实验1：inception - v4模型的实现

本来做的实验是：inception-v4模型实现，并且用它来进行推理，但是推理的部分实在是没必要做笔记。就是《inference汇总》稍微改了一点点而已。这里就只把inception-v4模型的实现列出来了。完整的inference的代码见：D:\pythonCodes\深度学习实验\4.1_经典分类网络\7：GoogLeNet v4\inference_inceptionV4

在torchvision中，是没有inception-v4的实现的。这里找的是：https://github.com/Cadene/pretrained-models.pytorch/blob/master/pretrainedmodels/models/inceptionv4.py

并下载了他提供的预训练模型参数。

代码：

from __future__ import print_function, division, absolute_import
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo

__all__ = ['InceptionV4', 'inceptionv4']

pretrained_settings = {
    'inceptionv4': {
        'imagenet': {
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/inceptionv4-8e4777a0.pth',
            'input_space': 'RGB',
            'input_size': [3, 299, 299],
            'input_range': [0, 1],
            'mean': [0.5, 0.5, 0.5],
            'std': [0.5, 0.5, 0.5],
            'num_classes': 1000
        },
        'imagenet+background': {
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/inceptionv4-8e4777a0.pth',
            'input_space': 'RGB',
            'input_size': [3, 299, 299],
            'input_range': [0, 1],
            'mean': [0.5, 0.5, 0.5],
            'std': [0.5, 0.5, 0.5],
            'num_classes': 1001
        }
    }
}


class BasicConv2d(nn.Module):

    def __init__(self, in_planes, out_planes, kernel_size, stride, padding=0):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_planes, out_planes,
                              kernel_size=kernel_size, stride=stride,
                              padding=padding, bias=False) # verify bias false
        self.bn = nn.BatchNorm2d(out_planes,
                                 eps=0.001, # value found in tensorflow
                                 momentum=0.1, # default pytorch value
                                 affine=True)
        self.relu = nn.ReLU(inplace=True)

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

# Stem
class Mixed_3a(nn.Module):

    def __init__(self):
        super(Mixed_3a, self).__init__()
        self.maxpool = nn.MaxPool2d(3, stride=2)
        self.conv = BasicConv2d(64, 96, kernel_si