https://github.com/parth-shastri/yolov2

This is from scratch implementation of yolov2 model. I have taken help from fairyonices blog https://fairyonice.github.io/Part_1_Object_Detection_with_Yolo_for_VOC_2014_data_anchor_box_clustering.html
https://github.com/parth-shastri/yolov2

Last synced: about 2 hours ago
JSON representation

This is from scratch implementation of yolov2 model. I have taken help from fairyonices blog https://fairyonice.github.io/Part_1_Object_Detection_with_Yolo_for_VOC_2014_data_anchor_box_clustering.html

• Host: GitHub
• URL: https://github.com/parth-shastri/yolov2
• Owner: parth-shastri
• Created: 2021-04-03T14:31:58.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2021-05-29T03:51:10.000Z (over 3 years ago)
• Last Synced: 2024-11-11T15:22:53.429Z (about 2 months ago)
• Language: Python
• Size: 15.8 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# YOLOv2

This is from scratch implementation of yolov2 model. I have taken help from fairyonices blog https://fairyonice.github.io/Part_1_Object_Detection_with_Yolo_for_VOC_2014_data_anchor_box_clustering.html

I have used tensorflow 2.2 and also some dependent python libraries like matplotlib and json.

I have referred the yolov2 and yolov3 papers while creating this project.

The model is overfit on 100 images from the MS COCO train 2014 dataset, I have done so to just check if the model works as intended.

I also have taken help from aladinn perssons youtube channel as well as github repo.

Current output on the overfit data itself:

![Output image](https://github.com/parth-shastri/YOLOv2/blob/main/images/Figure_1.png?raw=true)

The papers:

https://arxiv.org/pdf/1804.02767 - YOLOv3

https://arxiv.org/pdf/1612.08242 - YOLO9000