Stars
This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
ZenML 🙏: The bridge between ML and Ops. https://zenml.io.
Another Unofficial Python Wrapper for Coinbase Pro
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains
Arcade Car Physics - Vehicle Simulation for Unity3D
Nvidia Semantic Segmentation monorepo
A simple, fully convolutional model for real-time instance segmentation.
Tools for rlgym-tools for training multiple models at once, and training against other models
A minimalist environment for decision-making in autonomous driving
A Gym-like environment for Reinforcement Learning in Rocket League
A font with extra characters for button prompts in games
Train reinforcement learning agent using ML-Agents with Google Colab.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.
Extension of the fastai library to include object detection.
fastrl is a reinforcement learning library that extends Fastai. This project is not affiliated with fastai or Jeremy Howard.
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Mask R-CNN Model to detect the area of damage on a car. The rationale for such a model is that it can be used by insurance companies for faster processing of claims if users can upload pics and the…
Computer Vision and Deep Learning techniques to accurately classify vehicle damage to facilitate claims triage by training convolution neural networks
An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come