165 Forks
995 Stars
995 Watchers

neural-compressor

IntelĀ® Neural Compressor (formerly known as IntelĀ® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

How to download and setup neural-compressor

Open terminal and run command
git clone https://github.com/intel/neural-compressor.git
git clone is used to create a copy or clone of neural-compressor repositories. You pass git clone a repository URL.
it supports a few different network protocols and corresponding URL formats.

Also you may download zip file with neural-compressor https://github.com/intel/neural-compressor/archive/master.zip

Or simply clone neural-compressor with SSH
[email protected]:intel/neural-compressor.git

If you have some problems with neural-compressor

You may open issue on neural-compressor support forum (system) here: https://github.com/intel/neural-compressor/issues