Yunus Emre Çalışkan

@jspark1105 Thank you for the reply that's great, i'll be following the news. @hfp Thanks, that looks quite interesting as well.

> as you can see, it loads the original model and save some weights, and loads again with custom operation for fast inference. But both tests inside the inference.py use...

Thanks for the tips, i managed to use custom_op after using `extract_dense_weights`. However it has been slower than regular convolution so i decided to check the sparsities like you did...