Start Post-Training Static Quantization | AI Model Optimization with Intel® Neural Compressor
112Learn the basics of post-training static quantization to INT8. Then see how it’s applied to a BERT-large model using Intel Neural Compressor.
Static quantization provides the most optimization among the choices of quantization approaches. But it can seem challenging because you have to calibrate the model’s weights and activations to get the range of values to map to the integer range.
Learn the basic principles behind this approach, as well as the basic steps and requirements to get started with static quantization. These are illustrated using examples from Intel® Neural Compressor, so the same API can be used across PyTorch*, TensorFlow*, and ONNX* Runtime.
Future videos in this series will cover more depth and detail behind the static quantization basics shown in this video.
Intel® Neural Compressor: https://bit.ly/3Nl6pVj
Intel® Neural Compressor GitHub: https://bit.ly/3NlBgkH
About the AI Model Optimization with Intel® Neural Compressor Series:
Learn how to choose and get started with AI model optimization techniques. Get started with examples using Intel® Neural Compressor, which works within PyTorch*, TensorFlow*, and ONNX* Runtime
About Intel Software:
The Intel® Developer Zone encourages and supports software developers that are developing applications for Intel hardware and software products. The Intel Software YouTube channel is a place to learn tips and tricks, get the latest news, watch product demos from both Intel, and our many partners across multiple fields. You'll find videos covering the topics listed below, and to learn more, you can follow the links provided!
Connect with Intel Software:
Visit INTEL SOFTWARE WEBSITE: https://intel.ly/2KeP1hD
Like INTEL SOFTWARE on FACEBOOK: http://bit.ly/2z8MPFF
Follow INTEL SOFTWARE on TWITTER: http://bit.ly/2zahGSn
INTEL SOFTWARE GITHUB: http://bit.ly/2zaih6z
INTEL DEVELOPER ZONE LINKEDIN: http://bit.ly/2z979qs
INTEL DEVELOPER ZONE INSTAGRAM: http://bit.ly/2z9Xsby
INTEL GAME DEV TWITCH: http://bit.ly/2BkNshu
#oneAPI #intelsoftware #ai
Get Started with Post-Training Static Quantization | Intel Software