Core API Vanilla Gradients example not working

[aish-where-ya]

Hello,
I was trying to implement Vanilla Gradient Core API for my deep learning model and the tutorial did not work for me. I was implementing it on Google Colab.
This is my code -

from tf_explain.core.vanilla_gradients import VanillaGradients
img = image.load_img(sample_image2, target_size=(224, 224))
img = image.img_to_array(img)
data = ([img], None)
class_index = 1
vg_explainer = VanillaGradients()
grid = vg_explainer.explain(data, model, 1)
plt.imshow(grid)

I am using a Densenet201 model. Following is the traceback that I got -

---------------------------------------------------------------------------

AttributeError                            Traceback (most recent call last)

<ipython-input-34-c2b31b45db83> in <module>()
      5 class_index = 1
      6 explainer = VanillaGradients()
----> 7 grid = explainer.explain(data, model, 1)
      8 plt.imshow(grid)

8 frames

/usr/local/lib/python3.6/dist-packages/tf_explain/core/vanilla_gradients.py in explain(self, validation_data, model, class_index)
     33         images, _ = validation_data
     34 
---> 35         gradients = self.compute_gradients(images, model, class_index)
     36 
     37         grayscale_gradients = transform_to_normalized_grayscale(

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    578         xla_context.Exit()
    579     else:
--> 580       result = self._call(*args, **kwds)
    581 
    582     if tracing_count == self._get_tracing_count():

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    616       # In this case we have not created variables on the first call. So we can
    617       # run the first trace but we should fail if variables are created.
--> 618       results = self._stateful_fn(*args, **kwds)
    619       if self._created_variables:
    620         raise ValueError("Creating variables on a non-first call to a function"

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
   2417     """Calls a graph function specialized to the inputs."""
   2418     with self._lock:
-> 2419       graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
   2420     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   2421 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   2775 
   2776       self._function_cache.missed.add(call_context_key)
-> 2777       graph_function = self._create_graph_function(args, kwargs)
   2778       self._function_cache.primary[cache_key] = graph_function
   2779       return graph_function, args, kwargs

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   2665             arg_names=arg_names,
   2666             override_flat_arg_shapes=override_flat_arg_shapes,
-> 2667             capture_by_value=self._capture_by_value),
   2668         self._function_attributes,
   2669         # Tell the ConcreteFunction to clean up its graph once it goes out of

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    979         _, original_func = tf_decorator.unwrap(python_func)
    980 
--> 981       func_outputs = python_func(*func_args, **func_kwargs)
    982 
    983       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    439         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    440         # the function a weak reference to itself to avoid a reference cycle.
--> 441         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    442     weak_wrapped_fn = weakref.ref(wrapped_fn)
    443 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    966           except Exception as e:  # pylint:disable=broad-except
    967             if hasattr(e, "ag_error_metadata"):
--> 968               raise e.ag_error_metadata.to_exception(e)
    969             else:
    970               raise

AttributeError: in user code:

    /usr/local/lib/python3.6/dist-packages/tf_explain/core/vanilla_gradients.py:61 compute_gradients  *
        expected_output = tf.one_hot([class_index] * images.shape[0], num_classes)

    AttributeError: 'list' object has no attribute 'shape'

Upon checking vanilla_gradients.py , the function compute_gradients(images, model, class_index) expects the first argument to be -
images (numpy.ndarray): 4D-Tensor of images with shape (batch_size, H, W, 3)

Please could you help me solve this issue.

[RaphaelMeudec]

@aish-where-ya I guess you might want to try data = (np.array([img]), None