打印网络名称以及相应shape

最新推荐文章于 2024-09-17 23:15:58 发布

一名CV界的小学生

最新推荐文章于 2024-09-17 23:15:58 发布

阅读量91

点赞数

分类专栏： python Pytorch API 文章标签： python pytorch 深度学习

本文链接：https://blog.csdn.net/weixin_40132776/article/details/131852390

版权

python 同时被 2 个专栏收录

26 篇文章 0 订阅

订阅专栏

Pytorch API

5 篇文章 0 订阅

订阅专栏

import torch
from torch import nn

net05=nn.Sequential(
    nn.Conv2d(1,96,kernel_size=11,
              stride=4,padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3,stride=2),
    nn.Conv2d(96,256,kernel_size=5,padding=2),
    nn.MaxPool2d(kernel_size=3,stride=2),
    
    nn.Conv2d(256,384,kernel_size=3,padding=1),
    nn.ReLU(),
    nn.Conv2d(384,384,kernel_size=3,padding=1),
    nn.ReLU(),
    nn.Conv2d(384,256,kernel_size=3,padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3,stride=2),
    nn.Flatten(),
    nn.Linear(6400,4096),
    nn.ReLU(),
    nn.Dropout(p=0.5),
    nn.Linear(4096,4096),
    nn.ReLU(),
    nn.Dropout(p=0.5),
    nn.Linear(4096,10)
)

XX00=torch.randn(1,1,224,224)
for layer in net05:
    XX00=layer(XX00)
    print(layer.__class__.__name__,"output shape:\t",XX00.shape)