CNN神经网络猫狗分类经典案例，深度学习过程中间层激活特征图可视化

爱被打了一巴掌 2023-06-23 10:52 12阅读 0赞

# AI：CNN神经网络猫狗分类经典案例，深度学习过程中间层激活特征图可视化 #

基于前文 [https://zhangphil.blog.csdn.net/article/details/103581736][https_zhangphil.blog.csdn.net_article_details_103581736] ，这一次把前文神经网络在深度学习过程中，中间层的每一层激活的特征图可视化展现出来（中间层激活可视化），

取前8层

# 深度学习过程中每一层的神经网络激活图。
    def visible():
        model = load_model(model_file_name)
    
        layer_outputs = [layer.output for layer in model.layers[:8]]
        activation_model = models.Model(inputs=model.input, outputs=layer_outputs)
    
        img_path = './data/test/cat/cat.4041.jpg'
        img = image.load_img(img_path, target_size=(150, 150))
        img_tensor = image.img_to_array(img)
        img_tensor = img_tensor / 255
        img_tensor = np.expand_dims(img_tensor, axis=0)
    
        activations = activation_model.predict(img_tensor)
        for k in range(len(activations)):
            first_layer_activation = activations[k]
            print(first_layer_activation.shape)
    
            col = 8
            plt.figure(figsize=(50, 50))
            for i in range(first_layer_activation.shape[3]):
                # col列。
                plt.subplot((first_layer_activation.shape[3] / col) + 1, col, i + 1)
                plt.imshow(first_layer_activation[0, :, :, i], cmap='viridis')
            #保存图片。
            plt.savefig(str(k) + ".jpg", dpi=100)
            plt.show()

第一层（0）的激活图可视化：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70][]

第2层（1）的激活图可视化：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70 1][]

最后一层

第8层（7）神经网络激活图：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70 2][]

可以看到，随着深度学习往纵深发展，神经网络学习到的知识越来越抽象。层数加深，人类的直观越来越难以理解。

[https_zhangphil.blog.csdn.net_article_details_103581736]: https://zhangphil.blog.csdn.net/article/details/103581736
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20191218160956215.jpg?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20191218161211823.jpg?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20191218161351160.jpg?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly96aGFuZ3BoaWwuYmxvZy5jc2RuLm5ldA==,size_16,color_FFFFFF,t_70