Commit History
C++ Demo - Image Classification (PPResNet) (#241) 30e431e
Ryan Lee commited on
C++ Demo - Object Tracking (VitTrack) (#240) be1656e
Ryan Lee commited on
Fix spelling, spacing, and unused variables (#236) 1528081
Ryan Lee commited on
Fix visualization and correct default model (#237) a8f2672
Ryan Lee commited on
Add YOLOX C++ demo save functionality (#235) ab90c04
Ryan Lee commited on
C++ Demo - Object Detection (NanoDet) (#232) ea4ac47
Ryan Lee commited on
Fix OpenCV version assertions in ViTTrack & RAFT and text offset (#234) 44fe25c
Ryan Lee commited on
Introduce Preprocessing for Optimized Quantization in `quantize-ort.py` (#238) 2129055
C++ Demo - Facial Expression Recognition (#233) adfd76b
Add SFace visualization demo and example outputs (#231) 8a1a70c
add the first summary report (#227) f0b651e
Bump version 4.9 (#222) 1047434
add benchmark results on Atlas 200I DK A2 (#225) e9da4a7
add benchmark results on Jetson Nano Orin (#224) 51d25f9
add benchmark results on Khadas VIM4 (#223) 99e5ad0
remove text detection DB (#221) 43ea797
Wanli commited on
add text detection model from ppocrv3 (#180) ac5c83c
Wanli commited on
fix nontype error (#215) edd0844
Pose estimation mp (#186) 9665382
Laurent Berger commited on
benchmark: add vittrack benchmark results (#214) 3b8b9d5
Remove DaSiamRPN since we have its superseder VitTrack now (#213) 7c978be
upload a better vittrack model (#212) 55d9fad
lpylpy0514 commited on
Google Summer of Code: Adding RAFT Optical Flow Model using ONNX Format (#197) 47e6010
Aser Atawya commited on
Merge pull request #194 from lpylpy0514:main 435e017
lpylpy0514 commited on
yolox demo: cast input dtype to float32 for dtype-sensitive backends (#210) 556a873
fix model quantization to support timvx backend (#209) 80eebd6
Add 'load_label' parameter for image classification models (#185) 160af44
Wanli commited on
yolox in c++ (#177) ea63088
Laurent Berger commited on
update accuracy evaluation scripts (#184) c920270
Wanli commited on
Person detector from MediaPipe Pose (#179) b7e21c2
Text recognition crnn (#176) d2c2d3d
Laurent Berger commited on
bump version to 4.8.0 (#190) 00a9b48
clip palm bbox to (w,h) (#182) fc71ef8
Wanli commited on
add benchmark results on vision five 2 with conflicts resolved (#173) d6f4836
Text Detection model DB (#175) cda4a9b
Laurent Berger commited on
add mobilenet c++ sample (#171) c5ec220
Laurent Berger commited on
update sbc notation (#174) 43ce9de
Add gesture classification for handpose estimation (#168) 6f815fd
Wanli commited on
change links of table from 'master' to 'main' (#169) 866ff8d
Wanli commited on
Add back example output images as lfs tracked files (#166) 69ad792
add pose estimation model (#152) ab8d410
Wanli commited on
update generate table script (#164) 0e997e3
Wanli commited on
update yunet to v2 (#151) 41c69c8
Wwupup commited on
update and modify documentation (#161) af3dd88
Wanli commited on
add additional hardware notes in the frontal readme (#163) f8da712
Merge pull request #160 from fengyuentau/add_new_hardware 59e587d
Wanli commited on