NoneSoVile

vehicle-command

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

android-sdk

Smartcar Android Auth SDK

dlp

Deep learning platform based on tensorflow

fluid-engine-dev

Fluid simulation engine for computer graphics applications

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Object-Detection-for-Graphical-User-Interface

Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

yolov8_pytorch_python

YOLOv8 inference using Ultralytics API

Self_Driving_Car

Udacity Self Driving Car ND projects - including lane detection, Traffic sign classifier, behaviour cloning

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

sympy

A computer algebra system written in pure Python

llama.cpp

LLM inference in C/C++

webgl-noise

GLSL procedural noise functions compatible with WebGL

webgl-noise

Procedural Noise Shader Routines compatible with WebGL

raytracing.github.io

Main Web Site (Online Books)

winscp

WinSCP is a popular free SFTP and FTP client for Windows, a powerful file manager that will improve your productivity. It supports also Amazon S3, FTPS, SCP and WebDAV protocols, as well as copying between two local directories. Power users can automate WinSCP using .NET assembly.

FluidX3D

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs via OpenCL. Free for non-commercial use.

mine

Minimal and single-header cryptography library (AES, RSA, Base16, Base64, ZLib), implemented for education purposes - use @abumq/ripe for production.

libxcam

libXCam is a project for extended camera(not limited in camera) features and focus on image quality improvement and video analysis. There are lots features supported in image pre-processing, image post-processing and smart analysis. This library makes GPU/CPU/ISP working together to improve image quality. OpenCL is used to improve performance in different platforms.

NdkCamera

Simplified Android NDK Camera API 2

MultiCameraSample

Sample app to test Camera2 API's Multi Camera mode

native-camera2

A simple application to demonstrate how to use Android Camera HAL 3

compressonator

Tool suite for Texture and 3D Model Compression, Optimization and Analysis using CPUs, GPUs and APUs

opengl-framework

Cross-platform OpenGL demos