YOLOX
Trained on
MSCOCO Data
YOLO (You Only Look Once) Version X is a family of object detection models published in August 2021. It is a revisitation of the YOLOv3DarkNet53 model with several architectural and training improvements: the decoupling of classification and regression heads, the switch to an anchorfree pipeline, the introduction of an advanced labelassignment strategy named SimOTA (Simplified Optimal Transport Assignment) and the use of strong data augmentation techniques.
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 8,400 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 scaled 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

Z. Ge, S. Liu, F. Wang, Z. Li, J. Sun,"YOLOX: Exceeding YOLO Series in 2021," arXiv:2107.08430 (2021)
 Available from:

Rights:
Apache License