[英]In pytorch, how to train a model with two or more outputs?
output_1, output_2 = model(x)
loss = cross_entropy_loss(output_1, target_1)
loss.backward()
optimizer.step()
loss = cross_entropy_loss(output_2, target_2)
loss.backward()
optimizer.step()
但是,当我运行这段代码时,我得到了这个错误:
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [1, 4]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
然后,我真的很想知道我应该做什么来训练具有 2 个或更多输出的 model
pytorch(和其他 DL 框架)的整个前提是标量损失 function 的梯度的反向传播。
在您的情况下,您有一个向量(dim=2)损失 function:
[cross_entropy_loss(output_1, target_1), cross_entropy_loss(output_2, target_2)]
您需要决定如何将这两个损失组合成一个标量损失。
例如:
weight = 0.5 # relative weight
loss = weight * cross_entropy_loss(output_1, target_1) + (1. - weight) * cross_entropy_loss(output_2, target_2)
# now loss is a scalar
loss.backward()
optimizer.step()
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.