Skip to content

Instantly share code, notes, and snippets.

Last active April 18, 2019 17:58
What would you like to do?
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
# 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
#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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment