webcam-------------------> export PYTHONIOENCODING=utf-8;python tools/demo.py webcam ....--conf 0.25 --nms 0.45 --tsize 640 --save_result --device gpu

Traceback (most recent call last):
File "/data/my_cv/YOLOX/tools/demo.py", line 306, in
main(exp, args)
File "/data/my_cv/YOLOX/tools/demo.py", line 274, in main
model.load_state_dict(ckpt["model"])
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for YOLOX:
size mismatch for head.cls_preds.0.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 128, 1, 1]).
size mismatch for head.cls_preds.0.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([20]).
size mismatch for head.cls_preds.1.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 128, 1, 1]).
size mismatch for head.cls_preds.1.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([20]).
size mismatch for head.cls_preds.2.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 128, 1, 1]).
size mismatch for head.cls_preds.2.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([20]).

while True:
        ret_val, frame = cap.read()
        if ret_val:
            outputs, img_info = predictor.inference(frame)
            result_frame, _ = predictor.visual(outputs[0], img_info, predictor.confthre)
            cv2.imshow("det2022",result_frame)
            if args.save_result:
                vid_writer.write(result_frame)
            ch = cv2.waitKey(1)
            if ch == 27 or ch == ord("q") or ch == ord("Q"):
                break
        else:
            break

Start in tools/demo.py at the model.load_state_dict call and reproduce the supplied webcam command. Inspect how the experiment and checkpoint are selected, then verify that their class counts agree so loading completes and webcam inference starts successfully.