Pytorch 显示错误：“NoneType”对象没有属性“zero_”答案

【问题标题】：Pytorch showing the error: 'NoneType' object has no attribute 'zero_'Pytorch 显示错误：“NoneType”对象没有属性“zero_”
【发布时间】：2021-06-11 02:25:40
【问题描述】：

我正在使用 Python 3.8 和 VSCode。

我尝试创建一个没有激活和偏差的基本神经网络，但由于错误，我无法更新权重的梯度。

矩阵详情：

层形状：（1，神经元数量）

权重层形状：（上一层的神经元数，下一层的神经元数）

这是我的代码：

# sample neural network

# importing libraries
import torch
import numpy as np
torch.manual_seed(0)

# hyperparameters
epochs = 100
lr = 0.01 # learning rate

# data
X_train = torch.tensor([[1]], dtype = torch.float)
y_train = torch.tensor([[2]], dtype = torch.float)

'''
Network Architecture:
    1 neuron in the first layer
    4 neurons in the second layer
    4 neurons in the third layer
    1 neuron in the last layer

    * I haven't added bias and activation.
'''

# initializing the weights
weights = []
weights.append(torch.rand((1, 4), requires_grad = True))
weights.append(torch.rand((4, 4), requires_grad = True))
weights.append(torch.rand((4, 1), requires_grad = True))

# calculating y_pred
y_pred = torch.matmul(torch.matmul(torch.matmul(X_train, weights[0]), weights[1]), weights[2])

# calculating loss
loss = (y_pred - y_train)**2

# calculating the partial derivatives
loss.backward()

# updating the weights and zeroing the gradients
with torch.no_grad():
    for i in range(len(weights)):
        weights[i] = weights[i] - weights[i].grad
        weights[i].grad.zero_()

它显示错误：

File "test3.py", line 43, in <module>
weights[i].grad.zero_()
AttributeError: 'NoneType' object has no attribute 'zero_'

我不明白为什么它会显示此错误。谁能解释一下？

【问题讨论】：

因为weights[i] = weights[i] - weights[i].grad 中的weights[i].grad 属于Nonetype

标签： machine-learning neural-network pytorch

【解决方案1】：

您的模型没有任何可训练的参数来计算 grad。使用火炬的参数。请参阅此link 以创建具有可学习参数的模块。

  torch.nn.parameter.Parameter
        A kind of Tensor that is to be considered a module parameter.

【讨论】：