关于pytorch的autograd机制

关于源码还是没看懂

问题：

Q: 对pytorch里GAN更新G的过程疑问？
fake=G(x)
G.zero_gard()
out = D(fake)
loss = cri(out,label)
loss.backward()
opt_G.step()
这里，经过了D网络结构，怎么可以就之更新G了呢？？？
A: 经过了前向传播之后，pytorch就构建了计算图，可以想像G计算图的输出作为了D计算图的输入，当loss.backward的时候虽然计算了所有计算图的梯度，但是由于只更新了G参数的数值，所以只利用了G计算图的梯度，这是可以理解的。之前纠结的点是跳过D更新G,但计算梯度的时候确实是经过了D的。只是GAN这里没有去更新D。

code

敲了敲代码模拟了一下这个过程

import torch
import torch.nn as nn
import torch.optim as optim

net1 = nn.Conv2d(2,1,kernel_size=3)
net2 = nn.Linear(3,1)
x = torch.randn((1,2 ,5, 5), requires_grad=True)
opt_1 = optim.SGD(net1.parameters(),lr=0.01,momentum=0)
opt_2 = optim.SGD(net2.parameters(),lr=0.01,momentum=0)
cri = nn.MSELoss()

#打印参数（ out_channels x in_channels x kernel_size x kernel_size )
for p in net1.parameters():
    print(p) 
>>>
    Parameter containing:
    tensor([[[[-0.1586,  0.0571, -0.0606],
              [-0.0712, -0.0753,  0.1583],
              [-0.1438,  0.0217,  0.2169]],
    
             [[ 0.0830, -0.2124,  0.1965],
              [ 0.2107,  0.0655, -0.2229],
              [ 0.0809,  0.1761, -0.2056]]]], requires_grad=True)
    Parameter containing:
    tensor([0.2213], requires_grad=True)


for p in net2.parameters():
    print(p)
>>>
    Parameter containing:
    tensor([[0.1985, 0.0381, 0.3382]], requires_grad=True)
    Parameter containing:
    tensor([0.1597], requires_grad=True)

#through net1
y = net1(x)
print('y',y)
#through net2
z = net2(y)
print('z',z,z.shape)

>>>
    y tensor([[[[ 0.7343,  0.1432, -0.3362],
              [ 0.5525,  0.5968,  0.6297],
              [ 1.0429, -0.0552,  0.6783]]]], grad_fn=<MkldnnConvolutionBackward>)
    z tensor([[[[0.1972],
              [0.5050],
              [0.5940]]]], grad_fn=<AddBackward0>) torch.Size([1, 1, 3, 1])

#reshape z and compute loss
net1.zero_grad()
new_z = z.reshape(1,-1)
target = torch.tensor([[1,1,0]],dtype=torch.float)
loss = cri(new_z,target)

#before backward
print(net1.bias.grad)
print(net2.bias.grad)
#==========compute gradient======
loss.backward()
#================================
#after
print(net1.bias.grad)
print(net2.bias.grad)
for f in net1.parameters():
    print(f.grad.data)

>>>
    None
    None
    tensor([-0.2697])
    tensor([-0.4691])
    tensor([[[[-0.5155, -0.3812, -0.3589],
              [ 0.2562, -0.3376,  0.1517],
              [ 0.2322, -0.2214,  0.0431]],
    
             [[ 0.1007,  0.2636,  0.0203],
              [ 0.0201,  0.0348, -0.2474],
              [-0.0404,  0.0261,  0.0283]]]])
    tensor([-0.2697])

for p in net1.parameters():
    print(p)
    print('manully updata params:')
    tmp_p = p.data.clone()
    print(tmp_p.sub_(p.grad.data*0.01))#weight = weight-lr*d_p
    print('---')
    print(p.data)
for p in net2.parameters():
    print(p)

Parameter containing:
tensor([[[[-0.1586,  0.0571, -0.0606],
          [-0.0712, -0.0753,  0.1583],
          [-0.1438,  0.0217,  0.2169]],

         [[ 0.0830, -0.2124,  0.1965],
          [ 0.2107,  0.0655, -0.2229],
          [ 0.0809,  0.1761, -0.2056]]]], requires_grad=True)
manully updata params:
tensor([[[[-0.1535,  0.0609, -0.0570],
          [-0.0738, -0.0719,  0.1568],
          [-0.1461,  0.0239,  0.2165]],

         [[ 0.0820, -0.2150,  0.1963],
          [ 0.2105,  0.0652, -0.2204],
          [ 0.0813,  0.1758, -0.2059]]]])
---
tensor([[[[-0.1586,  0.0571, -0.0606],
          [-0.0712, -0.0753,  0.1583],
          [-0.1438,  0.0217,  0.2169]],

         [[ 0.0830, -0.2124,  0.1965],
          [ 0.2107,  0.0655, -0.2229],
          [ 0.0809,  0.1761, -0.2056]]]])
Parameter containing:
tensor([0.2213], requires_grad=True)
manully updata params:
tensor([0.2240])
---
tensor([0.2213])
Parameter containing:
tensor([[0.1985, 0.0381, 0.3382]], requires_grad=True)
Parameter containing:
tensor([0.1597], requires_grad=True)

#upadate
opt_1.step()

for p in net1.parameters():
    print(p)
print('=======')
for p in net2.parameters():
    print(p)

Parameter containing:
tensor([[[[-0.1535,  0.0609, -0.0570],
          [-0.0738, -0.0719,  0.1568],
          [-0.1461,  0.0239,  0.2165]],

         [[ 0.0820, -0.2150,  0.1963],
          [ 0.2105,  0.0652, -0.2204],
          [ 0.0813,  0.1758, -0.2059]]]], requires_grad=True)
Parameter containing:
tensor([0.2240], requires_grad=True)
=======
Parameter containing:
tensor([[0.1985, 0.0381, 0.3382]], requires_grad=True)
Parameter containing:
tensor([0.1597], requires_grad=True)

大概就是这么个流程，不过具体的自动求导机制暂时还看不懂源码，之后如果看懂的话，会在这里补充的。