머신러닝 · GitHub

Vehicle detection using machine learning and computer vision techniques for Udacity's Self-Driving Car Engineer Nanodegree.

One-click Portable Windows installation of 'AI-Toolkit by Ostris'

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with DNNs.

A quickstart and benchmark for pytorch distributed training.

Image Super-Resolution Using Deep Convolutional Networks in Tensorflow https://arxiv.org/abs/1501.00092v3

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

ncnn은 모바일 플랫폼에 최적화된 고성능 신경망 추론 프레임워크입니다.

• No third-party runtime dependencies and no BLAS / NNPACK requirement.
• Pure C++ implementation with C API and Python binding.

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

CVPR 2022 HFGI: High-Fidelity GAN Inversion for Image Attribute Editing

PyTorch + Gymnasium framework for aerospace control. Deep RL (SAC, PPO, DDPG, DQN, IHDP, ET-DHP) and adaptive controllers (AIDI, MPC, iADP) on nonlinear F-16/B747/UAV/satellite sims. Includes in-flight damage modeling, real-time 3D flight viewer, TensorBoard/WandB, Optuna. EN/RU docs.