要求不借助resnest.torch复现哦

好的，那么我将使用PyTorch自己实现resnest50模型，并将通道数改为1。

resnest50模型是由4个stage组成，每个stage包含多个基本块（basic block）。我们可以根据论文中的描述和代码来实现这个模型。

import torch.nn as nn
import torch

class ResNeStBottleneck(nn.Module):
    def __init__(self, in_channels, out_channels, stride, cardinality, base_width, dilation=1):
        super(ResNeStBottleneck, self).__init__()
        
        width_ratio = out_channels / (cardinality * base_width)
        D = int(out_channels * (dilation / 64))
        self.conv1 = nn.Conv2d(in_channels, base_width * cardinality, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(base_width * cardinality)
        self.conv2 = nn.Conv2d(base_width * cardinality, base_width * cardinality, kernel_size=3, stride=stride, padding=dilation, dilation=dilation, groups=cardinality, bias=False)
        self.bn2 = nn.BatchNorm2d(base_width * cardinality)
        self.conv3 = nn.Conv2d(base_width * cardinality, D, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn3 = nn.BatchNorm2d(D)
        self.relu = nn.ReLU(inplace=True)
        self.stride = stride
        self.width_ratio = width_ratio
        self.cardinality = cardinality
        self.base_width = base_width
        self.D = D

    def forward(self, x):
        residual = x

        out = 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 residual.shape[1] != out.shape[1]:
            residual = torch.nn.functional.avg_pool2d(residual, kernel_size=1, stride=self.stride)
            residual = torch.cat((residual, torch.zeros_like(residual)), dim=1)

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

        return out

class ResNeStStage(nn.Module):
    def __init__(self, in_channels, out_channels, stride, num_blocks, cardinality, base_width, dilation=1):
        super(ResNeStStage, self).__init__()

        self.blocks = nn.ModuleList()
        for i in range(num_blocks):
            self.blocks.append(ResNeStBottleneck(in_channels, out_channels, stride if i == 0 else 1, cardinality, base_width, dilation))

    def forward(self, x):
        for block in self.blocks:
            x = block(x)
        return x

class ResNeSt50(nn.Module):
    def __init__(self, num_classes=1000):
        super(ResNeSt50, self).__init__()
        self.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.stage1 = ResNeStStage(64, 256, stride=1, num_blocks=3, cardinality=1, base_width=64)
        self.stage2 = ResNeStStage(256, 512, stride=2, num_blocks=4, cardinality=32, base_width=4)
        self.stage3 = ResNeStStage(512, 1024, stride=2, num_blocks=6, cardinality=32, base_width=4)
        self.stage4 = ResNeStStage(1024, 2048, stride=2, num_blocks=3, cardinality=32, base_width=4)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(2048, num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.stage1(x)
        x = self.stage2(x)
        x = self.stage3(x)
        x = self.stage4(x)

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

        return x

在这里，我们定义了ResNeStBottleneck类，它实现了resnest50中的基本块。我们还定义了ResNeStStage类，它实现了resnest50中的stage。最后，我们定义了ResNeSt50类，它实现了整个resnest50模型。

在ResNeStBottleneck类中，我们首先定义了3个卷积层和3个Batch Normalization层。接下来，我们将输入x和残差连接进行加和操作，并将结果通过ReLU激活函数。在forward函数中，我们实现了前向传播。

在ResNeStStage类中，我们使用nn.ModuleList来存储多个ResNeStBottleneck块，并在forward函数中将x传递到每个块中。

在ResNeSt50类中，我们首先定义了输入卷积层和Batch Normalization层，并将结果通过ReLU激活函数。接下来，我们定义了4个stage，并将它们串联在一起。最后，我们定义了全局平均池化层和全连接层。

现在，我们已经成功地实现了resnest50模型，并将通道数改为1。