Scaled YOLOv4

Scaled YOLOv4 is an extension of the YOLOv4 research implemented in the YOLOv5 PyTorch framework.

Try the Model

Use the widget below to experiment with Scaled YOLOv4. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

What is Scaled YOLOv4

Scaled YOLOv4 is an extension of the YOLOv4 research, developed by Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao, and implemented in the YOLOv5 PyTorch framework. At its core, it primarily lies on Cross Stage Partial Networks, allowing the network to scale its depth, width, resolution, and structure while maintaining speed and accuracy.

Scaled YoloV4 Results

Learn More

More info here: https://blog.roboflow.com/scaled-yolov4-tops-efficientdet/

‍

Scaled YOLOv4 License

Scaled YOLOv4

is licensed under a

GPL-3.0

license.

Performance

Deploy a Scaled YOLOv4 API

You can use Roboflow Inference to deploy a

Scaled YOLOv4

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with Scaled YOLOv4

You can automatically label a dataset using Scaled YOLOv4 with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use Scaled YOLOv4 to train a computer vision model.

No items found.