def trainBatch(self, net, criterion, optimizer, cpu_images, cpu_texts):
batch_size = cpu_images.size(0)
loadData(self.image, cpu_images)
t, l = self.converter.encode(cpu_texts)
loadData(self.text, t)
loadData(self.length, l)
preds = net(self.image)
preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
cost = criterion(preds, self.text, preds_size,
self.length) / batch_size
net.zero_grad()
cost.backward()
optimizer.step()
return cost
def trainBatch(net, criterion, optimizer, cpu_images, cpu_texts):
# data = train_iter.next()
# cpu_images, cpu_texts = data
batch_size = cpu_images.size(0)
loadData(image, cpu_images)
t, l = converter.encode(cpu_texts)
loadData(text, t)
loadData(length, l)
preds = net(image)
preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
cost = criterion(preds, text, preds_size, length) / batch_size
net.zero_grad()
cost.backward()
optimizer.step()
return cost