A simple python module to generate anchor (aka default/prior) boxes for object detection tasks.
-
Updated
Jul 26, 2025 - Jupyter Notebook
A simple python module to generate anchor (aka default/prior) boxes for object detection tasks.
A modular YOLOv2 implementation in PyTorch with the Darknet-19 backbone. Includes dataset handling (VOC), letterbox preprocessing, training loop, custom loss, decoding, NMS, and VOC07 mAP evaluation. Designed for clarity, reproducibility, and research use, with unit tests and visualization tools.
Refer Readme.md
[YOLOv2/YOLOv3/YOLOv5]Tool used to generate anchor-boxes required for training YOLO networks
Custom object detection pipeline in PyTorch — anchor-based detector with FPN neck, no pretrained weights
Object detection and instant segmentation - Pascal VOC dataset
Add a description, image, and links to the anchor-boxes topic page so that developers can more easily learn about it.
To associate your repository with the anchor-boxes topic, visit your repo's landing page and select "manage topics."