原图：
Keras代码：
from keras.models import Sequentialfrom keras.layers.convolutional import Convolution2D,MaxPooling2D,AveragePooling2Dfrom keras.layers import Activationimport cv2import osimport shutilimport numpy as npimport 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：
