pytorch实现特殊的Module--Sqeuential三种写法

Python  /  管理员 发布于 5年前   371

我就废话不多说了，直接上代码吧！

# -*- coding: utf-8 -*-#@Time  :2019/7/1 13:34#@Author :XiaoMa import torch as tfrom torch import nn#Sequential的三种写法net1=nn.Sequential()net1.add_module('conv',nn.Conv2d(3,3,3))  #Conv2D(输入通道数，输出通道数，卷积核大小)net1.add_module('batchnorm',nn.BatchNorm2d(3))  #BatchNorm2d(特征数)net1.add_module('activation_layer',nn.ReLU()) net2=nn.Sequential(nn.Conv2d(3,3,3),          nn.BatchNorm2d(3),          nn.ReLU()          ) from collections import OrderedDictnet3=nn.Sequential(OrderedDict([  ('conv1',nn.Conv2d(3,3,3)),  ('bh1',nn.BatchNorm2d(3)),  ('al',nn.ReLU())])) print('net1',net1)print('net2',net2)print('net3',net3) #可根据名字或序号取出子moduleprint(net1.conv,net2[0],net3.conv1)

输出结果：

net1 Sequential( (conv): Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) (batchnorm): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activation_layer): ReLU()) net2 Sequential( (0): Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) (1): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU()) net3 Sequential( (conv1): Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) (bh1): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (al): ReLU()) Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1))

以上这篇pytorch实现特殊的Module--Sqeuential三种写法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。