Hi, thank you for your great work. I want to run your tracker, especially RGBT model on a custom video, I want to use video_demo.py like OSTrack, but when I use it to run the tracker on my video I see this error:
Traceback (most recent call last): File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 43, in <module> main() File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 39, in main run_video(args.tracker_name, args.tracker_param, args.videofile, args.optional_box, args.debug, args.save_results) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 20, in run_video tracker.run_video(videofilepath=videofile, optional_box=optional_box, debug=debug, save_results=save_results) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/evaluation/tracker.py", line 203, in run_video tracker.initialize(frame, _build_init_info(optional_box)) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/tracker/vipt.py", line 46, in initialize template = self.preprocessor.process(z_patch_arr) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/tracker/data_utils.py", line 23, in process img_tensor_norm = ((img_tensor / 255.0) - self.mean) / self.std # (1,6,H,W) RuntimeError: The size of tensor a (3) must match the size of tensor b (6) at non-singleton dimension 1
please help me solve this or show me another way to run the tracker on my video.
Hi, thank you for your great work. I want to run your tracker, especially RGBT model on a custom video, I want to use video_demo.py like OSTrack, but when I use it to run the tracker on my video I see this error:
Traceback (most recent call last): File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 43, in <module> main() File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 39, in main run_video(args.tracker_name, args.tracker_param, args.videofile, args.optional_box, args.debug, args.save_results) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/video_demo.py", line 20, in run_video tracker.run_video(videofilepath=videofile, optional_box=optional_box, debug=debug, save_results=save_results) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/evaluation/tracker.py", line 203, in run_video tracker.initialize(frame, _build_init_info(optional_box)) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/tracker/vipt.py", line 46, in initialize template = self.preprocessor.process(z_patch_arr) File "/media/strh/MyDrive/Track/OtherTracking/ViPT/tracking/../lib/test/tracker/data_utils.py", line 23, in process img_tensor_norm = ((img_tensor / 255.0) - self.mean) / self.std # (1,6,H,W) RuntimeError: The size of tensor a (3) must match the size of tensor b (6) at non-singleton dimension 1please help me solve this or show me another way to run the tracker on my video.