#254 · Primary category： Computer Vision
ScaledYOLOv4
Scaled-YOLOv4: Scaling Cross Stage Partial Network
Project last updated：11/03/24
GitHub Stars
2.0K
Forks
563
Contributors
1
License
GPL-3.0
Why we included this project
Object detection teams will find this to be the canonical PyTorch implementation of the scaled YOLOv4 paper, with P5, P6, and P7 models plus the CSP and tiny branches. It ships pretrained COCO weights and straightforward inference scripts, so you can load a model, run it on an image, and get boxes without building the network from scratch. The speed/accuracy tradeoff is easy to reason about: P5 runs around 41 fps at 896 pixels, while P7 goes for higher accuracy at 1536, which matters when picking between edge hardware and a server pipeline. The README's AP tables and per-class metrics let you compare variants before you commit to one.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)