kneron-mmtracking is a platform built upon the well-known mmtracking for tracking. We encourage you to start with ByteTrack: Multi-Object Tracking by Associating Every Detection Box to build basic knowledge of Kneron-Edition mmtracking, and read mmtracking docs for detailed mmtracking usage.
In this repository, we provide an end-to-end training/deployment flow to realize on Kneron's AI accelerators:
- Training/Evalulation:
- Modified model configuration file and verified for Kneron hardware platform
- Please see Overview of Benchmark and Model Zoo for Kneron-Verified model list
- Converting to ONNX:
- pytorch2onnx_kneron.py (beta)
- Export optimized and Kneron-toolchain supported onnx
- Automatically modify model for arbitrary data normalization preprocess
- Evaluation
- test_kneron.py (beta)
- Evaluate the model with pytorch checkpoint, onnx, and kneron-nef
- Testing
- inference_kn (beta)
- Verify the converted NEF model on Kneron USB accelerator with this API
- Converting Kneron-NEF: (toolchain feature)
- Convert the trained pytorch model to Kneron-NEF model, which could be used on Kneron hardware platform.
This project is released under the Apache 2.0 license.
N/A
Model | size | Mem (GB) | box AP | Config | Download |
---|---|---|---|---|---|
ByteTrack(YOLOX-s) | (448, 800) | 7.6 | 82.4 | config | model |
- Please refer to ByteTrack: Multi-Object Tracking by Associating Every Detection Box, Step 0. Environment for installation.
- Please refer to Kneron PLUS - Python: Installation for the environment setup for Kneron USB accelerator.
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box: A tutorial for users to get started easily. To see detailed documents, please see below.
- [Kneron ONNX Export] (under development)
- [Kneron Inference] (under development)
- Kneron Toolchain Step-By-Step (YOLOv3)
- Kneron Toolchain Manual
- Original mmtracking getting started: It is recommended to read the original mmtracking getting started documents for other mmtracking operations.
- Original mmtracking readthedoc: Original mmtracking documents.
kneron-mmtracking a platform built upon OpenMMLab-mmtracking
-
For issues regarding to the original mmtracking: We appreciate all contributions to improve OpenMMLab-mmtracking. Ongoing projects can be found in out GitHub Projects. Welcome community users to participate in these projects. Please refer to CONTRIBUTING.md for the contributing guideline.
-
For issues regarding to this repository kneron-mmtracking: Welcome to leave the comment or submit pull requests here to improve kneron-mmtracking
- kneron-mmdetection: Kneron training/deployment platform on OpenMMLab - mmDetection detection toolbox
- kneron-mmsegmentation: Kneron training/deployment platform on OpenMMLab - mmSegmentation semantic segmentation toolbox