从张量复制构造:用户警告

问题描述 投票:1回答:1

我正在从正态分布中创建一个随机张量,并且由于该张量在NN中用作权重,因此要添加require_grad属性,我使用torch.tensor()如下:

import torch 

input_dim, hidden_dim = 3, 5

norm = torch.distributions.normal.Normal(loc=0, scale=0.01)
W = norm.sample((input_dim, hidden_dim))
W = torch.tensor(W, requires_grad=True)

我收到如下用户警告错误:

    UserWarning: To copy construct from a tensor, 
    it is recommended to use sourceTensor.clone().detach() or 
sourceTensor.clone().detach().requires_grad_(True), 
rather than torch.tensor(sourceTensor).

是否有其他方法可以实现上述目标?谢谢

neural-network pytorch torch
1个回答
0
投票

您可以仅将W.requires_grad设置为True

import torch 

input_dim, hidden_dim = 3, 5

norm = torch.distributions.normal.Normal(loc=0, scale=0.01)
W = norm.sample((input_dim, hidden_dim))
W.requires_grad = True
© www.soinside.com 2019 - 2024. All rights reserved.