🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

Hardware controller for AI applications.

structured outputs for llms

A collaboration friendly studio for NeRFs

CLI interfaces & config objects, from types

CUDA kernel author's tools

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).

stdgpu: Efficient STL-like Data Structures on the GPU

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

ML model optimization product to accelerate inference.

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

A simple, fully convolutional model for real-time instance segmentation.

Top-level directory for documentation and general content

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Sparsity-aware deep learning inference runtime for CPUs

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

Mean Average Precision for Object Detection

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

PyTorch extensions for fast R&D prototyping and Kaggle farming

A toolkit for developing and comparing reinforcement learning algorithms.

Python Sorted Container Types: Sorted List, Sorted Dict, and Sorted Set

Python Sorted Collections Library

A technical report on convolution arithmetic in the context of deep learning

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Model summary in PyTorch similar to `model.summary()` in Keras