Error while loading Movinet fine tuned model after converting it into tfjs file

[FrIdAy-101-max]

This template is for miscellaneous issues not covered by the other issue categories.

For questions on how to work with TensorFlow.js, or support for problems that are not verified bugs in TensorFlow.js, please go to StackOverflow.

Uncaught n Error: Unknown layer: MovinetClassifier. This may be due to one of the following reasons:

1. The layer is defined in Python, in which case it needs to be ported to TensorFlow.js or your JavaScript code.
2. The custom layer is defined in JavaScript, but is not registered properly with tf.serialization.registerClass().

[gaikwadrahul8]

Hi, @FrIdAy-101-max

Thank you for reporting this issue, if possible could you please help us with your code and error log to replicate the same issue from our end ?

At the moment, it seems like in your code you're using such layer which does not support in TFJs yet if that is the case then this issue will be considered as feature request but to cross verify please help us with code snippet and error log. Thank you!

[FrIdAy-101-max]

Its seems like when the Library is present in Python as which can be called and I wonder why can't be it added and if there are any materials that are there to convert tfjs model with customization layer please provide it.

[gaikwadrahul8]

Hi, @FrIdAy-101-max

Could you please help us with your codepen/code example or your Github repo link where you're getting below error message so we'll try to replicate the same issue from our end so we'll considered this issue as feature request ? Thank you!

Uncaught n Error: Unknown layer: MovinetClassifier. This may be due to one of the following reasons:

The layer is defined in Python, in which case it needs to be ported to TensorFlow.js or your JavaScript code.
The custom layer is defined in JavaScript, but is not registered properly with tf.serialization.registerClass(). 

[mattsoulanille]

If you only need to run model inference, you can try converting to a TFJS graph model instead of a layers model. That will decompose the model into lower level ops instead of layers, which are more likely to be supported.

[github-actions]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

[github-actions]

This issue was closed due to lack of activity after being marked stale for past 7 days.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No