liyunlu0618

Sorry for keeping you waiting. We're actively working on making the initial release of sparse inference support in TFLite. It's hard to give an exact date but hopefully before Q3...

A spoiler: https://github.com/tensorflow/model-optimization/blob/master/tensorflow_model_optimization/python/examples/sparsity/keras/mnist/mnist_e2e.py Please note that we're still finalizing the API. The workflow in the released version may look different.

For the Conv op we only support these hosted models at the moment: https://github.com/google-research/google-research/tree/master/fastconvnets We need the block config to use SIMD instructions on Arm neon architecture. Feel free to...

This is currently available as an experimental feature in TFLite. For sparse CNNs, it needs to run with the XNNPack delegate. Please refer to [this](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/delegates/xnnpack). For sparse RNNs and transformers,...

We recently added support for pruning nested models, see this [PR](https://github.com/tensorflow/model-optimization/pull/658). For subclass models, since keras doesn't support cloning, we still don't have a model-level API. You can still re-construct...

Using quantization instead is definitely an alternative solution. You can also check out this blogpost: https://ai.googleblog.com/2021/03/accelerating-neural-networks-on-mobile.html For CNN models, you can use pruning to train the model and deploy it...

Can you follow the example of pruning the whole model and try prune_low_magnitude(your model)? Then post the model summary or let us know if you run into any issues. Thanks!

Thanks for reporting the error. I'm working on a change to support pruning a model recursively. Will let you know once it's checked-in.

The PR is merged. https://github.com/tensorflow/model-optimization/pull/658 You can try later with a nightly build and let us know if it works. Thanks!

Can you try a nightly build of tf-mot?