nn.ModuleList使用案例以及module’ object has no attributes ‘linear‘

最新推荐文章于 2024-03-21 09:56:32 发布

安之若醇

最新推荐文章于 2024-03-21 09:56:32 发布

阅读量811

点赞数

分类专栏：实验室的xml 文章标签：深度学习 python pytorch

本文链接：https://blog.csdn.net/weixin_49599247/article/details/129418756

版权

实验室的xml 专栏收录该内容

23 篇文章 1 订阅

订阅专栏

上网找的一个代码是这么写的：nn.ModuleList([nn.linear for i in range(10)])
我以为nn.linear是正常的呢！
没想到直接报错module’ object has no attributes ‘linear’

这里还是要注意大小写的

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.linears = nn.ModuleList([nn.Linear(128,128) for i in range(10)])

    # ModuleList can act as an iterable, or be indexed using ints
    def forward(self, x):
        for i, l in enumerate(self.linears):
            x = self.linears[i](x) 
        return x

输出网络：

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
t = MyModel().to(device)
print(t)

代码输出：

MyModel(
  (linears): ModuleList(
    (0): Linear(in_features=128, out_features=128, bias=True)
    (1): Linear(in_features=128, out_features=128, bias=True)
    (2): Linear(in_features=128, out_features=128, bias=True)
    (3): Linear(in_features=128, out_features=128, bias=True)
    (4): Linear(in_features=128, out_features=128, bias=True)
    (5): Linear(in_features=128, out_features=128, bias=True)
    (6): Linear(in_features=128, out_features=128, bias=True)
    (7): Linear(in_features=128, out_features=128, bias=True)
    (8): Linear(in_features=128, out_features=128, bias=True)
    (9): Linear(in_features=128, out_features=128, bias=True)
  )
)