train_dset_loader, 'val': val_dset_loader}
criterion_loss = nn.BCELoss()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Define trasnforms
common_transforms = [
transform_utils.RandomHorizontalFlip(0.5),
transform_utils.RandomVerticalFlip(0.5)
]
#img_transforms = [transforms.ColorJitter()]
# Define network
net = model_def.SmallSegNet(input_channels, img_size)
# Define dataloaders
train_root = os.path.join(data_root, "train")
val_root = os.path.join(data_root, "val")
train_dset = model_def.SegmentationDataset(train_root,
list_common_trans=common_transforms,
list_img_trans=None,
f_type="Numpy_array")
val_dset = model_def.SegmentationDataset(val_root, f_type="Numpy_array")
train_dset_loader = utils.data.DataLoader(train_dset,
batch_size=BATCH_SIZE,
shuffle=True)
val_dset_loader = utils.data.DataLoader(val_dset,
batch_size=BATCH_SIZE,
shuffle=True)
dset_loader_dict = {'train': train_dset_loader, 'val': val_dset_loader}
criterion_loss = nn.BCELoss()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")