def train(crnn, train_loader, criterion, epoch):
for p in crnn.parameters():
p.requires_grad = True
crnn.train()
#loss averager
loss_avg = utils.averager()
for i_batch, (image, index) in enumerate(train_loader):
#[b,c,h,w] [32,1,32,160]
image = image.to(device)
print('image.shape:', image.shape)
batch_size = image.size(0)
#['xxx','xxxx',...batch]
label = utils.get_batch_label(dataset, index)
#[41,batch,nclass]
preds = crnn(image)
# print('preds.shape',preds.shape)
# index = np.array(index.data.numpy())
#[, , ,] [len(lable[0]),len(lable[1]),...]
label_text, label_length = converter.encode(label)
# print('label_text:', len(label_text))
# print('label_length:', label_length)
#[41,41,41,...]*batch
preds_size = torch.IntTensor([preds.size(0)] * batch_size)
# print('preds.shape, label_text.shape, preds_size.shape, label_length.shape',preds.shape, label_text.shape, preds_size.shape, label_length.shape)
# torch.Size([41, 32, 6736]) torch.Size([320]) torch.Size([320]) torch.Size([320])
cost = criterion(preds, label_text, preds_size,
label_length) / batch_size
# print('cost:',cost)
crnn.zero_grad()
cost.backward()
optimizer.step()
loss_avg.add(cost)
if (i_batch + 1) % params.displayInterval == 0:
print('[%d/%d][%d/%d] Loss: %f' %
(epoch, params.epochs, i_batch, len(train_loader),
loss_avg.val()))
loss_avg.reset()
net.zero_grad()
cost.backward()
optimizer.step()
return cost
for epoch in range(config.niter):
loss_avg.reset()
print('epoch {}....'.format(epoch))
train_iter = iter(train_loader)
i = 0
n_batch = len(train_loader)
while i < len(train_loader):
for p in crnn.parameters():
p.requires_grad = True
crnn.train()
cost = trainBatch(crnn, criterion, optimizer)
print('epoch: {} iter: {}/{} Train loss: {:.3f}'.format(
epoch, i, n_batch, cost.item()))
loss_avg.add(cost)
loss_avg.add(cost)
i += 1
print('Train loss: %f' % (loss_avg.val()))
if config.use_log:
with open(log_filename, 'a') as f:
f.write('{}\n'.format(
datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')))
f.write('train_loss:{}\n'.format(loss_avg.val()))
val(crnn, test_dataset, criterion)