ScaledYOLO V4
Trained on
MSCOCO Data
This family of models revisits the YOLO Version 4 architecture with some key changes. First the net architecture was modified to employ CSPNet (Cross Stage Partial Network) blocks, improving the speed/accuracy tradeoff. Then a thorough scaling analysis was performed in order to find the optimal way to scale up the depth, width and resolution of the net by various factors.
Examples
Resource retrieval
Get the pretrained net:
NetModel parameters
This model consists of a family of individual nets, each identified by a specific parameter combination. Inspect the available parameters:
Pick a nondefault net by specifying the parameters:
Pick a nondefault uninitialized net:
Evaluation function
Write an evaluation function to scale the result to the input image size and suppress the least probable detections:
Basic usage
Obtain the detected bounding boxes with their corresponding classes and confidences for a given image:
Inspect which classes are detected:
Visualize the detection:
Network result
The network computes 65,856 bounding boxes and the probability that the objects in each box are of any given class:
Rescale the bounding boxes to the coordinates of the input image and visualize them scaled by their "objectness" measures:
Visualize all the boxes scaled by the probability that they contain a cat:
Superimpose the cat prediction on top of the input received by the net:
Net information
Inspect the number of parameters of all arrays in the net:
Obtain the total number of parameters:
Obtain the layer type counts:
Display the summary graphic:
Resource History
Reference

C. Wang, A. Bochkovskiy, H. Liao, "ScaledYOLOv4: Scaling Cross Stage Partial Network," arXiv:2011.08036 (2020)
 Available from:

Rights:
GNU General Public License