dlunion / ffmpeg-hardware-decodeLinks
Use ffmpeg and NVCodec to hardware decode video or video stream. in DNN inference system
☆53Updated 5 years ago
Alternatives and similar repositories for ffmpeg-hardware-decode
Users that are interested in ffmpeg-hardware-decode are comparing it to the libraries listed below
Sorting:
- 华为海思hi系列芯片使用的NNIE推理框架教程☆61Updated last year
- ⚡️ Using NNIE as simple as using ncnn ⚡️☆186Updated 3 years ago
- centernet_mobilenetv2 inference by ncnn☆64Updated 5 years ago
- ncnn of yolov5 v5.0 branch☆87Updated 4 years ago
- yolov5 nine hi3516 hi3519 object detect real-time☆43Updated 4 years ago
- rknn inference☆47Updated 3 years ago
- Implement yolov5 with Tensorrt C++ api, and integrate batchedNMSPlugin. A Python wrapper is also provided.☆49Updated 3 years ago
- openpose, yolov3 with tiny-tensorrt☆86Updated 4 years ago
- yolov5s nnie☆48Updated 3 years ago
- CenterTrack_caffe☆24Updated 5 years ago
- the C++ version of solov2 with ncnn☆77Updated 4 years ago
- ☆9Updated 6 years ago
- ☆27Updated 4 years ago
- SORT (A simple online and realtime tracking algorithm for 2D multiple object tracking in video sequences) and SSD face detector.☆17Updated 4 years ago
- A C++ API of the LFFD with ncnn☆99Updated 5 years ago
- 基于AlphaPose的TensorRT加速☆61Updated 4 years ago
- yolov5 onnx caffe☆88Updated 4 years ago
- U版yolov5 2.0的tensorrt加速☆37Updated 4 years ago
- MTCNN light + SORT tracking☆43Updated 5 years ago
- 基于海思3519的YOLOv3例程☆22Updated 4 years ago
- Lightweight Mat and imread()/imwrite()/imshow()☆82Updated last year
- MNN MTCNN C++☆50Updated 6 years ago
- centerNet Caffe inference CPP☆69Updated 5 years ago
- Android hand detect and pose estimation by ncnn☆96Updated 3 years ago
- Code for some onnxruntime projects☆122Updated 4 years ago
- YOLO5Face 2021 with MNN/NCNN/TNN/ONNXRuntime☆59Updated 2 years ago
- This is a TensorRT based deepsort project☆79Updated 3 years ago
- 用pytorch训练ssd,相比原版pytorch-ssd改动了不少☆11Updated 3 years ago
- ☆66Updated 3 years ago
- yolov5s_ncnn_inference pipeline☆21Updated 4 years ago