net = RNNModel(rnn_type='LSTM',
ntoken=helper.n_tokens,
ninp=helper.params['emsize'],
nhid=helper.params['nhid'],
nlayers=helper.params['nlayers'],
dropout=helper.params['dropout'],
tie_weights=helper.params['tied'])
else:
net = Net()
if helper.params.get('multi_gpu', False):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
logger.info(f"Let's use {torch.cuda.device_count()} GPUs!")
net = nn.DataParallel(net)
net.to(device)
if helper.params.get('resumed_model', False):
logger.info('Resuming training...')
loaded_params = torch.load(
f"saved_models/{helper.params['resumed_model']}")
net.load_state_dict(loaded_params['state_dict'])
helper.start_epoch = loaded_params['epoch']
# helper.params['lr'] = loaded_params.get('lr', helper.params['lr'])
logger.info(
f"Loaded parameters from saved model: LR is"
f" {helper.params['lr']} and current epoch is {helper.start_epoch}"
)
else:
helper.start_epoch = 1
num_workers=args.num_worker)
test_loader = DataLoader(dataset_test,
batch_size=args.batch_size_test,
shuffle=False,
num_workers=args.num_worker)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse',
'ship', 'truck')
print('==> Making model..')
net = DenseNet(growth_rate=args.growth_rate,
theta=args.theta,
num_layers=[12, 12, 12],
num_classes=10)
net = net.to(device)
if device == 'cuda':
net = torch.nn.DataParallel(net)
cudnn.benchmark = True
num_params = sum(p.numel() for p in net.parameters() if p.requires_grad)
print('The number of parameters of model is', num_params)
if args.resume is not None:
checkpoint = torch.load('./save_model/' + args.resume)
net.load_state_dict(checkpoint['net'])
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(),
lr=args.lr,
momentum=args.momentum,
