search

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.18k stars 316 forks source link

decode detection results in CUDA #190

Closed ccccwb closed 1 year ago

ccccwb commented 1 year ago
  1. Add decodeTensorCUDA.cu and decodeTensorCUDA.h
  2. change yolov5.cpp
  3. Use CUDA to speed up the decoding process of detection results.
Nuzhny007 commented 1 year ago

Working great! Thnx!