pytorch Variable與Tensor合并后 requires_grad()默認(rèn)與修改方式

import torch
from torch.autograd import Variable #使用Variabl必須調(diào)用庫
lis=torch.range(1,6).reshape((-1,3))#創(chuàng)建1~6 形狀 
#行不指定（-1意為由計算機自己計算）列為3的floattensor矩陣

print(lis)
print(lis.requires_grad) #查看默認(rèn)的requires_grad是否是Flase

lis.requires_grad_() #使用.requires_grad_()修改默認(rèn)requires_grad為true
print(lis.requires_grad)

import torch
from torch.autograd import Variable
tensor=torch.FloatTensor(range(8)).reshape((-1,4))
my_ten=Variable(tensor)
print(my_ten)
print(my_ten.requires_grad)

my_ten.requires_grad_()
print(my_ten.requires_grad)

# 默認(rèn)創(chuàng)建requires_grad = False的Tensor  
x = torch . ones ( 1 ) # create a tensor with requires_grad=False (default)
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
# 因為兩個Tensor x,y，requires_grad=False.都無法實現(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
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 ) 
w . requires_grad
# out: True

# add to the previous result that has require_grad=False
# 因為total的操作中輸入Tensor w的requires_grad=True，因而操作可以進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 ( ) 
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
existing_tensor . requires_grad_ ( ) 
existing_tensor . requires_grad
# out：True

my_tensor = torch.zeros(3,4,requires_grad = True) 
my_tensor.requires_grad
# out: True

lis=torch.range(1,6,requires_grad=True).reshape((-1,3))
print(lis)
print(lis.requires_grad)
lis.requires_grad_()
print(lis.requires_grad)