Resnet for Fashion_Mnist（二）

最新推荐文章于 2024-08-04 17:14:56 发布

lai199508

最新推荐文章于 2024-08-04 17:14:56 发布

阅读量917

点赞数

分类专栏：深度学习 pytorch 计算机视觉 Resnet 文章标签：计算机视觉 pytorch Fashion_Mnist 深度学习 Resnet

本文链接：https://blog.csdn.net/lai199508/article/details/85040009

版权

Resnet for Fashion_Mnist（二）

模型定义

下面给出Resnet的模型定义代码，包含了resnet18。想写其他restnet模型，可以在此基础上扩展。

import torch
import torch.nn as nn
import utils
import math
from torch.autograd import Variable


__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152']


def conv3x3(in_planes, out_planes, stride=1):
    "3x3 convolution with padding"
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d