Neural network 从张量复制构造：用户警告

我正在从正态分布创建一个随机张量，由于该张量用作NN中的权重，为了添加requires_grad属性，我使用torch.tensor（）如下所示：

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)

    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).

我收到如下用户警告错误：

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)

    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).

---

是否有其他方法实现上述目标？谢谢

您可以将

W.requires\u 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