pytorch获取nn.Sequential的中间层输出

对于nn.Sequential结构，要想获取中间网络层输出，可以使用循环遍历的方式得到。

示例

import torch
import torch.nn as nn
model = nn.Sequential(
            nn.Conv2d(3, 9, 1, 1, 0, bias=False),
            nn.BatchNorm2d(9),
            nn.ReLU(inplace=True),
            nn.AdaptiveAvgPool2d((1, 1)),
        )
# 假如想要获得ReLu的输出
x = torch.rand([2, 3, 224, 224])
for i in range(len(model)):
    x = model[i](x)
    if i == 2:
        ReLu_out = x
print('ReLu_out.shape：\n\t',ReLu_out.shape)
print('x.shape：\n\t',x.shape)

结果

ReLu_out.shape：
  torch.Size([2, 9, 224, 224])
x.shape：
  torch.Size([2, 9, 1, 1])