Development repository for the Triton language and compiler

Sparse4D v1 & v2

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

code for Image Manipulation Detection by Multi-View Multi-Scale Supervision

华中科技大学研究生课程资料

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Neural Unsigned Distance Fields (NDF) - Codebase

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

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

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

A multi-thread crawler framework with many builtin image crawlers provided.

Deformable Convolutional Networks v2 with Pytorch

OpenMMLab Computer Vision Foundation

📊 Benchmark multiple object trackers (MOT) in Python

OpenMMLab Detection Toolbox and Benchmark

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Basic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).

Reference models and tools for Cloud TPUs.

This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423

Open source person re-identification in Pytorch

pytorch CircleLoss for Face recognition