Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error Converting Existing Model to Tennsorflow.js Web Format #69

Open
roshanbiswanath opened this issue Sep 16, 2023 · 0 comments
Open

Comments

@roshanbiswanath
Copy link

I was trying to convert the SavedModel to Web Format for running in Tensorflow.js but encountered the error signature not found.
Ran in CMD: tensorflowjs_converter --input_format=tf_saved_model bodyTrack result
Followed This Article: https://www.tensorflow.org/js/tutorials/conversion/import_saved_model

Error Output:
Traceback (most recent call last): File "<frozen runpy>", line 198, in _run_module_as_main File "<frozen runpy>", line 88, in _run_code File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Scripts\tensorflowjs_converter.exe\__main__.py", line 7, in <module> File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\converter.py", line 813, in pip_main main([' '.join(sys.argv[1:])]) File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\converter.py", line 817, in main convert(argv[0].split(' ')) File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\converter.py", line 803, in convert _dispatch_converter(input_format, output_format, args, quantization_dtype_map, File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\converter.py", line 523, in _dispatch_converter tf_saved_model_conversion_v2.convert_tf_saved_model( File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\tf_saved_model_conversion_v2.py", line 766, in convert_tf_saved_model _convert_tf_saved_model(output_dir, saved_model_dir=saved_model_dir, File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\tf_saved_model_conversion_v2.py", line 606, in _convert_tf_saved_model saved_model_sigature = _find_signature(saved_model_dir, saved_model_tags, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\groot\Documents\Biswanath\Pose Estimation\metrabsExport\env\Lib\site-packages\tensorflowjs\converters\tf_saved_model_conversion_v2.py", line 549, in _find_signature raise ValueError('Signature "%s" does not exist in the saved model' ValueError: Signature "serving_default" does not exist in the saved model

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant