def test_guided_backprop(vgg):
# load the vgg into the deoxys model
deo = Model(vgg)
# load an real image
img = load_image('tests/img/cat.jpg')
layer_list = [layer.name for layer in vgg.layers[1:4]]
for i, layer in enumerate(layer_list):
outs = deprocess_image(deo.guided_backprop(layer, img, mode='mean')[0])
# fig, axes = plt.subplots(nrow, ncol)
# for ax in axes.flatten():
# ax.axis('off')
# for i, layer in enumerate(layer_list):
# outs = deprocess_image(deo.deconv(layer, img)[0])
# axes[i//5, i % 5].imshow(outs)
# axes[i//5, i % 5].set_title(layer)
# plt.suptitle('Deconvnet Map')
# plt.show()
# input('Press ENTER to continue...')
fig, axes = plt.subplots(nrow, ncol)
for ax in axes.flatten():
ax.axis('off')
for i, layer in enumerate(layer_list):
outs = deprocess_image(deo.guided_backprop(layer, img)[0])
axes[i // 5, i % 5].imshow(outs)
axes[i // 5, i % 5].set_title(layer)
plt.suptitle('Guided Backprop Map')
plt.show()
input('Press ENTER to continue...')
# fig, axes = plt.subplots(nrow, ncol)
# for ax in axes.flatten():
# ax.axis('off')
# for i, layer in enumerate(layer_list):
# outs = deprocess_image(deo.gradient_map(
# layer, epochs=5, step_size=2)[0])
# axes[i//5, i % 5].imshow(outs)
# axes[i//5, i % 5].set_title(layer)
# plt.suptitle('Gradients Map')