def test__call__if_smoothing_is_active(model):
saliency = Saliency(model)
result = saliency(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
smooth_samples=1)
assert result.shape == (1, 8, 8)
result = saliency(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
smooth_samples=2)
assert result.shape == (1, 8, 8)
def test__call__with_mutiple_outputs_model_but_losses_is_too_many(
multiple_outputs_model):
activation_maximization = ActivationMaximization(multiple_outputs_model)
with pytest.raises(ValueError):
activation_maximization([
CategoricalScore(1, 2),
CategoricalScore(1, 2),
CategoricalScore(1, 2)
],
steps=1,
input_modifiers=None)
def test__call__if_penultimate_layer_is_no_exist_name(model):
scorecam = ScoreCAM(model)
with pytest.raises(ValueError):
scorecam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
penultimate_layer='hoge',
max_N=3)
def test__call__with_mutiple_inputs_model(multiple_inputs_model):
activation_maximization = ActivationMaximization(multiple_inputs_model)
result = activation_maximization(CategoricalScore(1, 2),
steps=1,
input_modifiers=None)
assert result[0].shape == (1, 8, 8, 3)
assert result[1].shape == (1, 10, 10, 3)
def test__call__if_penultimate_layer_is_None(model):
scorecam = ScoreCAM(model)
result = scorecam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
penultimate_layer=None,
max_N=3)
assert result.shape == (1, 8, 8)
def test__call__if_expand_cam_is_False(model):
scorecam = ScoreCAM(model)
result = scorecam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
expand_cam=False,
max_N=3)
assert result.shape == (1, 6, 6)
def test__call__if_seed_input_shape_is_invalid(model):
gradcam = Gradcam(model)
try:
gradcam(CategoricalScore(1, 2), np.random.sample((8, )))
assert False
except (ValueError, tf.errors.InvalidArgumentError):
# TF became to raise InvalidArgumentError from ver.2.0.2.
assert True
def test__call__if_model_has_multiple_inputs(multiple_inputs_model):
saliency = Saliency(multiple_inputs_model)
result = saliency(
CategoricalScore(1, 2),
[np.random.sample((1, 8, 8, 3)),
np.random.sample((1, 10, 10, 3))])
assert len(result) == 2
assert result[0].shape == (1, 8, 8)
assert result[1].shape == (1, 10, 10)
def test__call__if_model_has_multiple_io(multiple_io_model):
gradcam = Gradcam(multiple_io_model)
result = gradcam(
[CategoricalScore(1, 2), lambda x: x],
[np.random.sample((1, 8, 8, 3)),
np.random.sample((1, 10, 10, 3))])
assert len(result) == 2
assert result[0].shape == (1, 8, 8)
assert result[1].shape == (1, 10, 10)
def test__call__if_expand_cam_is_False_and_model_has_multiple_inputs(
multiple_inputs_model):
gradcam = Gradcam(multiple_inputs_model)
result = gradcam(
CategoricalScore(1, 2),
[np.random.sample((1, 8, 8, 3)),
np.random.sample((1, 10, 10, 3))],
expand_cam=False)
assert result.shape == (1, 8, 8)
def test__call__if_model_has_multiple_io_when_batchsize_is_2(
multiple_io_model):
gradcam = Gradcam(multiple_io_model)
result = gradcam(
[CategoricalScore([1, 0], 2), lambda x: x],
[np.random.sample((2, 8, 8, 3)),
np.random.sample((2, 10, 10, 3))])
assert len(result) == 2
assert result[0].shape == (2, 8, 8)
assert result[1].shape == (2, 10, 10)
def test__call__with_callback(model):
activation_maximization = ActivationMaximization(model)
mock = MockCallback()
result = activation_maximization(CategoricalScore(1, 2),
steps=1,
callbacks=mock)
assert result.shape == (1, 8, 8, 3)
assert mock.on_begin_was_called
assert mock.on_call_was_called
assert mock.on_end_was_called
def test__call__if_model_has_multiple_inputs(multiple_inputs_model):
scorecam = ScoreCAM(multiple_inputs_model)
result = scorecam(
CategoricalScore(1, 2),
[np.random.sample((1, 8, 8, 3)),
np.random.sample((1, 10, 10, 3))],
max_N=3)
assert len(result) == 2
assert result[0].shape == (1, 8, 8)
assert result[1].shape == (1, 10, 10)
def test__call__with_mutiple_outputs_model(multiple_outputs_model):
activation_maximization = ActivationMaximization(multiple_outputs_model)
result = activation_maximization(CategoricalScore(1, 2),
steps=1,
input_modifiers=None)
assert result.shape == (1, 8, 8, 3)
activation_maximization = ActivationMaximization(multiple_outputs_model)
result = activation_maximization(
[CategoricalScore(1, 2),
CategoricalScore(1, 2)],
steps=1,
input_modifiers=None)
assert result.shape == (1, 8, 8, 3)
activation_maximization = ActivationMaximization(multiple_outputs_model)
result = activation_maximization(
[CategoricalScore(1, 2),
CategoricalScore(1, 2)],
steps=1,
input_modifiers=None,
regularizers=[TotalVariation(10.), L2Norm(10.)])
assert result.shape == (1, 8, 8, 3)
def test__call__if_expand_cam_is_False(model):
gradcam = Gradcam(model)
result = gradcam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
expand_cam=False)
assert result.shape == (1, 6, 6)
def test__call__if_model_has_multiple_outputs(multiple_outputs_model):
gradcam = Gradcam(multiple_outputs_model)
result = gradcam([CategoricalScore(1, 2), lambda x: x],
np.random.sample((1, 8, 8, 3)))
assert result.shape == (1, 8, 8)
def test__call__if_model_has_only_dense_layer(dense_model):
gradcam = Gradcam(dense_model)
with pytest.raises(ValueError):
gradcam(CategoricalScore(1, 2), np.random.sample((1, 3)))
def test__call__with_seed_input(model):
activation_maximization = ActivationMaximization(model)
result = activation_maximization(CategoricalScore(1, 2),
seed_input=np.random.sample((8, 8, 3)),
steps=1)
assert result.shape == (1, 8, 8, 3)
def test__call__if_seed_input_has_not_batch_dim(model):
scorecam = ScoreCAM(model)
result = scorecam(CategoricalScore(1, 2),
np.random.sample((8, 8, 3)),
max_N=3)
assert result.shape == (1, 8, 8)
def test__call__with_gradient_modifier(model):
activation_maximization = ActivationMaximization(model)
result = activation_maximization(CategoricalScore(1, 2),
steps=1,
gradient_modifier=lambda x: x)
assert result.shape == (1, 8, 8, 3)
def test__call__(model):
gradcam = Gradcam(model)
result = gradcam(CategoricalScore(1, 2), np.random.sample((1, 8, 8, 3)))
assert result.shape == (1, 8, 8)
def test__call__if_model_has_multiple_outputs(multiple_outputs_model):
scorecam = ScoreCAM(multiple_outputs_model)
result = scorecam([CategoricalScore(1, 2), lambda x: x],
np.random.sample((1, 8, 8, 3)),
max_N=3)
assert result.shape == (1, 8, 8)
def test__call__(model):
activation_maximization = ActivationMaximization(model)
result = activation_maximization(CategoricalScore(1, 2), steps=1)
assert result.shape == (1, 8, 8, 3)
def test__call__(model):
scorecam = ScoreCAM(model)
result = scorecam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
max_N=3)
assert result.shape == (1, 8, 8)
def test__call__if_seed_input_is_None(model):
gradcam = Gradcam(model)
with pytest.raises(ValueError):
gradcam(CategoricalScore(1, 2), None)
def test__call__if_penultimate_layer_is_no_exist_index(model):
gradcam = Gradcam(model)
with pytest.raises(ValueError):
gradcam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
penultimate_layer=100000)
def test__call__if_seed_input_has_not_batch_dim(model):
gradcam = Gradcam(model)
result = gradcam(CategoricalScore(1, 2), np.random.sample((8, 8, 3)))
assert result.shape == (1, 8, 8)
def test__call__if_loss_is_list(model):
activation_maximization = ActivationMaximization(model)
result = activation_maximization([CategoricalScore(1, 2)], steps=1)
assert result.shape == (1, 8, 8, 3)
def test__call__if_penultimate_layer_is_None(model):
gradcam = Gradcam(model)
result = gradcam(CategoricalScore(1, 2),
np.random.sample((1, 8, 8, 3)),
penultimate_layer=None)
assert result.shape == (1, 8, 8)
def test__call__if_seed_input_is_None(model):
scorecam = ScoreCAM(model)
with pytest.raises(ValueError):
scorecam(CategoricalScore(1, 2), None, max_N=3)