How to get the confidence score of all class for a bounding box while using pretrained object detector in pytorch

1

for a pretrained object detection model in pytorch and for each bounding box predicted by the model how to get the confidence score for each of the 80 COCO classes for that bounding box?

I have put the code I am using for object detection using pretrained fasterRCNN Resnet-50 FPN model

    img = Image.open(img_path) # Load the image
    transform = transforms.Compose([transforms.ToTensor()]) # Defing PyTorch Transform
    img = transform(img) # Apply the transform to the image
    pred = model([img.cuda()]) # Pass the image to the model
    pred_class = [COCO_INSTANCE_CATEGORY_NAMES[i] for i in list(pred[0]['labels'].cpu().numpy())] # Get the Prediction Score
    pred_boxes = [[(i[0], i[1]), (i[2], i[3])] for i in list(pred[0]['boxes'].cpu().detach().numpy())] # Bounding boxes
    pred_score = list(pred[0]['scores'].cpu().detach().numpy())

pred only provides all possible bounding boxes and the best possible class for the bounding box but how to get the confidence score for all possible classes for one bounding box?

Any help will be highly appreciated.