写一个基于resnet18模型，用mish函数代替relu的代码

以下是使用Mish激活函数替换ReLU激活函数的ResNet18代码：

import torch.nn as nn
import torch.nn.functional as F
from mish_activation import Mish

class BasicBlock(nn.Module):
    
    expansion = 1
    
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        
        self.mish = Mish()
        
        self.downsample = downsample
        self.stride = stride
        
    def forward(self, x):
        identity = x
        
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.mish(out)
        
        out = self.conv2(out)
        out = self.bn2(out)
        
        if self.downsample is not None:
            identity = self.downsample(x)
            
        out += identity
        out = self.mish(out)
        
        return out
    

class ResNet(nn.Module):
    
    def __init__(self, block, layers, num_classes=1000):
        super(ResNet, self).__init__()
        
        self.in_channels = 64
        
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)
        
        self.mish = Mish()
        
    def _make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        
        if (stride != 1) or (self.in_channels != out_channels * block.expansion):
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * block.expansion)
            )
            
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * block.expansion
        
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))
            self.in_channels = out_channels * block.expansion
            
        return nn.Sequential(*layers)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.mish(x)
        x = self.maxpool(x)
        
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        
        x = self.avgpool(x)
        x = x.reshape(x.shape[0], -1)
        x = self.fc(x)
        
        return x

这里使用的是另一篇文章里提供的Mish激活函数实现，可在这里找到：https://github.com/digantamisra98/Mish