'BatchNormalization' object has no attribute 'get_input_at'

[DenSandu]

Hi, I cloned the repo using git clone [git@github.com](mailto:git@github.com):PlasmaControl/keras2c.git --branch v1.0.2 but

1. I got this error raise

NotImplementedError(
        "numpy() is only available when eager execution is enabled.")

which I solved by changing the keras2c_main.py to enable

tf.compat.v1.enable_eager_execution()

2. I got another error which says:

  File ".../keras2c/keras2c/io_parsing.py", line 59, in get_layer_num_io
    layer.get_input_at(num_inputs)
    ^^^^^^^^^^^^^^^^^^
AttributeError: 'BatchNormalization' object has no attribute 'get_input_at'

[github-actions]

Message that will be displayed on users' first issue

[DenSandu]

I also tried from Windows and I get:

Traceback (most recent call last):
  File "C:\Local\Programs\Python\Python39\lib\runpy.py", line 197, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\AppData\Local\Programs\Python\Python39\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "C:\keras2c\keras2c\__main__.py", line 55, in <module>
    main(sys.argv[1:])
  File "C:\keras2c\keras2c\__main__.py", line 51, in main
    k2c(args.model_path, args.function_name, malloc, num_tests)
  File "C:\keras2c\keras2c\keras2c_main.py", line 208, in k2c
    model = keras.models.load_model(model, compile=False)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\saving\save.py", line 201, in load_model
    return hdf5_format.load_model_from_hdf5(filepath, custom_objects,
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\saving\hdf5_format.py", line 180, in load_model_from_hdf5
    model = model_config_lib.model_from_config(model_config,
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\saving\model_config.py", line 59, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\layers\serialization.py", line 159, in deserialize
    return generic_utils.deserialize_keras_object(
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\utils\generic_utils.py", line 668, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\engine\functional.py", line 668, in from_config
    input_tensors, output_tensors, created_layers = reconstruct_from_config(
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\engine\functional.py", line 1279, in reconstruct_from_config
    process_layer(layer_data)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\engine\functional.py", line 1261, in process_layer
    layer = deserialize_layer(layer_data, custom_objects=custom_objects)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\layers\serialization.py", line 159, in deserialize
    return generic_utils.deserialize_keras_object(
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\utils\generic_utils.py", line 675, in deserialize_keras_object
    deserialized_obj = cls.from_config(cls_config)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 740, in from_config
    return cls(**config)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\layers\pooling.py", line 1023, in __init__
    super(GlobalPooling2D, self).__init__(**kwargs)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\training\tracking\base.py", line 522, in _method_wrapper
    result = method(self, *args, **kwargs)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer_v1.py", line 159, in __init__
    generic_utils.validate_kwargs(kwargs, allowed_kwargs)
  File "C:\keras2c\venv\lib\site-packages\tensorflow\python\keras\utils\generic_utils.py", line 1137, in validate_kwargs
    raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'keepdims')

[ashtoncbuci]

Is someone going to work on this issue? I am running into the same issue except for a dense layer instead of a batch normalization layer:

File ~/keras2c/keras2c/io_parsing.py:59 in get_layer_num_io
layer.get_input_at(num_inputs)

AttributeError: 'Dense' object has no attribute 'get_input_at'