Find bounding box coordinates from checkpoint (best_ckpt.pth.tar) file

I am trying to predict image and trying to find the bounding box coordinates and class name by loading the pretrained model, please help how to proceed to find the bounding box

##i tried to find the result in that way, but showing error dic

import torch
model = torch.load('/content/drive/MyDrive/Violence_Gun_detection/YOLOX/YOLOX_outputs/yolox_voc_s/best_ckpt.pth.tar')

dir = 'https://github.com/ultralytics/yolov5/raw/master/data/images/'
imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batched list of images

results = model(imgs)
results.print()  
results.save()  # or .show()
print(results.xyxy[0])  # print img1 predictions (pixels)

Start with the checkpoint-loading and model-call lines in the supplied Python snippet, then compare them with YOLOX's documented inference entry points. Verify how best_ckpt.pth.tar is loaded and how predictions are exposed; done means an image produces bounding-box coordinates and class names without the shown error.