Paddle:VGG16 识别 MNIST

数据的处理

## 数据的生成器
# 加载相关库
import os
import random
import paddle
import paddle.fluid as fluid
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, Linear
import numpy as np
from PIL import Image

import gzip
import json

# 定义数据集读取器
def load_data(mode='train'):

    # 读取数据文件
    datafile = './work/mnist.json.gz'
    print('loading mnist dataset from {} ......'.format(datafile))
    data = json.load(gzip.open(datafile))
    # 读取数据集中的训练集，验证集和测试集
    train_set, val_set, eval_set = data

    # 数据集相关参数，图片高度IMG_ROWS, 图片宽度IMG_COLS
    IMG_ROWS = 28
    IMG_COLS = 28
    # 根据输入mode参数决定使用训练集，验证集还是测试
    if mode == 'train':
        imgs = train_set[0]
        labels = train_set[1]
    elif mode == 'valid':
        imgs = val_set[0]
        labels = val_set[1]
    elif mode == 'eval':
        imgs = eval_set[0]
        labels = eval_set[1]
    # 获得所有图像的数量
    imgs_length = len(imgs)
    # 验证图像数量和标签数量是否一致
    assert len(imgs) == len(labels), \
          "length of train_imgs({}) should be the same as train_labels({})".format(
                  len(imgs), len(labels))

    index_list = list(range(imgs_length))

  
    # 定义数据生成器
    def data_generator():
        # 训练模式下，打乱训练数据
        if mode == 'train':
            random.shuffle(index_list)
        imgs_list = []
        labels_list = []
        # 按照索引读取数据
        for i in index_list:
            # 读取图像和标签，转换其尺寸和类型
            img = np.reshape(imgs[i], [1, IMG_ROWS, IMG_COLS]).astype('float32')
            label = np.reshape(labels[i], [1]).astype('int64')
            imgs_list.append(img) 
            labels_list