extraction of the features of the detected objects

[rabahMoulai]

i'm trying to get the features of the objects detected by the faster Rcnn. I'm new in object detection.
so I'm sorry if my question seems obvious. here is my code for detection. if someone can help me I will be really grateful

from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.data import MetadataCatalog
from detectron2.utils.visualizer import ColorMode, Visualizer
from detectron2 import model_zoo

import cv2
import numpy as np

class Detector :
    def __init__(self,model_type):
        self.cfg=get_cfg()
        self.model_type=model_type
        #load model config and pretrained model 
        if model_type=="OD":

            self.cfg.merge_from_file(model_zoo.get_config_file("COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml"))
            self.cfg.MODEL.WEIGHTS="detectron2://COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl"
        
        
        self.cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST=0.65
        self.cfg.MODEL.DEVICE="cpu"
        self.predictor=DefaultPredictor(self.cfg)

    def onImage(self,imagePath):
        image=cv2.imread(imagePath)
        if self.model_type !="PS":
    
            predictions=self.predictor(image)
            instances = predictions["instances"]
            #classes indexes
            detected_class_indexes = instances.pred_classes
            #objects bounding boxes
            prediction_boxes = instances.pred_boxes
            #classes names
            metadata = MetadataCatalog.get(self.cfg.DATASETS.TRAIN[0])
            classes_names= metadata.thing_classes
            # afficher les classes des objets et leurs boundinx box
            for idx, coordinates in enumerate(prediction_boxes):
                class_index = detected_class_indexes[idx]
                class_name = classes_names[class_index]
                print(class_name, coordinates)

            viz = Visualizer(image[:, :, ::-1], MetadataCatalog.get(self.cfg.DATASETS.TRAIN[0]), scale=1.2)
            output=viz.draw_instance_predictions(predictions["instances"].to("cpu"))
        else :
            predictions,segmentInfo=self.predictor(image)["panoptic_seg"]
            viz=Visualizer(image[:,:,::-1],MetadataCatalog.get(self.cgf.DATASETS.TRAIN[0]))
            output=viz.draw_panoptic_seg_predictions(predictions.to("cpu"),segmentInfo)


        cv2.imshow("Result",output.get_image()[:,:,::-1])
        cv2.waitKey(0)
        
from  Detectron import *

detector= Detector(model_type="OD")
detector.onImage("A.jpg")

[Aayushjshah]

predictions,segmentInfo=self.predictor(image)["panoptic_seg"]
Here , predictions will be a python dictionary . You can explore it .