Tensors and Dynamic neural networks in Python with strong GPU acceleration

Focus on prompting and generating

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A cryptocurrency trading API with more than 100 exchanges in JavaScript / TypeScript / Python / C# / PHP / Go

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

OpenMMLab Detection Toolbox and Benchmark

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Image augmentation for machine learning experiments.

OpenMMLab Computer Vision Foundation

NeuralProphet: A simple forecasting package

NVIDIA's Deep Imagination Team's PyTorch Library

Siamese and triplet networks with online pair/triplet mining in PyTorch

On the Variance of the Adaptive Learning Rate and Beyond

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

A General Toolbox for Identifying Object Detection Errors

[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation

Unofficial PyTorch implementation of the paper titled "Progressive growing of GANs for improved Quality, Stability, and Variation"

D-Adaptation for SGD, Adam and AdaGrad

Domain Adaptive Faster R-CNN in PyTorch

DCGAN LSGAN WGAN-GP DRAGAN PyTorch

Blender environment to create synthetic data for deep learning purpose