Collaborative cheatsheets for console commands 📚.

Presentation Slides for Developers

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

A list of awesome compiler projects and papers for tensor computation and deep learning.

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

RamDrive that is backed by GPU Memory

[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

Convert pointpillars Pytorch Model To ONNX for TensorRT Inference

Simplify your onnx model

Implementation of popular deep learning networks with TensorRT network definition API

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Productive, portable, and performant GPU programming in Python.

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

Deep Learning tools and applications for NVIDIA AGX platforms.

Brevitas: neural network quantization in PyTorch

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Count the MACs / FLOPs of PyTorch models

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

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