Include tf.IsInf on Tensorflow Lite Operators

[JuanuMusic]

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux
• TensorFlow installed from (source or binary): binary
• TensorFlow version (or github SHA if from source): 2.11

Provide the text output from tflite_convert

<unknown>:0: error: failed while converting: 'main': 
Some ops in the model are custom ops, See instructions to implement custom ops: https://www.tensorflow.org/lite/guide/ops_custom 
Custom ops: IsInf
Details:
    tf.IsInf(tensor<?x21x?xf64>) -> (tensor<?x21x?xi1>) : {device = ""}
    tf.IsInf(tensor<?x33x?xf64>) -> (tensor<?x33x?xi1>) : {device = ""}

Standalone code to reproduce the issue Provide a reproducible test case that is the bare minimum necessary to generate the problem. If possible, please share a link to Colab/Jupyter/any notebook.

Also, please include a link to a GraphDef or the model if possible.

Any other info / logs

Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.

[synandi]

Hi @JuanuMusic, As mentioned in the error, as a workaround you can create your own custom implementation of an unsupported TensorFlow operator in TensorFlow Lite, known as a custom operator by following the instructions mentioned here. Thank you!

[JuanuMusic]

Hi! Yes, I know, but its also suggested to open an Issue to request to add. I think it's an important operator since there are some pre-procesdsing strategies that indeed require it.