Blog
Blog
How to Train Scaled-YOLOv4 to Detect Custom Objects
This blog is written to help you apply Scaled-YOLOv4 to your custom object detection task, to detect any object in the world, given the right training data.
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.
More info here: https://blog.roboflow.com/scaled-yolov4-tops-efficientdet/