Skip to content
Avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
39 followers · 5 following · 366
Block or Report

Block or report DefTruth

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DefTruth/README.md

logo

Author is DefTruth 👋

  • 🎓 JNU(master's degree)
  • 📖 DefTruth's page
  • 🔭 Computer Vision (检测/分割/抠图/识别/目标跟踪)
  • ❤ Languages: Python C/C++
  • ❤ Frameworks: PyTorch ONNXRuntime MNN NCNN
logo

Pinned

  1. lite.ai.toolkit Public

    Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models(一个开箱即用的C++ AI工具箱), such as RobustVideoMatting🔥, YOLOX🔥, YOLOP🔥 etc. (https://github.com/DefTruth/lite.ai.toolkit/releases/tag/v0.1.0)

    C++ 272 52

  2. hustvl/YOLOP Public

    You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）

    Python 624 106

  3. WongKinYiu/ScaledYOLOv4 Public

    Scaled-YOLOv4: Scaling Cross Stage Partial Network

    Python 1.6k 398

  4. WongKinYiu/yolor Public

    implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

    Python 869 178

  5. Megvii-BaseDetection/YOLOX Public

    YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

    Python 4.1k 734

  6. PeterL1n/RobustVideoMatting Public

    Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

    Python 3.2k 281

633 contributions in the last year

Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Mon Wed Fri
Learn how we count contributions
Less More

Contribution activity

September 2021

Created 130 commits in 11 repositories
Created 26 repositories
1 repository not shown

Created a pull request in PeterL1n/RobustVideoMatting that received 7 comments

Add inference_onnx.py

Features: Video Matting demo using onnxruntime and onnx file. all test passed @PeterL1n

+331 −0 • 7 comments

Opened their first pull request on GitHub in hustvl/YOLOP Public

DefTruth created their first pull request!

First pull request

Add converted YOLOP .onnx files、export_onnx.py and test_onnx.py ! Public
Opened 5 other pull requests in 5 repositories
DefTruth/RobustVideoMatting.lite.ai.toolkit 1 merged
PeterL1n/RobustVideoMatting 1 merged
WongKinYiu/yolor 1 open
amusi/awesome-lane-detection 1 open
amusi/awesome-object-detection 1 open

Created an issue in PeterL1n/RobustVideoMatting that received 4 comments

👉An ONNXRuntime C++ Demo for RobustVideoMatting is released.

ONNXRuntime C++ Demo: lite.ai.toolkit from DefTruth rvm.cpp rvm.h rvm-cpp-demo the output using rvm_mobilenetv3_fp32 of rvm-cpp-demo is: 详…

4 comments
Opened 3 other issues in 2 repositories

Seeing something unexpected? Take a look at the GitHub profile guide.