NNDL 实验六 卷积神经网络（5）使用预训练resnet18实现CIFAR-10分类

5.5 实践：基于ResNet18网络完成图像分类任务

图像分类（Image Classification）

计算机视觉中的一个基础任务，将图像的语义将不同图像划分到不同类别。

很多任务可以转换为图像分类任务。

比如人脸检测就是判断一个区域内是否有人脸，可以看作一个二分类的图像分类任务。

• 数据集：CIFAR-10数据集，
• 网络：ResNet18模型，
• 损失函数：交叉熵损失，
• 优化器：Adam优化器，Adam优化器的介绍参考NNDL第7.2.4.3节。
• 评价指标：准确率。

5.5.1 数据处理

5.5.1.1数据集导入

def load_cifar10_batch(folder_path, batch_id=1, mode='train'):
    if mode == 'test':
        file_path = os.path.join(folder_path, 'test_batch')
    else:
        file_path = os.path.join(folder_path, 'data_batch_' + str(batch_id))
    with open(file_path, 'rb') as batch_file:
        batch = pickle.load(batch_file, encoding='latin1')

    imgs = batch['data'].reshape((len(batch['data']), 3, 32, 32)) / 255.
    labels = batch['labels']

    return np.array(imgs, dtype='float32'), np.array(labels)

加载数据集：

imgs_batch, labels_batch = load_cifar10_batch(folder_path='C:/Users/20637/Documents/Tencent Files/2063716648/FileRecv/cifar-10-batches-py',batch_id=1, mode='train')

print("batch of imgs shape: ", imgs_batch.shape, "batch of labels shape: ", labels_batch.shape)

观察一下数据集中的一张图片：

import matplotlib.pyplot as plt

image, label = imgs_batch[1], labels_batch[1]
print("The label in the picture is {}".format(label))
plt.figure(figsize=(2, 2))
plt.imshow(image.transpose(1, 2, 0))
plt.savefig('cnn-car.pdf')

5.5.1.2 划分训练集、验证集、测试集

import torch
from torch.utils.data import Dataset, DataLoader
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import PIL.Image as Image

划分训练集、验证集、测试集的函数：

class CIFAR10Dataset(Dataset):
    def __init__(self, folder_path='C:/Users/20637/Documents/Tencent Files/2063716648/FileRecv/cifar-10-batches-py', mode='train'):
        if mode == 'train':
            self.imgs, self.labels = load_cifar10_batch(folder_path=folder_path, batch_id=1, mode='train')
            for i in range(2, 5):
                imgs_batch, labels_batch = load_cifar10_batch(folder_path=folder_path, batch_id=i, mode='train')
                self.imgs, self.labels = np.concatenate([self.imgs, imgs_batch]), np.concatenate(
                    [self.labels, labels_batch])
        elif mode == 'dev':
            self.imgs, self.labels = load_cifar10_batch(folder_path=folder_path, batch_id=5, mode='dev')
        elif mode == 'test':
            self.imgs, self.labels = load_cifar10_batch(folder_path=folder_path, mode='test')
        self.transform = transforms