test_data_loader = data_utils.DataLoader(
test_dataset, batch_size=hparams.syncnet_batch_size,
num_workers=8)
device = torch.device("cuda" if use_cuda else "cpu")
# Model
model = SyncNet().to(device)
print('total trainable params {}'.format(sum(p.numel() for p in model.parameters() if p.requires_grad)))
optimizer = optim.Adam([p for p in model.parameters() if p.requires_grad],
lr=hparams.syncnet_lr)
if checkpoint_path is not None:
load_checkpoint(checkpoint_path, model, optimizer, reset_optimizer=False)
train(device, model, train_data_loader, test_data_loader, optimizer,
checkpoint_dir=checkpoint_dir,
checkpoint_interval=hparams.syncnet_checkpoint_interval,
nepochs=hparams.nepochs)
#we add a save option
if not os.path.exists(model_dir):
os.mkdir(model_dir)
model_path = model_dir+"/color_syncnet.pth"
print('\nModel Path : {}'.format(model_path))
torch.save(model.state_dict(),model_path)
else:
print('\nExisting model found at ' + model_dir)
print('\nDid not overwrite old model. Run the job again with a different location to store the model')
device = torch.device("cuda" if use_cuda else "cpu")
# Model
model = SyncNet().to(device)
print('total trainable params {}'.format(
sum(p.numel() for p in model.parameters() if p.requires_grad)))
wandb.watch(model)
optimizer = optim.Adam([p for p in model.parameters() if p.requires_grad],
lr=hparams.syncnet_lr)
if checkpoint_path is not None:
load_checkpoint(checkpoint_path,
model,
optimizer,
reset_optimizer=False)
train(device,
model,
train_data_loader,
test_data_loader,
optimizer,
checkpoint_dir=checkpoint_dir,
checkpoint_interval=hparams.syncnet_checkpoint_interval,
nepochs=hparams.nepochs)
torch.save(model.state_dict(), "model.h5")
wandb.save('model.h5')
