def test_should_generate_ponderated_output(mocker):
mocker.patch(
"tf_explain.core.grad_cam.GradCAM.ponderate_output",
side_effect=[
mocker.sentinel.ponderated_1, mocker.sentinel.ponderated_2
],
)
expected_output = [
mocker.sentinel.ponderated_1, mocker.sentinel.ponderated_2
]
outputs = [mocker.sentinel.output_1, mocker.sentinel.output_2]
grads = [mocker.sentinel.grads_1, mocker.sentinel.grads_2]
output = GradCAM.generate_ponderated_output(outputs, grads)
for real, expected in zip(output, expected_output):
assert real == expected
def explain(self,
model_input,
model,
layer_name,
class_index,
colormap=cv2.COLORMAP_INFERNO):
"""
Compute GradCAM for a specific class index.
Args:
model_input (tf.tensor): Data to perform the evaluation on.
model (tf.keras.Model): tf.keras model to inspect
layer_name (str): Targeted layer for GradCAM
class_index (int, None): Index of targeted class
colormap (int): Used in parent method signature, but ignored here
Returns:
tf.cams: The gradcams
"""
outputs, guided_grads, predictions = FEGradCAM.get_gradients_and_filters(
model, model_input, layer_name, class_index)
cams = GradCAM.generate_ponderated_output(outputs, guided_grads)
input_min = tf.reduce_min(model_input)
input_max = tf.reduce_max(model_input)
# Need to move input image into the 0-255 range
adjust_sum = 0.0
adjust_factor = 1.0
if input_min < 0:
adjust_sum = 1.0
adjust_factor /= 2.0
if input_max <= 1:
adjust_factor *= 255.0
heatmaps = [
heatmap_display(cam.numpy(),
(inp.numpy() + adjust_sum) * adjust_factor,
colormap) for cam, inp in zip(cams, model_input)
]
return heatmaps, predictions
