GitHub - Robert-JunWang/Pelee: Pelee: A Real-Time Object Detection System on Mob...
source link: https://github.com/Robert-JunWang/Pelee
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
Pelee: A Real-Time Object Detection System on Mobile Devices
This repository contains the code for the following paper.
Pelee: A Real-Time Object Detection System on Mobile Devices (ICLR 2018 workshop track)
The code is based on the SSD framework.
Citation
If you find this work useful in your research, please consider citing:
@article{wang2018pelee,
title={Pelee: A Real-Time Object Detection System on Mobile Devices},
author={Wang, Robert J and Li, Xiang and Ao, Shuang and Ling, Charles X},
journal={arXiv preprint arXiv:1804.06882},
year={2018}
}
Results on VOC 2007
The table below shows the results on PASCAL VOC 2007 test.
Method mAP (%) FPS (Intel i7) FPS (iPhone 6s) FPS (iPhone 8) # parameters YOLOv2-288 69.0 1.0 - - 58.0M DSOD300_smallest 73.6 1.3 - - 5.9M Tiny-YOLOv2 57.1 2.4 9.3 23.8 15.9M SSD+MobileNet 68.0 6.1 16.1 22.8 5.8M Pelee 70.9 6.7 17.1 23.6 5.4M Method 07+12 07+12+coco SSD300 77.2 81.2 SSD+MobileNet 68 72.7 Pelee 70.9 76.4Results on COCO
The table below shows the results on COCO test-dev2015.
Method mAP@[0.5:0.95] [email protected] [email protected] Computational Cost (MACs) # parameters SSD300 25.1 43.1 25.8 34,360 M 34.30 M YOLOv2-416 21.6 44.0 19.2 17,500 M 67.43 M SSD+MobileNet 18.8 - - 1,200 M 6.80 M Pelee 22.4 38.3 22.9 1,290 M 5.98 MPreparation
-
Install SSD (https://github.com/weiliu89/caffe/tree/ssd) following the instructions there, including: (1) Install SSD caffe; (2) Download PASCAL VOC 2007 and 2012 datasets; and (3) Create LMDB file. Make sure you can run it without any errors.
-
Download the pretrained PeleeNet model. By default, we assume the model is stored in $CAFFE_ROOT/models/
-
Clone this repository and create a soft link to $CAFFE_ROOT/examples
git clone https://github.com/Robert-JunWang/Pelee.git ln -sf `pwd`/Pelee $CAFFE_ROOT/examples/pelee
Training & Testing
-
Train a Pelee model on VOC 07+12:
cd $CAFFE_ROOT python examples/pelee/train_voc.py
-
Evaluate the model:
cd $CAFFE_ROOT python examples/pelee/eval_voc.py
Models
-
PASCAL VOC 07+12: Download (20.3M)
-
PASCAL VOC 07+12+coco: Download (20.3M)
-
MS COCO: Download (21M)
Recommend
-
149
Professionals | Community Groups Programs | Google Developers
-
71
-
37
Chapter 1 - Introduction processes inherit the UID and GID permission octal values: r=4, w=2, x=1. Order is user, group, everyone else functions normally just return a -1 to indicate an...
-
41
OpenPCDet OpenPCDet is a clear, simple, self-contained open source project for LiDAR-based 3D object detection. It is also the official code release of [PointRCNN]
-
15
Frigate - NVR With Realtime Object Detection for IP Cameras A complete and local NVR designed for HomeAssistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras. ...
-
11
NanoDet Super fast and lightweight anchor-free object detection model. Real-time on mobile devices. Super lightweight: Model fil...
-
4
3DETR: An End-to-End Transformer Model for 3D Object Detection PyTorch implementation and models for 3DETR. 3DETR (3D DEtection TRansformer)...
-
24
ByteTrack ByteTrack is a simple, fast and strong multi-object tracker. ByteTrack: Multi-Object Tracking by Associating Every Detection Box Yif...
-
4
DE⫶TR: End-to-End Object Detection with Transformers PyTorch training code and pretrained models for DETR (DEtection TRansformer). We replace the full complex hand-c...
-
7
End-to-End Semi-Supervised Object Detection with Soft Teacher By Mengde Xu*, Zheng Zhang*,
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK