svenssona

openpilot

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

machine-learning-notes

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

dlwpt-code

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

jetson-containers

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

progress

Easy to use progress bars for Python

ViTPose

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

resource-stream

CUDA related news and material links

PETR

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

pycococreator

Helper functions to create COCO datasets

Neural-Network-Architecture-Diagrams

Diagrams for visualizing neural network architecture (Created with diagrams.net)

StreamPETR

[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

nimblephysics

Nimble: Physics Engine for Biomechanics and Deep Learning

VisionMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

image-to-coco-json-converter

Convert segmentation RGB mask images to COCO JSON format

opera

A Unified Toolbox for Object Perception & Application

Dual-task-Pose-Transformer-Network

[CVPR 2022] Exploring Dual-task Correlation for Pose Guided Person Image Generation

Pose3D-RIE

The PyTorch implementation for "Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation" (ACM MM2021).

runningpose

We introduce a new 3D pose estimator and model designed for runners.

HOWTO

Practical instructions and advice on how to achieve various things with build2

qtm-scripting

mediocre_chess_ai

A deep neural network chess AI

muzero

Learning how muzero works

VehicleSim

School project learning OOP. Applying design patterns, principles to refactor when building a toy vehicle simulator.

web-app