《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Python sample codes for robotics algorithms.

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

3D Reconstruction Software

An open source implementation of CLIP.

An elegant PyTorch deep reinforcement learning library.

Object detection, 3D detection, and pose estimation using center point detection:

Graph Convolutional Networks in PyTorch

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

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

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

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 highly efficient implementation of Gaussian Processes in PyTorch

Python package for the evaluation of odometry and SLAM

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Visual localization made easy with hloc

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

PyRobot: An Open Source Robotics Research Platform

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

Automatically "block" people in images (like Black Mirror) using a pretrained neural network.

Dense Prediction Transformers

[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

High-quality implementations of standard and SOTA methods on a variety of tasks.