【问题标题】:Using flatten in pytorch v1.0 Sequential module在 pytorch v1.0 Sequential 模块中使用 flatten
【发布时间】:2020-04-05 08:05:07
【问题描述】:

由于我的 CUDA 版本是 8,我使用的是 torch 1.0.0

我需要将 Flatten 层用于 Sequential 模型。这是我的代码:

import torch
import torch.nn as nn
import torch.nn.functional as F
print(torch.__version__)
# 1.0.0
from collections import OrderedDict

layers = OrderedDict()
layers['conv1'] = nn.Conv2d(1, 5, 3)
layers['relu1'] = nn.ReLU()
layers['conv2'] = nn.Conv2d(5, 1, 3)
layers['relu2'] = nn.ReLU()
layers['flatten'] = nn.Flatten()
layers['linear1'] = nn.Linear(3600, 1)
model = nn.Sequential(
layers
).cuda()

它给了我以下错误:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-38-080f7c5f5037> in <module>
      6 layers['conv2'] = nn.Conv2d(5, 1, 3)
      7 layers['relu2'] = nn.ReLU()
----> 8 layers['flatten'] = nn.Flatten()
      9 layers['linear1'] = nn.Linear(3600, 1)
     10 model = nn.Sequential(

AttributeError: module 'torch.nn' has no attribute 'Flatten'

如何在 pytorch 1.0.0 中展平我的转换层输出?

【问题讨论】:

    标签: python pytorch conv-neural-network


    【解决方案1】:

    只需新建一个 Flatten 层。

    from collections import OrderedDict
    
    class Flatten(nn.Module):
        def forward(self, input):
            return input.view(input.size(0), -1)
    
    layers = OrderedDict()
    layers['conv1'] = nn.Conv2d(1, 5, 3)
    layers['relu1'] = nn.ReLU()
    layers['conv2'] = nn.Conv2d(5, 1, 3)
    layers['relu2'] = nn.ReLU()
    layers['flatten'] = Flatten()
    layers['linear1'] = nn.Linear(3600, 1)
    model = nn.Sequential(
    layers
    ).cuda()
    

    【讨论】:

      猜你喜欢
      • 2017-10-23
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2019-12-05
      • 1970-01-01
      相关资源
      最近更新 更多