pytorch_detach 切斷網(wǎng)絡(luò)反傳方式

    detach = _add_docstr(_C._TensorBase.detach, r"""
    Returns a new Tensor, detached from the current graph.
    The result will never require gradient.
    .. note::
      Returned Tensor uses the same data tensor as the original one.
      In-place modifications on either of them will be seen, and may trigger
      errors in correctness checks.
    """)

import torch
from torch.nn import init
t1 = torch.tensor([1., 2.],requires_grad=True)
t2 = torch.tensor([2., 3.],requires_grad=True)
v3 = t1 + t2
v3_detached = v3.detach()
v3_detached.data.add_(t1) # 修改了 v3_detached Variable中 tensor 的值
print(v3, v3_detached)    # v3 中tensor 的值也會改變
print(v3.requires_grad,v3_detached.requires_grad)
'''
tensor([4., 7.], grad_fn=<AddBackward0>) tensor([4., 7.])
True False
'''

# 默認(rèn)創(chuàng)建requires_grad = False的Tensor
x = torch.ones(1)   # create a tensor with requires_grad=False (default)
print(x.requires_grad)
 # out: False
 
 # 創(chuàng)建另一個Tensor，同樣requires_grad = False
y = torch.ones(1)  # another tensor with requires_grad=False
 # both inputs have requires_grad=False. so does the output
z = x + y
 # 因?yàn)閮蓚€Tensor x,y，requires_grad=False.都無法實(shí)現(xiàn)自動微分，
 # 所以操作（operation）z=x+y后的z也是無法自動微分，requires_grad=False
print(z.requires_grad)
 # out: False
 
 # then autograd won't track this computation. let's verify!
 # 因而無法autograd，程序報錯
# z.backward()
 # out：程序報錯：RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
    
# now create a tensor with requires_grad=True
w = torch.ones(1, requires_grad=True)
print(w.requires_grad)
 # out: True
 
 # add to the previous result that has require_grad=False
 # 因?yàn)閠otal的操作中輸入Tensor w的requires_grad=True，因而操作可以進(jìn)行反向傳播和自動求導(dǎo)。
total = w + z
# the total sum now requires grad!
total.requires_grad
# out: True
# autograd can compute the gradients as well
total.backward()
print(w.grad)
#out: tensor([ 1.])
# and no computation is wasted to compute gradients for x, y and z, which don't require grad
# 由于z，x，y的requires_grad=False,所以并沒有計算三者的梯度
z.grad == x.grad == y.grad == None
# True

import torch.nn.functional as F
# With square kernels and equal stride
filters = torch.randn(8,4,3,3)
weiths = torch.nn.Parameter(torch.randn(8,4,3,3))
inputs = torch.randn(1,4,5,5)
out = F.conv2d(inputs, weiths, stride=2,padding=1)
print(out.shape)
con2d = torch.nn.Conv2d(4,8,3,stride=2,padding=1)
out_2 = con2d(inputs)
print(out_2.shape)

import torch 
a = torch.tensor([1, 2, 3.], requires_grad=True)
print(a)
print(a.grad)
out = a.sigmoid()
 
out.sum().backward()
print(a.grad)

import torch 
a = torch.tensor([1, 2, 3.], requires_grad=True)
print(a.grad)
out = a.sigmoid()
print(out)
 
#添加detach(),c的requires_grad為False
c = out.detach()
print(c)
 
#這時候沒有對c進(jìn)行更改，所以并不會影響backward()
out.sum().backward()
print(a.grad)
 
'''返回：
None
tensor([0.7311, 0.8808, 0.9526], grad_fn=<SigmoidBackward>)
tensor([0.7311, 0.8808, 0.9526])
tensor([0.1966, 0.1050, 0.0452])
'''