卷积神经网络的特征图可视化

原图：

Keras代码：

from keras.models  import Sequential
from keras.layers.convolutional import Convolution2D,MaxPooling2D,AveragePooling2D
from keras.layers import Activation
import cv2
import os
import shutil
import numpy as np
import matplotlib.pyplot as plt

#网络模型
def create_model():
    model = Sequential()
    #输入 img.shape = (28，28，3)

    #第一层卷积
    model.add(Convolution2D(9,(5,5),padding='same',strides=(1,1),input_shape=img.shape)) #(1, 24, 24, 9)
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))

    # # 第二层卷积
    # model.add(Convolution2D(9,(5,5),padding='same',strides=(2,2)))
    # model.add(Activation('relu'))
    # model.add(MaxPooling2D(pool_size=(2,2)))
    return model

#保存特征图
def save_conv_img(conv_img):
    feature_maps = np.squeeze(conv_img,axis=0)
    img_num = feature_maps.shape[2]
    all_feature_maps = []
    for i in range(0,img_num):
        single_feature_map = feature_maps[:,:,i]
        all_feature_maps.append(single_feature_map)
        plt.imshow(single_feature_map)
        plt.savefig('./feature_map/'+'feature_{}'.format(i))
        sum_feature_map = sum(feature_map for feature_map in all_feature_maps)
        plt.imshow(sum_feature_map)
        plt.savefig("./feature_map/feature_map_sum.png")

def create_dir():
    if not os.path.exists('./feature_map'):
        os.mkdir('./feature_map')
    else:
        shutil.rmtree('./feature_map')
        os.mkdir('./feature_map')

if __name__ =='__main__':
    img = cv2.imread('b0.jpg')
    print(img.shape)
    create_dir()
    model = create_model()

    img_batch = np.expand_dims(img,axis=0)

    conv_img = model.predict(img_batch) #predict()的参数是需要四维的
    save_conv_img(conv_img)

经过第一层卷积后，得到的特征图为：

因为第一层卷积设置了一共有9个卷积核，所以对应就会有9张特征图

而网络的输出则是9张特征图合在一起，形成总的特征图：