Gumpest/YOLOv5-Multibackbone-Compression
A YOLOv5 compression toolbox supporting multi-backbone substitution, model pruning (EagleEye, Network Slimming), quantization (MQBench), and deployment (TensorRT, ncnn).
Not currently ranked — collecting fresh signals.
star history
This repository provides a comprehensive suite of model compression techniques for YOLOv5 object detection models. It includes multi-backbone substitutions using architectures like Ghostnet, ShuffleNetv2, Swin Transformer, and MobileNetv3. The toolbox implements pruning methods (EagleEye, Network Slimming) and quantization via MQBench, and supports deployment optimization through TensorRT and ncnn runtimes for edge device inference.
Frequently asked
- What is Gumpest/YOLOv5-Multibackbone-Compression?
- A YOLOv5 compression toolbox supporting multi-backbone substitution, model pruning (EagleEye, Network Slimming), quantization (MQBench), and deployment (TensorRT, ncnn).
- Is YOLOv5-Multibackbone-Compression open source?
- Yes — Gumpest/YOLOv5-Multibackbone-Compression is an open-source project tracked on heatdrop.
- What language is YOLOv5-Multibackbone-Compression written in?
- Gumpest/YOLOv5-Multibackbone-Compression is primarily written in Python.
- How popular is YOLOv5-Multibackbone-Compression?
- Gumpest/YOLOv5-Multibackbone-Compression has 1k stars on GitHub.
- Where can I find YOLOv5-Multibackbone-Compression?
- Gumpest/YOLOv5-Multibackbone-Compression is on GitHub at https://github.com/Gumpest/YOLOv5-Multibackbone-Compression.