Saliency_1.py

from vis.visualization import visualize_saliency
from vis.utils import utils
from keras import activations
#read the image
image = io.imread('car.jpeg')
#plot the image
io.imshow(image)

saliency_2.py

# Utility to search for layer index by name. 
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, 'predictions')

# Swap softmax with linear
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)

#generating saliency map with unguided backprop
grads1 = visualize_saliency(model, layer_idx,filter_indices=None,seed_input=image)
#plotting the unguided saliency map
plt.imshow(grads1,cmap='jet')

saliency_3.py

#generating saliency map with guided backprop
grads2 =  visualize_saliency(model, layer_idx,filter_indices=None,seed_input=image,backprop_modifier='guided')
#plotting the saliency map as heatmap
plt.imshow(grads2,cmap='jet')