cifar10 32*32转227*227 适合AlexNet

def read_cifar10_data():
    data_dir = CURRENT_DIR+'/data/cifar-10-batches-py/'
    train_name = 'data_batch_'
    test_name = 'test_batch'
    train_X = None
    train_Y = None
    test_X = None
    test_Y = None

    # train data
    for i in range(1,6):
        file_path = data_dir+train_name+str(i)
        with open(file_path, 'rb') as fo:
            
            dict = cPickle.load(fo)
           
            if  train_X is None:
                train_X = dict['data']
                train_Y = dict['labels']
            else:
                train_X = np.concatenate((train_X, dict['data']), axis=0)
                train_Y = np.concatenate((train_Y, dict['labels']), axis=0)
                
                
    # test_data
    file_path = data_dir + test_name
    with open(file_path, 'rb') as fo:
        dict = cPickle.load(fo)

        test_X = dict['data']
        test_Y = dict['labels']
    
    
    train_X = train_X.reshape((50000, 3, 32, 32)).transpose(0, 2, 3, 1)
    
    train_X_resized = np.zeros((50000,227,227,3))# 创建一个存储修改过图片分辨率的矩阵
    
    for i in range(0,50000):
        img = train_X[i]
        img = Image.fromarray(img)
        img = np.array(img.resize((227,227),Image.BICUBIC))# 修改分辨率，再转为array类
        train_X_resized[i,:,:,:] = img
    
    test_X = test_X.reshape((10000, 3, 32, 32)).transpose(0, 2, 3, 1)
    
    test_X_resized = np.zeros((10000,227,227,3))# 创建一个存储修改过图片分辨率的矩阵
    
    for i in range(0,10000):
        img = test_X[i]
        img = Image.fromarray(img)
        img = np.array(img.resize((227,227),Image.BICUBIC))# 修改分辨率，再转为array类
        test_X_resized[i,:,:,:] = img
    

    train_y_vec = np.zeros((len(train_Y), 10), dtype=np.float)
    test_y_vec = np.zeros((len(test_Y), 10), dtype=np.float)
    for i, label in enumerate(train_Y):
        train_y_vec[i, int(train_Y[i])] = 1.  # y_vec[1,3] means #2 row, #4column
    for i, label in enumerate(test_Y):
        test_y_vec[i, int(test_Y[i])] = 1.  # y_vec[1,3] means #2 row, #4column

    return train_X_resized/255., train_y_vec, test_X_resized/255., test_y_vec

缺点：需要至少60G内存