ptorch F.softmax() 梯度信息为None

我在进行一个测试梯度实验的时候,发现,当原始变量流经F.softmax以后,原始变量的梯度就无法获得了,例子如下:

import torch.nn.functional as F
import torch


x = torch.randn(1,5,requires_grad=True)
print(x)
# x = F.softmax(x,dim=1)
# print(x)
l = 0
for i in range(5):
    l = l + x[0][i]

print(l)
l.backward()
print(x.grad)

如果x不经过F.softmax(),则会出现如下的梯度信息:

tensor([[ 1.4093, -0.2620,  0.6668, -0.3897,  1.4681]], requires_grad=True)
tensor(2.8925, grad_fn=)
tensor([[1., 1., 1., 1., 1.]])

如果经过了F.softmax(),则x的梯度信息就无法获得了,例子如下:

import torch.nn.functional as F
import torch


x = torch.randn(1,5,requires_grad=True)
print(x)
x = F.softmax(x,dim=1)
print(x)
l = 0
for i in range(5):
    l = l + x[0][i]

print(l)
l.backward()
print(x.grad)

此时的x的梯度为None:

tensor([[ 1.0408,  0.5212,  0.2902, -0.7637, -0.7276]], requires_grad=True)
tensor([[0.4163, 0.2476, 0.1965, 0.0685, 0.0710]], grad_fn=)
tensor(1., grad_fn=)
None

 

你可能感兴趣的:(pytorch,深度学习)