Question

我整天都在解决这个问题。

torch.autograd.backward(loss_seq, grad_seq)将出现错误。

输出：

Traceback (most recent call last):
  File "train_vgg.py", line 272, in <module>
    torch.autograd.backward(loss_seq, grad_seq)
  File "/root/anaconda3/lib/python3.6/site- 
packages/torch/autograd/__init__.py", line 90, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: invalid gradient at index 0 - expected shape [] but got [1]

输入：

loss_seq:[tensor(7.3761, device='cuda:1', grad_fn=<ThAddBackward>), tensor(4.3005, device='cuda:1', grad_fn=<ThAddBackward>), tensor(4.2209, device='cuda:1', grad_fn=<ThAddBackward>)]
grad_seq:[tensor([1.], device='cuda:1'), tensor([1.], device='cuda:1'), tensor([1.], device='cuda:1')]

```

有人可以告诉他们如何解决吗？

输入代码：

images = Variable(images).cuda(gpu)

label_yaw = Variable(labels[:,0]).cuda(gpu)
label_pitch = Variable(labels[:,1]).cuda(gpu)
label_roll = Variable(labels[:,2]).cuda(gpu)

pre_yaw, pre_pitch, pre_roll = model(images)

# Cross entropy loss
loss_yaw = criterion(pre_yaw, label_yaw)
loss_pitch = criterion(pre_pitch, label_pitch)
loss_roll = criterion(pre_roll, label_roll)

loss_yaw += 0.005 * loss_reg_yaw
loss_pitch += 0.005 * loss_reg_pitch
loss_roll += 0.005 * loss_reg_roll

loss_seq = [loss_yaw, loss_pitch, loss_roll]
grad_seq = [torch.ones(1).cuda(gpu) for _ in range(len(loss_seq))]

# crash here
torch.autograd.backward(loss_seq, grad_seq)

Answer 1

我已经解决了这个问题。唯一的改变：

grad_seq = [torch.ones(1).cuda(gpu) for _ in range(len(loss_seq))]

收件人：

grad_seq = [torch.tensor(1.0).cuda(gpu) for _ in range(len(loss_seq))]

Pytorch 0.4.1在索引0处无效的渐变-预期形状[]但得到了[1]

1 个答案: