[tfjs-converter] Unsupported Ops: PartitionedCall, BitwiseAnd

[josephrocca]

System information

• TensorFlow.js version (you are using): tensorflowjs_converter --version = 3.13.0
• Are you willing to contribute it (Yes/No): Yes, where possible.

Here's the command I ran:

tensorflowjs_converter --input_format=tf_saved_model --output_format=tfjs_graph_model /content/saved_model /content/tfjs_model

And here's the full error:

Traceback (most recent call last):
  File "/usr/local/bin/tensorflowjs_converter", line 8, in <module>
    sys.exit(pip_main())
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/converter.py", line 813, in pip_main
    main([' '.join(sys.argv[1:])])
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/converter.py", line 817, in main
    convert(argv[0].split(' '))
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/converter.py", line 804, in convert
    weight_shard_size_bytes, metadata_map)
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/converter.py", line 533, in _dispatch_converter
    metadata=metadata_map)
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/tf_saved_model_conversion_v2.py", line 771, in convert_tf_saved_model
    metadata=metadata)
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/tf_saved_model_conversion_v2.py", line 724, in _convert_tf_saved_model
    metadata=metadata)
  File "/usr/local/lib/python3.7/dist-packages/tensorflowjs/converters/tf_saved_model_conversion_v2.py", line 157, in optimize_graph
    ', '.join(unsupported))
ValueError: Unsupported Ops in the model before optimization
PartitionedCall, BitwiseAnd

[gaikwadrahul8]

Hi, @josephrocca

Apologize for the delayed response and we are re-visiting our older feature requests and checking whether those feature requests implemented or not as of now and it seems like we haven't implemented these Ops yet so May I know are you still looking for these Ops in TFJs ?

If someone wants to contribute for this feature then you're always welcome and please feel free to do it and please refer these links Ref-1, Ref-2 . Thank you!

[josephrocca]

Yep, still need them.