PyTorch实现ResNet50、ResNet101和ResNet152示例


Posted in Python onJanuary 14, 2020

PyTorch: https://github.com/shanglianlm0525/PyTorch-Networks

PyTorch实现ResNet50、ResNet101和ResNet152示例

import torch
import torch.nn as nn
import torchvision
import numpy as np

print("PyTorch Version: ",torch.__version__)
print("Torchvision Version: ",torchvision.__version__)

__all__ = ['ResNet50', 'ResNet101','ResNet152']

def Conv1(in_planes, places, stride=2):
  return nn.Sequential(
    nn.Conv2d(in_channels=in_planes,out_channels=places,kernel_size=7,stride=stride,padding=3, bias=False),
    nn.BatchNorm2d(places),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
  )

class Bottleneck(nn.Module):
  def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 4):
    super(Bottleneck,self).__init__()
    self.expansion = expansion
    self.downsampling = downsampling

    self.bottleneck = nn.Sequential(
      nn.Conv2d(in_channels=in_places,out_channels=places,kernel_size=1,stride=1, bias=False),
      nn.BatchNorm2d(places),
      nn.ReLU(inplace=True),
      nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
      nn.BatchNorm2d(places),
      nn.ReLU(inplace=True),
      nn.Conv2d(in_channels=places, out_channels=places*self.expansion, kernel_size=1, stride=1, bias=False),
      nn.BatchNorm2d(places*self.expansion),
    )

    if self.downsampling:
      self.downsample = nn.Sequential(
        nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False),
        nn.BatchNorm2d(places*self.expansion)
      )
    self.relu = nn.ReLU(inplace=True)
  def forward(self, x):
    residual = x
    out = self.bottleneck(x)

    if self.downsampling:
      residual = self.downsample(x)

    out += residual
    out = self.relu(out)
    return out

class ResNet(nn.Module):
  def __init__(self,blocks, num_classes=1000, expansion = 4):
    super(ResNet,self).__init__()
    self.expansion = expansion

    self.conv1 = Conv1(in_planes = 3, places= 64)

    self.layer1 = self.make_layer(in_places = 64, places= 64, block=blocks[0], stride=1)
    self.layer2 = self.make_layer(in_places = 256,places=128, block=blocks[1], stride=2)
    self.layer3 = self.make_layer(in_places=512,places=256, block=blocks[2], stride=2)
    self.layer4 = self.make_layer(in_places=1024,places=512, block=blocks[3], stride=2)

    self.avgpool = nn.AvgPool2d(7, stride=1)
    self.fc = nn.Linear(2048,num_classes)

    for m in self.modules():
      if isinstance(m, nn.Conv2d):
        nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
      elif isinstance(m, nn.BatchNorm2d):
        nn.init.constant_(m.weight, 1)
        nn.init.constant_(m.bias, 0)

  def make_layer(self, in_places, places, block, stride):
    layers = []
    layers.append(Bottleneck(in_places, places,stride, downsampling =True))
    for i in range(1, block):
      layers.append(Bottleneck(places*self.expansion, places))

    return nn.Sequential(*layers)


  def forward(self, x):
    x = self.conv1(x)

    x = self.layer1(x)
    x = self.layer2(x)
    x = self.layer3(x)
    x = self.layer4(x)

    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    x = self.fc(x)
    return x

def ResNet50():
  return ResNet([3, 4, 6, 3])

def ResNet101():
  return ResNet([3, 4, 23, 3])

def ResNet152():
  return ResNet([3, 8, 36, 3])


if __name__=='__main__':
  #model = torchvision.models.resnet50()
  model = ResNet50()
  print(model)

  input = torch.randn(1, 3, 224, 224)
  out = model(input)
  print(out.shape)

以上这篇PyTorch实现ResNet50、ResNet101和ResNet152示例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三水点靠木。

Python 相关文章推荐
python定时检查启动某个exe程序适合检测exe是否挂了
Jan 21 Python
python 实现红包随机生成算法的简单实例
Jan 04 Python
Python实现KNN邻近算法
Jan 28 Python
Python简单实现查找一个字符串中最长不重复子串的方法
Mar 26 Python
对python的输出和输出格式详解
Dec 08 Python
使用python3实现操作串口详解
Jan 01 Python
python+logging+yaml实现日志分割
Jul 22 Python
在 Python 中接管键盘中断信号的实现方法
Feb 04 Python
python 实现字符串下标的输出功能
Feb 13 Python
python requests.get带header
May 05 Python
解决Keras使用GPU资源耗尽的问题
Jun 22 Python
Python使用pandas导入xlsx格式的excel文件内容操作代码
Dec 24 Python
python重要函数eval多种用法解析
Jan 14 #Python
关于ResNeXt网络的pytorch实现
Jan 14 #Python
Python属性和内建属性实例解析
Jan 14 #Python
Python程序控制语句用法实例分析
Jan 14 #Python
dpn网络的pytorch实现方式
Jan 14 #Python
Django之form组件自动校验数据实现
Jan 14 #Python
简单了解python filter、map、reduce的区别
Jan 14 #Python
You might like
手把手教你使用DedeCms的采集的图文教程
2007/03/11 PHP
PHP set_time_limit(0)长连接的实现分析
2010/03/02 PHP
在VS2008中编译MYSQL5.1.48的方法
2010/07/03 PHP
Linux fgetcsv取得的数组元素为空字符串的解决方法
2011/11/25 PHP
WordPress自定义时间显示格式
2015/03/27 PHP
Yii2.0建立公共方法简单示例
2019/01/29 PHP
使一个函数作为另外一个函数的参数来运行的javascript代码
2007/08/13 Javascript
JavaScript中几个重要的属性(this、constructor、prototype)介绍
2013/05/19 Javascript
js复制到剪切板的实例方法
2013/06/28 Javascript
js与jquery获取父级元素,子级元素,兄弟元素的实现方法
2014/01/09 Javascript
JavaScript截取字符串的Slice、Substring、Substr函数详解和比较
2014/03/20 Javascript
JavaScript中的some()方法使用详解
2015/06/09 Javascript
jQuery下拉友情链接美化效果代码分享
2015/08/26 Javascript
AngularJS使用自定义指令替代ng-repeat的方法
2016/09/17 Javascript
微信小程序(应用号)开发新闻客户端实例
2016/10/24 Javascript
JS公共小方法之判断对象是否为domElement的实例
2016/11/25 Javascript
详解jQuery同步Ajax带来的UI线程阻塞问题及解决办法
2017/08/09 jQuery
Nuxt.js实战详解
2018/01/18 Javascript
Vue press 支持图片放大功能的实例代码
2018/11/09 Javascript
jquery添加div实现消息聊天框
2020/02/08 jQuery
简述Python中的面向对象编程的概念
2015/04/27 Python
python SQLAlchemy 中的Engine详解
2019/07/04 Python
使用python接受tgam的脑波数据实例
2020/04/09 Python
python 简单的调用有道翻译
2020/11/25 Python
Mytheresa美国官网:德国知名的女性奢侈品电商
2017/05/27 全球购物
马歇尔耳机官网:Marshall Headphones
2020/02/04 全球购物
Lookfantastic阿联酋官网:英国知名美妆护肤购物网站
2020/05/26 全球购物
PHP面试题集
2016/12/18 面试题
咖啡店自主创业商业计划书
2014/01/22 职场文书
关于责任的演讲稿
2014/05/20 职场文书
党员对十八届四中全会的期盼思想汇报范文
2014/10/17 职场文书
2014年数学教师工作总结
2014/12/03 职场文书
2015年全国科普日活动总结
2015/03/23 职场文书
四年级作文之说明文作文
2019/10/14 职场文书
Nginx+Tomcat实现负载均衡、动静分离的原理解析
2021/03/31 Servers
Redis入门教程详解
2021/08/30 Redis