李宏毅 机器学习2020 作业5 hw5-explainAI

本次作业做的是解释机器学习是如何识别一张图片的。用到了上一次CNN作业训练好的模型。
先导入需要用得到的库，其中lime需要提前安装。
我在安装的时候，conda install命令不能使用，但是使用pip命令就可以安装了。

import os
from torch.utils.data import DataLoader
import sys
import argparse
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.optim import Adam
from torch.utils.data import Dataset
import torchvision.transforms as transforms
from skimage.segmentation import slic
from lime import lime_image
from pdb import set_trace

如果要用torch.model（）来导入模型是需要这个类的定义的。

class Classifier(nn.Module):
    def __init__(self):
        super(Classifier, self).__init__()
        # torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
        # torch.nn.MaxPool2d(kernel_size, stride, padding)
        # input 維度 [3, 128, 128]
        self.cnn = nn.Sequential(
            nn.Conv2d(3, 64, 3, 1, 1),  # [64, 128, 128]
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(2, 2, 0),      # [64, 64, 64]

            nn.Conv2d(64, 128, 3, 1, 1), # [128, 64, 64]
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(2, 2, 0),      # [128, 32, 32]

            nn.Conv2d(128, 256, 3, 1, 1), # [256, 32, 32]
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(2, 2, 0),      # [256, 16, 16]

            nn.Conv2d(256, 512, 3, 1, 1), # [512, 16, 16]
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(2, 2, 0),       # [512, 8, 8]
            
            nn.Conv2d(512, 512, 3, 1, 1), # [512, 8, 8]
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(2, 2, 0),       # [512, 4, 4]
        )
        self.fc = nn.Sequential(
            nn.Linear(512*4*4, 1024),
            nn.ReLU(),
            nn.Linear(1024, 512),
            nn.ReLU(),
            nn.Linear(512, 11)
        )

    def forward(self, x):
        out = self.cnn(x)
        out = out.view(out.size()[0], -1)
        return self.fc(out)

class FoodDataset(Dataset):
    def __init__(self, paths, labels, mode):
        # mode: 'train' or 'eval'
        #mode是train就用train的transform
        
        
        #paths是每一个图片的名字
        #labels是每一个图片对应的label        
        self.paths = paths
        self.labels = labels
        
        trainTransform = transforms.Compose([
            transforms.Resize(size=(128, 128)),
            transforms.RandomHorizontalFlip(),
            transforms.RandomRotation(15),
            transforms.ToTensor(),
        ])
        evalTransform = transforms.Compose([
            transforms.Resize(size=(128, 128)),
            transforms.ToTensor(),
        ])        
        self.transform = trainTransform if mode == 'train' else evalTransform
        
    def __len__(self):
        return len(self.paths)

    def __getitem__(self, index):
        X = Image.open(self.paths[index])
        X = self.transform(X)
        Y = self.labels[index]
        return X, Y

#这个函数是为了方便的取出指定index的图片
    def getbatch(self, indices):
        images = []
        labels = []
        for index in indices:
          image, label = self.__getitem__(index)
          images.append(image)
          labels.append(label)
        return torch.stack(images), torch.tensor(labels)

    
# 给一个文件夹的名字，可以返回他下面图片的名字和labels的名字
def get_paths_labels(path)