tensorflow / tfjs

A WebGL accelerated JavaScript library for training and deploying ML models.
https://js.tensorflow.org
Apache License 2.0
18.46k stars 1.92k forks source link

Request to add support for Timestamp #7808

Open MikeyLev opened 1 year ago

MikeyLev commented 1 year ago

system information

TensorFlow.js version (you are using): 4.4.0 Are you willing to contribute it (Yes/No): Yes, if I'm able; I have no experience with the internals of TF.js Describe the feature and the current behavior/state.

Unsupported Ops: Timestamp

Hi TF.js team,

We have a TF SavedModel which we'd like to convert, using the tensorflowjs_converter, for use with TF.js.

When attempting to run the following code to convert the model... tensorflowjs_converter \ --input_format=tf_saved_model \ --output_format=tfjs_graph_model \ --signature_name=serving_default \ --saved_model_tags=serve \ /path/to/saved_model \ /path/to/tfjs_model ...we get the following error: raise ValueError('Unsupported Ops in the model before optimization\n' + ValueError: Unsupported Ops in the model before optimization Timestamp

Question: per the guidance at https://www.tensorflow.org/js/tutorials/conversion/import_saved_model#supported_operations, would it be possible to add support for this op to TensorFlow.js?

Thanks

gaikwadrahul8 commented 1 year ago

Hi, @MikeyLev

Thank you for bringing this issue to our attention and I have checked official documentation for Supported Tensorflow Ops for tfjs-converter and at the moment we do not support Timestamp Op if I'm not wrong

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