Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

2nd Place Solution for the RSNA 2023 Abdominal Trauma Detection Kaggle Competition

Image-to-point cloud Registration Tool

Painter & SegGPT Series: Vision Foundation Models from BAAI

Simple jupyter notebook for 3D reconstruction using kornia and pycolmap

python library for invisible image watermark (blind image watermark)

WebUI extension for using Blip2

付録コード

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

SOTA Semantic Segmentation Models in PyTorch

Utilities for object detection

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

[CVPR 2022] This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

Python package for reading, and extracting data from rosbag files and performing any analysis on it.

Official PyTorch Implementation of MotionSqueeze, ECCV 2020

BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

My 1st place solution at Kaggle Hotel-ID 2021

Unofficial implementation of PatchCore anomaly detection

Vision Transformer for 3D medical image registration (Pytorch)

Flexible Python configuration system. The last one you will ever need.

Top 1 solution of Chexpert

Reproducing CheXpert paper using the PyTorch library.

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier

Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.