def main():
start_time = time()
net = Net().to(setting.device)
net.train()
print('The modle has been initialized.')
# define loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate)
train_dataloader = data_preprocess.get_train_dataloader()
for epoch in tqdm(range(num_epochs)):
start = time()
# for train accuracy
# total = setting.train_img_nums
# correct = 0
for batch_idx, (imgs, labels) in enumerate(train_dataloader):
# imgs = Variable(imgs)
# label = Variable(labels)
imgs, labels = imgs.to(setting.device), labels.to(setting.device)
labels = labels.long()
labels_ohe_predict = net(imgs)
loss = 0
for i in range(setting.char_num):
one_label = labels[:, i * setting.pool_length:(i + 1) *
setting.pool_length]
one_class = one_label.argmax(dim=1)
one_predict_label = labels_ohe_predict[:,
i * setting.pool_length:
(i + 1) *
setting.pool_length]
one_loss = criterion(one_predict_label, one_class)
loss += one_loss
optimizer.zero_grad()
loss.backward()
optimizer.step()
# for single in range(labels_ohe_predict.shape[0]):
# single_labels_ohe_predict = labels_ohe_predict[single, :]
# predict_label = ''
# # get predict_label
# for slice in range(setting.char_num):
# char = ohe.num2char[np.argmax(
# single_labels_ohe_predict[slice*setting.pool_length:(slice+1)*setting.pool_length].cpu().data.numpy())]
# predict_label += char
# # get true label
# true_label = ohe.decode(labels[single, :].cpu().numpy())
# if predict_label == true_label:
# correct += 1
end = time()
print('epoch: {}, time: {:.2f}s loss: {:.04}'.format(
epoch, end - start, loss.item()))
# print('epoch: {}, time: {:.2f}s loss: {:.04} accuracy: {}/{} -- {:.4f}'.format(
# epoch, end-start, loss.item(), correct, total, correct/total))
torch.save(net.state_dict(), './model.pt')
finnal_time = time()
print('End at {}, cost {:.0f}s'.format(finnal_time,
finnal_time - start_time))
def train(loaders, save_path):
"""returns trained model"""
# Initialize custom defined cnn
model = Net()
use_cuda = torch.cuda.is_available()
if use_cuda:
model.cuda()
# cross entropy loss for classification task
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=config.lr)
# initialize tracker for minimum validation loss
valid_loss_min = np.Inf
n_epochs = config.n_epochs
for epoch in range(1, n_epochs + 1):
# initialize variables to monitor training and validation loss
train_loss = 0.0
valid_loss = 0.0
model.train()
for batch_idx, (data, target) in enumerate(loaders['train']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()
# average training loss
train_loss += (1 / (batch_idx + 1)) * (loss.data - train_loss)
# vaidation
model.eval()
for batch_idx, (data, target) in enumerate(loaders['valid']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## update the average validation loss
output = model(data)
loss = criterion(output, target)
valid_loss += (1 / (batch_idx + 1)) * (loss.data - valid_loss)
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.
format(epoch, train_loss, valid_loss))
# save the model if validation loss has decreased
if valid_loss <= valid_loss_min:
torch.save(model.state_dict(), save_path)
# Updating the validation loss minimum
valid_loss_min = valid_loss
# return trained model
return model
help='whether to use dropout in network')
parser.add_argument('--epochs', default=20, help='Number of Epochs')
parser.add_argument('--lr', default=0.01, help='Default LR set to one')
return parser.parse_args()
if __name__ == '__main__':
args = parse()
# is cuda available?
use_cuda = not args.no_cuda and torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
# load the data
train_loader, test_loader = LoadData().load_data()
model = Net(dropout=args.dropout).to(device)
logging.debug("Model Summary {}".format(
summary(model, input_size=(3, 32, 32))))
model = Net().to(device)
optimizer = optim.SGD(model.parameters(),
lr=0.01,
momentum=0.9,
nesterov=False)
# scheduler = StepLR(optimizer, step_size=8, gamma=0.1)
for epoch in range(args.epochs):
# print('Epoch:', epoch+1,'LR:', scheduler.get_lr()[0])
model.train(model, device, train_loader, optimizer)
model.test(model, device, test_loader)