新版本torch中Variable和Tensor合并

Variable和Tensor

import torch
from torch.autograd import Variable # torch 中 Variable 模块

tensor = torch.FloatTensor([[1,2],[3,4]])
variable = Variable(tensor)

print(tensor)
print(variable)
结果如下:
tensor([[1., 2.], [3., 4.]]) tensor([[1., 2.], [3., 4.]])

发现tensor和variable输出的形式是一样的,在新版本的torch中可以直接使用tensor而不需要使用variable。

在旧版本中variable和tensor的区别在于,variable可以进行误差的反向传播,而tensor不可以。

接下来看一下,合并Tensor和Variable之后autograd是如何实现历史追踪和反向传播的

作为能否autograd的标签,requires_grad现在是Tensor的属性,所以,只要当一个操作(operation)的任何输入Tensor具有requires_grad = True的属性,autograd就可以自动追踪历史和反向传播了。

官方给出的具体例子如下:

# 默认创建requires_grad = False的Tensor
 x = torch.ones(1)   # create a tensor with requires_grad=False (default)
 x.requires_grad
 # out: False
 
 # 创建另一个Tensor,同样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
 # 因为两个Tensor x,y,requires_grad=False.都无法实现自动微分,
 # 所以操作(operation)z=x+y后的z也是无法自动微分,requires_grad=False
 z.requires_grad
 # out: False
 
 # then autograd won't track this computation. let's verify!
 # 因而无法autograd,程序报错
 z.backward()
 # out:程序报错: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
 # 因为total的操作中输入Tensor w的requires_grad=True,因而操作可以进行反向传播和自动求导。
 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,所以并没有计算三者的梯度
z.grad == x.grad == y.grad == None
# True

猜你喜欢

转载自www.cnblogs.com/funnything/p/11022557.html