jenriver comments

Repositories
Issues
Comments

Results 3 comments of


                                            jenriver

Non-uniform sparsity layer-wise with PolynomialDecay scheduler

Hi AmoghDabholkar@, thanks for your input! We haven't considered this feature yet in tfmot sparsity, but will consider this to be included in our next batch of updates. Thanks!

Support for Recurrent layers for Quantization Aware Training.

Thanks for filing this issue, Parth. As you said, it looks like RNN was disabled as it was unsupported and yet to be verified on TFLite. We'll be keeping track...

JAX backend - exporting to TF savedmodel via JAX2TF errors (Cannot convert '(b, t, 1)' to a shape. Found invalid entry 't' AND ValueError: Invalid dtype: _DimExpr)

I'm also facing `AttributeError: 'DynamicJaxprTracer' object has no attribute '_keras_mask'`. Any hack to mitigate this?