Introduce Preprocessing for Optimized Quantization in `quantize-ort.py` (#238) 2129055 Shuyao "Tim" Xu Tim-Xu commited on Feb 27, 2024
Remove DaSiamRPN since we have its superseder VitTrack now (#213) 7c978be ytfeng commited on Oct 24, 2023
Add 'load_label' parameter for image classification models (#185) 160af44 Wanli commited on Aug 9, 2023
Update handpose estimation model from MediaPipe (2023feb) (#133) 50fc340 Wanli commited on Feb 22, 2023
move setting description outside for loop in evaluation scripts (#134) 5de3983 Labib Asari commited on Feb 22, 2023
Add model file collector, fix some bugs and add some features (#123) 39d77a4 ytfeng commited on Jan 26, 2023
Re-quantify some models from per_channel mode to per_tensor mode (#90) 323da84 Wanli commited on Jan 6, 2023
revise the quantize-ort to quantize crnn into int8 with high accuracy (#94) d30c3db Yiyao Wang commited on Oct 13, 2022
Text Recognition: Add script to evaluate text recognition by ICDAR2003 (#71) 46b1f95 Yiyao Wang commited on Sep 7, 2022
use QuantFormat.QOperator by default to avoid fake quantization (#88) 4b236af ytfeng commited on Aug 29, 2022
Add the missing yaml config for quantizing MP-PalmDet and improve quantized MP-PalmDet (#60) 83c563e ytfeng commited on Jun 8, 2022
Use YuNet of fixed input shape to avoid 'parseShape' error (#45) 62917b7 ytfeng commited on Apr 1, 2022