以VGG16为例如何数网络层数 |
您所在的位置：网站首页 › vgg有多少层 › 以VGG16为例如何数网络层数 |
以VGG16为例如何数网络层数
|
以VGG16为例如何数网络层数 flyfish 方法1 使用Pytorch调用代码输出网络 import torch import torch.nn as nn import torch.nn.functional as F from collections import namedtuple from typing import List, Tuple import torchvision.models as models import sys model=models.vgg16() print(model)输出的网络如下 VGG( (features): Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): ReLU(inplace) (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (6): ReLU(inplace) (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (8): ReLU(inplace) (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU(inplace) (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (13): ReLU(inplace) (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (15): ReLU(inplace) (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (18): ReLU(inplace) (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (20): ReLU(inplace) (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (22): ReLU(inplace) (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (25): ReLU(inplace) (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (27): ReLU(inplace) (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (29): ReLU(inplace) (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) (avgpool): AdaptiveAvgPool2d(output_size=(7, 7)) (classifier): Sequential( (0): Linear(in_features=25088, out_features=4096, bias=True) (1): ReLU(inplace) (2): Dropout(p=0.5) (3): Linear(in_features=4096, out_features=4096, bias=True) (4): ReLU(inplace) (5): Dropout(p=0.5) (6): Linear(in_features=4096, out_features=1000, bias=True) ) )可以数Conv2D MaxPool2D 以下面5行为例 (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): ReLU(inplace) (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)从0开始算 第0行的Conv2d 是 conv1_1 第2行的conv2 是 conv1_2 第4行的MaxPool2d pool1 这样依次向下 遇到Linear 就是FC 第0行 Linear(in_features=25088, out_features=4096, bias=True) 25088实际是51277 ，已经到了FC6 最后的Linear是FC8 方法2 根据源码的配置 地址是 https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py cfgs = { 'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'], 'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'], 'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'], 'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'], }A B D E分别表示vgg11, vgg13, vgg16, vgg19 16和19的卷积网络都是stride=1，kernel size=3，padding=1的卷积， 池化层则使用的是最大池化层，stride=2，kernel size=2 cfgs中的m表示batch normalization，可以根据参数选择使用M还是不使用， 例如VGG16排除M，数个数，最后加上3个Linear即FC 2（个64）+2个（128）+3(个256)+6（个512）+3（个FC）=16 可视化的图形如下 
|
【本文地址】