Hi, I am trying to convert an ONNX model to tflite format but I got the following error:
The command I used:
python -m onnx2tflite --weights "/content/bob.paper.tbiom2023_edgeface/edgeface.onnx" --outpath "/content/bob.paper.tbiom2023_edgeface/checkpoints" --formats "tflite"
Error:
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/content/onnx2tflite/onnx2tflite/main.py", line 41, in
run()
File "/content/onnx2tflite/onnx2tflite/main.py", line 24, in run
onnx_converter(
File "/content/onnx2tflite/onnx2tflite/converter.py", line 44, in onnx_converter
keras_model, input_layout, output_layout = keras_builder(model_proto, native_groupconv)
File "/content/onnx2tflite/onnx2tflite/components/builder.py", line 43, in keras_builder
raise KeyError(f"{op_name} not implemented yet")
KeyError: 'LayerNormalization not implemented yet'
Hi, I am trying to convert an ONNX model to tflite format but I got the following error:
The command I used: python -m onnx2tflite --weights "/content/bob.paper.tbiom2023_edgeface/edgeface.onnx" --outpath "/content/bob.paper.tbiom2023_edgeface/checkpoints" --formats "tflite"
Error: Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/content/onnx2tflite/onnx2tflite/main.py", line 41, in
run()
File "/content/onnx2tflite/onnx2tflite/main.py", line 24, in run
onnx_converter(
File "/content/onnx2tflite/onnx2tflite/converter.py", line 44, in onnx_converter
keras_model, input_layout, output_layout = keras_builder(model_proto, native_groupconv)
File "/content/onnx2tflite/onnx2tflite/components/builder.py", line 43, in keras_builder
raise KeyError(f"{op_name} not implemented yet")
KeyError: 'LayerNormalization not implemented yet'
Any help on this would be highly appreciated