l-net-1992 Goto Github PK

training_extensions

Trainable models and NN optimization tools

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for Hugging Face transformer models 🚀

transfuser

[CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

tsmainui

Decompiled source for Main UI (CenterService MCU Communication Protocol) on the MTK Android 6

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

ultra-light-fast-generic-face-detector-1mb

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

unicorn

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

updatinghdmapbymonocamera

a hdmap updating project by mono camera and gps rtk

vcpkg

C++ Library Manager for Windows, Linux, and MacOS

vectormap2opendrive

Convert Autoware vector map to Opendrive format

vehicle-dsm

Vehicle detection and speed measurement system

ventoy

A new bootable USB solution.

videostitch

viewer

ML models and internal tensors 3D visualizer

violation-detection-in-videos

SMAI Final Project - to detect smoking, drinking and obscenity (violations) in videos.

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

vision-radar

visualdl

Deep Learning Visualization Toolkit（『飞桨』深度学习可视化工具 ）

vitis-ai

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

vlc

VLC media player - All pull requests are ignored, please follow https://wiki.videolan.org/Sending_Patches_VLC/

workflow

C++ Parallel Computing and Asynchronous Networking Engine

wslg

Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios

x64dbg

An open-source x64/x32 debugger for windows.

xiangshan

Open-source high-performance RISC-V processor

xnxpilot

Openpilot on Jetson Xavier NX

ymir

YMIR, a streamlined model development product.

yolo-fastestv2

:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

yoloair

🔥🔥🔥YOLOAir：Including YOLOv5, YOLOv7, Transformer, YOLOX, YOLOR and other networks... Support to improve backbone, head, loss, IoU, NMS...The original version was created based on YOLOv5

yolop

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

yolop-opencv-dnn

使用OpenCV部署全景驾驶感知网络YOLOP，可同时处理交通目标检测、可驾驶区域分割、车道线检测，三项视觉感知任务，包含C++和Python两种版本的程序实现。本套程序只依赖opencv库就可以运行， 从而彻底摆脱对任何深度学习框架的依赖。