错误：
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.
代码：
optimizer.zero_grad() # word
features = encoder(src)
loss = decoder(features, trg)
loss.backward()
grad_norm = torch.nn.utils.clip_grad_norm(decoder.parameters(), opt.grad_clip)############3
optimizer.step()
optimizer.zero_grad() # pos
# features = encoder(src)
loss = decoder.forward_pos(features, trg_pos)
loss.backward()
grad_norm = torch.nn.utils.clip_grad_norm(decoder.parameters(), opt.grad_clip)############3
optimizer.step()
代码更改为：
optimizer.zero_grad() # word
features = encoder(src)
loss = decoder(features, trg)
loss.backward()
grad_norm = torch.nn.utils.clip_grad_norm(decoder.parameters(), opt.grad_clip)############3
optimizer.step()
optimizer.zero_grad() # pos
features = encoder(src)
loss = decoder.forward_pos(features, trg_pos)
loss.backward()
grad_norm = torch.nn.utils.clip_grad_norm(decoder.parameters(), opt.grad_clip)############3
optimizer.step()
错误消失。
其他可参考网址：https://blog.csdn.net/u010829672/article/details/79538853