“RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time”

当模型有多输出的时候，容易产生此问题，如以下程序所示：

        # zero the parameter gradients
        model.zero_grad()

        # forward + backward + optimize
        outputs, hidden = model(inputs, hidden)
        loss = _loss(outputs, session, items)
        acc_loss += loss.data[0]

        loss.backward()
        # Add parameters' gradients to their values, multiplied by learning rate
        for p in model.parameters():
            p.data.add_(-learning_rate, p.grad.data)

 

第一种解决方案：

detach/repackage the hidden state in between batches. There are (at least) three ways to do this.

1. hidden.detach_()
2. hidden = hidden.detach()
3. hidden = Variable(hidden.data, requires_grad=True) 

第二种解决方案：

replace loss.backward() with loss.backward(retain_graph=True) but know that each successive batch will take more time than the previous one because it will have to back-propagate all the way through to the start of the first batch.  

通常来说，第二种解决方案速度很慢，如果内存小的话会内存溢出