Ahmad-Shawahna / FxP-QNet

A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation for Efficient Hardware Acceleration on Edge Devices

Geek Repo

Github PK Tool

neural-networks model-compression deep-learning quantization fixed-point-arithmetic mixed-precision acceleration accuracy efficient-inference resource-constrained-devices

FxP-QNet

About

A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation for Efficient Hardware Acceleration on Edge Devices

neural-networks model-compression deep-learning quantization fixed-point-arithmetic mixed-precision acceleration accuracy efficient-inference resource-constrained-devices