RangiLyu / nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
☆5,829Updated 5 months ago
Alternatives and similar repositories for nanodet:
Users that are interested in nanodet are comparing it to the libraries listed below
- Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is…☆2,029Updated 3 years ago
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆9,599Updated 2 months ago
- 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥☆3,127Updated last year
- PyTorch ,ONNX and TensorRT implementation of YOLOv4☆4,499Updated 7 months ago
- Scaled-YOLOv4: Scaling Cross Stage Partial Network☆2,022Updated 2 months ago
- Implementation of popular deep learning networks with TensorRT network definition API☆7,148Updated last month
- YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)☆2,157Updated 6 months ago
- PyTorch implementation of YOLOv4☆1,896Updated 2 months ago
- implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)☆1,994Updated 2 months ago
- BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models☆6,916Updated this week
- OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.☆3,075Updated 6 months ago
- [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box☆4,997Updated 7 months ago
- The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.☆5,215Updated 3 years ago
- 🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署,支持Android与iOS。☆1,500Updated 2 years ago
- YOLOv6: a single-stage object detection framework dedicated to industrial applications.☆5,748Updated 5 months ago
- OpenMMLab Model Deployment Framework☆2,831Updated 3 months ago
- OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT…☆3,628Updated last year
- 🔥🔥🔥 专注于YOLOv5,YOLOv7、YOLOv8、YOLOv9改进模型,Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀☆2,567Updated 9 months ago
- MOT using deepsort and yolov3 with pytorch☆2,858Updated 6 months ago
- 🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉☆3,751Updated last month
- Object detection, 3D detection, and pose estimation using center point detection:☆7,342Updated last year
- Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smar…☆834Updated last year
- An easy to use PyTorch to TensorRT converter☆4,658Updated 5 months ago
- [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking☆4,061Updated last year
- Simple Online Realtime Tracking with a Deep Association Metric☆5,461Updated 6 months ago
- Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors☆13,562Updated 5 months ago
- A simple, fully convolutional model for real-time instance segmentation.☆5,063Updated last year
- 🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~☆2,304Updated 7 months ago
- SOTA Re-identification Methods and Toolbox☆3,518Updated 5 months ago
- OpenMMLab Computer Vision Foundation☆5,989Updated last week