Pytorch 实现冻结指定卷积层的参数

可以通过设置 requires_grad=False 来冻结指定卷积层的参数，示例如下：

import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
        self.conv4 = nn.Conv2d(64, 128, 3, padding=1)
        self.conv5 = nn.Conv2d(128, 256, 3, padding=1)

        # 将 conv3 和 conv4 冻结，不更新权重参数
        for param in self.conv3.parameters():
            param.requires_grad = False
        for param in self.conv4.parameters():
            param.requires_grad = False

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        return x

希望以上回答对您有所帮助！