Neural Networks and Deep Learning 学习笔记(十二)

最新推荐文章于 2022-05-14 16:01:54 发布

土逗甜菜

最新推荐文章于 2022-05-14 16:01:54 发布

阅读量785

点赞数

CC 4.0 BY-SA版权

分类专栏： TensorFlow 文章标签：深度学习

本文链接：https://blog.youkuaiyun.com/lmw21848/article/details/52057418

TensorFlow 专栏收录该内容

13 篇文章

订阅专栏

本文通过展示样本标签和图像，验证了数据集的质量，并检查各类别数据是否均衡分布。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Problem 2

Let’s verify that the data still looks good. Displaying a sample of the labels and images from the ndarray. Hint: you can use matplotlib.pyplot.

import matplotlib as mpl

set_filename = train_folders[1] + '.pickle'


try:
    with open(set_filename, 'rb') as f:
        data = pickle.load(f)
except Exception as e:
    print('Unable to read data from', set_filename, ':', e)

data_small = data[::500]
for x in data_small:
    plt.imshow(x, cmap=mpl.cm.gray_r)
    plt.show()

Problem 3

Another check: we expect the data to be balanced across classes. Verify that.

for num in range(10): 
    set_filename = train_folders[num] + '.pickle'
    try:
        with open(set_filename, 'rb') as f:
            data = pickle.load(f)
    except Exception as e:
        print('Unable to read data from', set_filename, ':', e)
    print(data.shape[0])