Pytorch实现GoogLeNet解决各类数据集(cifar10/mnist/imagenet)分类

有一段时间没有更新了，这次我给大家带来的是大名鼎鼎的GoogleNet模型。也可以称为Inception v3模型。参考了源代码，写出了可读性与性能更优的模型，在模型上有些许微调，输入的图片大小是224 x 224 x 3.!!! 图片大小可以任意调节，甚至用来训练CIFAR10也可以。本文先放出代码。

完整代码点这里
)

import torch
from torch import nn

NUM_CLASSES = 10


class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.relu(x)
        return x


class Inception(nn.Module):
    def __init__(self, in_channel, n1_1, n3x3red, n3x3, n5x5red, n5x5, pool_plane):
        super(Inception, self).__init__()
        # first line
        self.branch1x1 = BasicConv2d(in_channel, n1_1, kernel_size=1)

        # s