Ready for 🤯 ? You can sparsify ResNet-50 models up to 95% while retaining 99% of their accuracy! And then deploy them on commodity CPUs at GPU speeds! Learn more, benchmark, and apply your data with only a few lines of code: Tweet added by Neural Magic @neuralmagic

Neural Magic

2 years

Ready for 🤯 ? You can sparsify ResNet-50 models up to 95% while retaining 99% of their accuracy! And then deploy them on commodity CPUs at GPU speeds! Learn more, benchmark, and apply your data with only a few lines of code: