An Extensible Deep Learning Library

DIODE Development Toolkit

Code for the CVPR 2020 paper "OASIS: A Large-Scale Dataset for Single Image 3D in the Wild"

Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"

A native PyTorch Library for large model training

nyuv2 toolbox for data extraction and loading.

A simple image generator for NYU2 (labeled dataset), which provides independent images for your evaluation goals.

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

ICRA 2019 "FastDepth: Fast Monocular Depth Estimation on Embedded Systems"

Converts a depth map image to a normal map image using Python

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

Neural Network Compression Framework for enhanced OpenVINO™ inference

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Flower: A Friendly Federated AI Framework

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"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

An extremely fast Python linter and code formatter, written in Rust.

OpenMMLab Text Detection, Recognition and Understanding Toolbox

OpenMMLab Pose Estimation Toolbox and Benchmark.

[CVPR 2023 Highlight] Freestyle Layout-to-Image Synthesis

[ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

Painter & SegGPT Series: Vision Foundation Models from BAAI

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

Training PyTorch models with differential privacy

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

A tool for exploring each layer in a docker image

A Docker image for PyTorch