metadata
license: apache-2.0
tags:
- onnx
- object-detection
- ezonnx
RTMDet real-time object detection model.
MMPose
from ezonnx import RTMDet
rtm = RTMDet("s-coco") # you can choose "n-person","m-person","n-hand","tiny-coco","s-coco","m-coco","l-coco","x-coco"
result = rtm("image.jpg")
print(result.boxes) # (N, 4) array of bounding boxes
print(result.classes) # (N,) array of class labels
print(result.scores) # (N,) array of confidence scores
print(result.visualized_img) # (H, W, 3) image with boxes