Generate report for troubleshooting the quantized model

[reuvenperetz]

Pull Request Description:

Add functions for generating a report on Tensorboard with similarity metrics and histograms to help and detect errors in the quantized model.

Checklist before requesting a review:

• I set the appropriate labels on the pull request.
• I have added/updated the release note draft (if necessary).
• I have updated the documentation to reflect my changes (if necessary).
• All function and files are well documented.
• All function and classes have type hints.
• There is a licenses in all file.
• The function and variable names are informative.
• I have checked for code duplications.
• I have added new unittest (if necessary).

[ofirgo]

Very nice!
A lot to discuss offline

[lior-dikstein]

Consider also adding a read-me with usage examples in Keras and Pytorch and a figure of how it looks

[ofirgo]

why the "%"?

[reuvenperetz]

It is used to indicate a magic command in Jupyter notebooks. Magic commands are a feature of
Jupyter notebooks to perform various tasks without a lot of complex code.
In this specific case, %load_ext tensorboard is a line magic command that loads the TensorBoard extension, enabling you to use TensorBoard directly within the notebook.

[ofirgo]

Also, why the link of this image is so long?

[reuvenperetz]

I don't know, to be honest... I guess this is how it is stored when you add an image to a colab notebook...