ResNet50《pytorch学习篇》

引言：resNet50网络作为res网络家族中的一员，特别强调的是残差网络是何大神提出的，轰动世界的大江南北，主要是因为：当时的卷积神经网络主要通过不断地增加卷积层来提取图像的特征，但是这会引发一个问题-----梯度爆炸问题或者梯度消失问题，也就是说卷积层的数量设置，必须有一定的限制，否则会出现物极必反的现象，然而此时，和大神就提出了残差网络，成功地解决了此类问题，也为自己在国际深度学习的领域奠定了基础。今天主要是学习一下是如何实现的，以一个简单的resNet网络为例子学习，下面一起来看看吧！！！（物极必反--古训）

1》res50主要构成:

首先介绍一下网络的主要框架。如下：（主要由Bottleneck组成）

Sequential((0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(4): Sequential(（0）Bottleneck（）（1）Bottleneck（）（2）Bottleneck（）)(5): Sequential((0): Bottleneck()(1): Bottleneck()(2): Bottleneck()(3): Bottleneck())(6): Sequential((0): Bottleneck()(1): Bottleneck()(2): Bottleneck()(3): Bottleneck()(4): Bottleneck()(5): Bottleneck())(7): Sequential((0): Bottleneck()(1): Bottleneck()(2): Bottleneck())

解释：这里的Bottleneck大同小异，差不多，但还是有区别滴，我的小可爱梦，请注意哦！！！

2》what is it Bottleneck？

so，here is :

import torch.nn as nnclass Bottleneck(nn.Module):expansion = 4def __init__(self, inplanes, planes, stride=1, downsample=None):super(Bottleneck, self).__init__()self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False) # changeself.bn1 = nn.BatchNorm2d(planes)self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # changepadding=1, bias=False)self.bn2 = nn.BatchNorm2d(planes)self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)self.bn3 = nn.BatchNorm2d(planes * 4)self.relu = nn.ReLU(inplace=True)self.downsample = downsampleself.stride = stridedef forward(self, x):residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)if self.downsample is not None:residual = self.downsample(x)out += residualout = self.relu(out)return out

解释：也是由基础的卷积、正则化、激活函数构成。只不过在此基础上增加了一个小插曲，residual （残差，类似于劈腿那种，第三者插入，盗用一张图！）

图片来源于百度（侵权请联系删除）

解释：只不过上图所示是经过两次然后融合，然而Bottleneck是经过三次然后融合。

3》完整代码

官方：torchvision.models — Torchvision 0.11.0 documentation

文章：https://arxiv.org/abs/1512.03385

代码：

res50代码：

Sequential((0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(4): Sequential((0): Bottleneck((conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(5): Sequential((0): Bottleneck((conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(3): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(6): Sequential((0): Bottleneck((conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(3): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(4): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(5): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(7): Sequential((0): Bottleneck((conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))
)

ResNet50《pytorch学习篇》相关推荐

迁移学习篇之如何迁移经典CNN网络-附迁移学习Alexnet，VGG，Googlenet，Resnet详细代码注释和方法-pytorch
鸽了好久的迁移学习篇学习终于打算更新,这次我们来学习一个机器学习中经典常用的简单快速提高网络指标的trick,迁移学习,迁移学习本身是机器学习中的一个trick,但是近些年在深度学习中应用广泛.之前我 ...
Pytorch学习- 小型知识点汇总 unsqueeze()/squeeze() 和 .max() 等等
1. unsqueeze(input, dim, out=None)函数 - 升维作用参考链接在指定的地方上增加一个维度 0(-2) [行扩展]: 表示在张量最外层增加一个中括号变成第一维 1(- ...
手撕 CNN 经典网络之 VGGNet（PyTorch实战篇）
大家好,我是红色石头! 在上一篇文章: 手撕 CNN 经典网络之 VGGNet(理论篇) 详细介绍了 VGGNet 的网络结构,今天我们将使用 PyTorch 来复现VGGNet网络,并用VGGNet ...
pytorch学习笔记（2）：在MNIST上实现一个CNN
参考文档:https://mp.weixin.qq.com/s/1TtPWYqVkj2Gaa-3QrEG1A 这篇文章是在一个大家经常见到的数据集 MNIST 上实现一个简单的 CNN.我们会基于上一 ...
PyTorch学习笔记（六）：PyTorch进阶训练技巧
PyTorch实战:PyTorch进阶训练技巧往期学习资料推荐: 1.Pytorch实战笔记_GoAI的博客-CSDN博客 2.Pytorch入门教程_GoAI的博客-CSDN博客本系列目录: P ...
PyTorch学习笔记（五）：模型定义、修改、保存
往期学习资料推荐: 1.Pytorch实战笔记_GoAI的博客-CSDN博客 2.Pytorch入门教程_GoAI的博客-CSDN博客本系列目录: PyTorch学习笔记(一):PyTorch环境安 ...
PyTorch学习笔记2：nn.Module、优化器、模型的保存和加载、TensorBoard
文章目录一.nn.Module 1.1 nn.Module的调用 1.2 线性回归的实现二.损失函数三.优化器 3.1.1 SGD优化器 3.1.2 Adagrad优化器 3.2 分层学习率 3 ...
PyTorch学习系列教程：构建一个深度学习模型需要哪几步？
导读继续PyTorch学习系列.前篇介绍了PyTorch中最为基础也最为核心的数据结构--Tensor,有了这些基本概念即可开始深度学习实践了.本篇围绕这一话题,本着提纲挈领删繁就简的原则,从宏观上 ...
PyTorch学习笔记——图像处理（transforms.Normalize 归一化）
PyTorch学习笔记--图像处理 transforms.Normalize 归一化回顾 torchvision.ToTensor 归一化 transforms.Normalize 公式回顾 to ...

ResNet50《pytorch学习篇》

1》res50主要构成:

2》what is it Bottleneck？

3》完整代码

ResNet50《pytorch学习篇》相关推荐

最新文章

热门文章