phase="val",
valSize=4)
print("Train Dataset Path :", trainData_path)
print("Val Dataset Path :", valData_path)
# make model
pix2pixHD = Pix2PixHDModel(opt)
# dataloader
train_dataloader = DataLoader(
dataset=train_dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.nThreads,
)
val_dataloader = DataLoader(
dataset=val_dataset,
batch_size=len(val_dataset),
shuffle=False,
num_workers=opt.nThreads,
)
# updater
updater = Updater(dataloader=train_dataloader, model=pix2pixHD)
# trainer
trainer = Trainer(updater, opt, val_dataloader=val_dataloader)
# run
log = trainer.run()
# The device (GPU/CPU) on which to execute the code
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# The model to train
model = Glow(context_blocks=4,
flow_steps=8,
input_channels=3,
hidden_channels=256,
quantization=256,
lu_decomposition=False)
model.to(device)
# Path to the directory where the results will be saved
saving_directory = \
os.path.join(os.getcwd(), 'results',
datetime.now().strftime("%Y-%m-%d_%H-%M-%S"))
trainer = Trainer(model=model,
data_path=data_dir,
batch_size=4,
learning_rate=0.0001,
saving_directory=saving_directory,
device=device,
weight_norm=True,
data_augmentation=0.1)
# Start the learning
trainer.run()
