Unable to do "out-of-the-box" inference using the CenterNet Hourglass104 Keypoints Model - Object detection

• [ X] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• [ X] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [ X] I checked to make sure that this issue has not already been filed.

The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/inference_tf2_colab.ipynb

Describe the bug

On request opening a fresh issues reference to #9507

Steps to reproduce

Changed models dictionary to centernet_hourglass104_512x512_kpts_coco17_tpu-32 to download and extract the correct model.

Pick up the config from this location for the above model
pipeline_config = .../research/object_detection/configs/tf2/centernet_hourglass104_512x512_kpts_coco17_tpu-32.config

Changes made in the above config file -
line 44 --> keypoint_label_map_path: ".../research/object_detection/data/face_person_with_keypoints_label_map.pbtxt"
line 60 --> keypoint_class_name: "Person"
line 241 --> (in eval_cong) class_label: "Person" as suggested in #9507

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 16.04
• TensorFlow version (use command below): v2.2.0-rc4-8-g2b96f3662b 2.2.0
• Python version: 3.6.10

Expected behavior

Run the test image successfully and return predictions.

Code from colab

#Testing on image from test_images folder
image_dir = '.../research/object_detection/test_images/'
image_path = os.path.join(image_dir, 'image2.jpg')
image_np = load_image_into_numpy_array(image_path)

input_tensor = tf.convert_to_tensor(
    np.expand_dims(image_np, 0), dtype=tf.float32)
detections, predictions_dict, shapes = detect_fn(input_tensor)

Error:

TypeError                                 Traceback (most recent call last)
<ipython-input-26-53d3633f8f72> in <module>
     13 input_tensor = tf.convert_to_tensor(
     14     np.expand_dims(image_np, 0), dtype=tf.float32)
---> 15 detections, predictions_dict, shapes = detect_fn(input_tensor)
     16 
     17 label_id_offset = 1

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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():

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    625       # This is the first call of __call__, so we have to initialize.
    626       initializers = []
--> 627       self._initialize(args, kwds, add_initializers_to=initializers)
    628     finally:
    629       # At this point we know that the initialization is complete (or less

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    504     self._concrete_stateful_fn = (
    505         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 506             *args, **kwds))
    507 
    508     def invalid_creator_scope(*unused_args, **unused_kwds):

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2444       args, kwargs = None, None
   2445     with self._lock:
-> 2446       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2447     return graph_function
   2448 

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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,

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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 

~/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-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

TypeError: in user code:

    <ipython-input-17-04098793256e>:27 detect_fn  *
        detections = model.postprocess(prediction_dict, shapes)
    /home/ubuntu/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/object_detection/meta_architectures/center_net_meta_arch.py:2945 postprocess  *
        keypoints, keypoint_scores = (
    /home/ubuntu/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/object_detection/meta_architectures/center_net_meta_arch.py:1086 convert_strided_predictions_to_normalized_keypoints  *
        keypoint_coords_normalized = tf.map_fn(

    TypeError: map_fn() got an unexpected keyword argument 'fn_output_signature'

Let me know if something is missing.