keras特征图可视化：visualize_feature_map_keras特征图可视化resnet101

版本：

(labelme) C:\Users\wym\Desktop\cjr\Centernet-Tensorflow2.0\TF2-CenterNet>

1、pip install keras

2、pip install tensorflow-cpu==2.2.0

img：

feature_map：

# coding: utf-8
from keras.applications.vgg19 import VGG19
from keras.preprocessing import image
from keras.applications.vgg19 import preprocess_input
from keras.models import Model
import numpy as np
import matplotlib.pyplot as plt
from pylab import *
 
def get_row_col(num_pic):
    squr = num_pic ** 0.5
    row = round(squr)
    col = row + 1 if squr - row > 0 else row
    return row, col
 
def visualize_feature_map(img_batch,img_prefix,num):
    feature_map = img_batch
    print(feature_map.shape)
 
    feature_map_combination = []
    plt.figure()
 
    num_pic = feature_map.shape[2]
    row, col = get_row_col(num_pic)
    print(num_pic)
    for i in range(0, num_pic):
        feature_map_split = feature_map[:, :, i]
        feature_map_combination.append(feature_map_split)
        plt.subplot(row, col, i + 1)
        plt.imshow(feature_map_split)
        # plt.pause(1)
        axis('off')#关闭坐标轴
 
    plt.savefig('./result/img_prefix{}_{}feature_map.png'.format(img_prefix,num))
    plt.show()
    plt.pause(1)
 
    # 各个特征图按1：1 叠加
    feature_map_sum = sum(ele for ele in feature_map_combination)
    plt.imshow(feature_map_sum)
    plt.pause(1)
    plt.savefig("./result/img_prefix{}_{}feature_map_sum.png".format(img_prefix,num))
 
 
if __name__ == "__main__":
 
    base_model = VGG19(weights='imagenet', include_top=False)
    for index in range(1,6):
    # model = Model(inputs=base_model.input, outputs=base_model.get_layer('block1_pool').output)
    # model = Model(inputs=base_model.input, outputs=base_model.get_layer('block2_pool').output)
    # model = Model(inputs=base_model.input, outputs=base_model.get_layer('block3_pool').output)
    # model = Model(inputs=base_model.input, outputs=base_model.get_layer('block4_pool').output)
        model = Model(inputs=base_model.input, outputs=base_model.get_layer('block{}_pool'.format(index)).output)
        img_path = '3.jpg'
        img_pathPrefix=img_path.split(".")[0]
        img = image.load_img(img_path)
        x = image.img_to_array(img)
        x = np.expand_dims(x, axis=0)
        x = preprocess_input(x)
        block_pool_features = model.predict(x)
        print(block_pool_features.shape)
 
        feature = block_pool_features.reshape(block_pool_features.shape[1:])
        visualize_feature_map(feature,img_pathPrefix,index,)

如果觉得文章错，可以扫码关注下下哈，CSDN里可能更新不那么及时，公众号里面会每天更新干货知识。

参考文献：

卷积神经网络特征图可视化（自定义网络和VGG网络）_-牧野-的博客-CSDN博客_特征图可视化