Robust Speech Recognition via Large-Scale Weak Supervision

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

A collection of design patterns/idioms in Python

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

PyTorch Tutorial for Deep Learning Researchers

State-of-the-art 2D and 3D Face Analysis Project

End-to-End Object Detection with Transformers

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

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

PyTorch ,ONNX and TensorRT implementation of YOLOv4

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

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

MOT using deepsort and yolov3 with pytorch

Convolutional recurrent network in pytorch

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

You Only Look Once for Panopitic Driving Perception.（MIR2022）

Semi-Supervised Learning, Object Detection, ICCV2021

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

HybridNets: End-to-End Perception Network

A Python toolkit for applications driven by The Clean Architecture

using yolox+deepsort for object-tracking

This project aims to count every vehicle (motorcycle, bus, car, cycle, truck, train) detected in the input video using YOLOv3 object-detection algorithm.

multi-task learning for text recognition with joint CTC-attention