SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone
YOLOv3/v4 object detection implementation with model compression techniques including pruning, quantization, and knowledge distillation across multiple backbones.
Not currently ranked — collecting fresh signals.
star history
This project provides YOLOv3 and YOLOv4 implementations for object detection with support for multiple datasets including COCO, BDD100k, and Visdrone. It implements model compression through pruning (channel and layer), quantization-aware training (8-bit), and knowledge distillation. Multiple backbone architectures are supported: standard Darknet, Tiny-YOLO, and MobileNetV3-based variants for different speed/accuracy tradeoffs. The repository enables multi-dataset training and provides pre-trained weights for various configurations.
Frequently asked
- What is SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone?
- YOLOv3/v4 object detection implementation with model compression techniques including pruning, quantization, and knowledge distillation across multiple backbones.
- Is YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone open source?
- Yes — SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone is open source, released under the GPL-3.0 license.
- What language is YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone written in?
- SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone is primarily written in Python.
- How popular is YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone?
- SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone has 442 stars on GitHub.
- Where can I find YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone?
- SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone is on GitHub at https://github.com/SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone.