I am trying to convert an ONNX model to Keras, but when I call the conversion function I receive the following error message "TypeError: unhashable type: 'google._upb._message.RepeatedScalarContainer'"
INFO:onnx2keras:Converter is called.
DEBUG:onnx2keras:List input shapes:
DEBUG:onnx2keras:None
DEBUG:onnx2keras:List inputs:
DEBUG:onnx2keras:Input 0 -> image.
DEBUG:onnx2keras:List outputs:
DEBUG:onnx2keras:Output 0 -> TFLITE2ONNX_Quant_scores_dequantized.
DEBUG:onnx2keras:Gathering weights to dictionary.
Traceback (most recent call last):
File "/home/kurpav00/anaconda3/envs/tf/lib/python3.9/site-packages/onnx2keras-0.0.24-py3.9.egg/onnx2keras/converter.py", line 86, in onnx_to_keras
weights[onnx_extracted_weights_name] = numpy_helper.to_array(onnx_w)
TypeError: unhashable type: 'google._upb._message.RepeatedScalarContainer'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/kurpav00/anaconda3/envs/tf/lib/python3.9/site-packages/onnx2keras-0.0.24-py3.9.egg/onnx2keras/converter.py", line 88, in onnx_to_keras
onnx_extracted_weights_name = onnx_w.ListFields()[3][1]
IndexError: list index out of range
It seems to be the same error as in #23 although it is claimed to be fixed. Using "name_policy='renumerate'" also does not help.
I am trying to convert an ONNX model to Keras, but when I call the conversion function I receive the following error message "TypeError: unhashable type: 'google._upb._message.RepeatedScalarContainer'"
Results in:
It seems to be the same error as in #23 although it is claimed to be fixed. Using "name_policy='renumerate'" also does not help.
Here is the ONNX model used: model.zip