from keras.applications.vgg16 import VGG16, preprocess_input
from keras.preprocessing.image import load_img,img_to_array
from keras.models import Model
import matplotlib.pyplot as plt
import numpy as np

model = VGG16()

layer_dict = dict([(layer.name, layer) for layer in model.layers])

layer_name = 'block1_conv2'

model = Model(inputs=model.inputs, outputs=layer_dict[layer_name].output)

# Perpare the image
image = load_img('tiger.jpg', target_size=(224, 224))
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)

# Apply the model to the image
feature_maps = model.predict(image)

square = 8
index = 1
for _ in range(square):
	for _ in range(square):

		ax = plt.subplot(square, square, index)
		ax.set_xticks([])
		ax.set_yticks([])

		plt.imshow(feature_maps[0, :, :, index-1], cmap='viridis')
		index += 1

plt.show()