no .torch file. file not found error

[usernamex1x23]

i clossed the last issue after i found out that it had already been ans but the solution did not work for me. i downloaded both yolov3 files

but when i went to c/user/{user name}/.torch

i found out there was no .torch file i made a new folder name it .torch added models and config folders and copied the respected yolov3 filles in each

tried running python demo_alter.py --vid_file sample_video.mp4 --output_folder output/ --display nothing same error closed the prompt re-opened it. double checked that it was in admin. reinstalled everything nothing same error copy past of error (venv_vibe) D:\video\3\4>python demo_alter.py --vid_file sample_video.mp4 --output_folder output/ --display Running "ffmpeg -i sample_video.mp4 -f image2 -v error /tmp\sample_video_mp4/%06d.png" Traceback (most recent call last): File "demo_alter.py", line 405, in main(args) File "demo_alter.py", line 72, in main image_folder, num_frames, img_shape = video_to_images(video_file, return_info=True) File "D:\video\3\4\lib\utils\demo_utils.py", line 195, in video_to_images subprocess.call(command) File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 339, in call with Popen(*popenargs, **kwargs) as p: File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 800, in init restore_signals, start_new_session) File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 1207, in _execute_child startupinfo) FileNotFoundError: [WinError 2] The system cannot find the file specified

[carlosedubarreto]

I dont know if I'm understanding correctly, but seems like the demo_alter didnt find the sample_video.mp4 file are you running it from the root directory where there is the sample_video.mp4 file?

Asking it just to be sure, because, I dont have an idea of what else could be the problem,,,

[usernamex1x23]

yep the same folder where both vibe files where extracted .

Unpack the VIBE github pack to a folder

https://github.com/mkocabas/VIBE/archive/master.zip

unpack the contents of this github to the same folder

https://github.com/carlosedubarreto/vibe_win_install/archive/main.zip

i double checked the the sample video file is in that folder

[carlosedubarreto]

What about the ffmpeg "installation"? Maybe the script is trying to use ffmepg but you hada problem to add ffmepg library folder on the windows path. So when it tries to run FFMPEG it says that cant find it.

So, please double check the ffmpeg "installation"

with instalation i mean, unpacking the zip file and add the ffmpeg executable folder to windows path.

[usernamex1x23]

i had installed frankmocap before so i thought i already had done the step i followed the instruction from the video again and ran into this error

(base) D:\video\3\4>conda activate venv_vibe

(venv_vibe) D:\video\3\4>python demo_alter.py --vid_file sample_video.mp4 --output_folder output/ --display Running "ffmpeg -i sample_video.mp4 -f image2 -v error /tmp\sample_video_mp4/%06d.png" Images saved to "/tmp\sample_video_mp4" Input video number of frames 300 Downloading files from https://pjreddie.com/media/files/yolov3.weights Traceback (most recent call last): File "demo_alter.py", line 405, in main(args) File "demo_alter.py", line 93, in main yolo_img_size=args.yolo_img_size, File "D:\Newfolder\envs\venv_vibe\lib\site-packages\multi_person_tracker\mpt.py", line 53, in init device=self.device, img_size=yolo_img_size, person_detector=True, video=True, return_dict=True File "D:\Newfolder\envs\venv_vibe\lib\site-packages\yolov3\yolo.py", line 32, in init download_url(url, outdir) File "D:\Newfolder\envs\venv_vibe\lib\site-packages\yolov3\yolo.py", line 11, in download_url subprocess.call(cmd) File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 339, in call with Popen(*popenargs, **kwargs) as p: File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 800, in init restore_signals, start_new_session) File "D:\Newfolder\envs\venv_vibe\lib\subprocess.py", line 1207, in _execute_child startupinfo) FileNotFoundError: [WinError 2] The system cannot find the file specified

[usernamex1x23]

deleting and remaking .torch folder fixed the above problem but i ran into a new error.

(venv_vibe) D:\video\3\4>python demo_alter.py --vid_file sample_video.mp4 --output_folder output/ --display Running "ffmpeg -i sample_video.mp4 -f image2 -v error /tmp\sample_video_mp4/%06d.png" Images saved to "/tmp\sample_video_mp4" Input video number of frames 300 Running Multi-Person-Tracker 100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [01:45<00:00, 1.02s/it] Finished. Detection + Tracking FPS 2.84 Displaying results.. WARNING: You are using a SMPL model, with only 10 shape coefficients. Downloading: "https://download.pytorch.org/models/resnet50-19c8e357.pth" to C:\Users\Hp/.cache\torch\checkpoints\resnet50-19c8e357.pth 100%|█████████████████████████████████████████████████████████████████████████████| 97.8M/97.8M [00:42<00:00, 2.39MB/s] WARNING: You are using a SMPL model, with only 10 shape coefficients. => loaded pretrained model from 'data/vibe_data\spin_model_checkpoint.pth.tar' Performance of pretrained model on 3DPW: 56.56075477600098 Loaded pretrained weights from "data/vibe_data/vibe_model_wo_3dpw.pth.tar" Running VIBE on each tracklet... 0%| | 0/1 [00:00<?, ?it/s]Traceback (most recent call last): Traceback (most recent call last): File "", line 1, in File "demo_alter.py", line 405, in File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\spawn.py", line 105, in spawn_main main(args) exitcode = _main(fd) File "demo_alter.py", line 152, in main File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\spawn.py", line 114, in _main for batch in dataloader: prepare(preparation_data) File "D:\Newfolder\envs\venv_vibe\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\spawn.py", line 225, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path run_name="mp_main") File "D:\Newfolder\envs\venv_vibe\lib\runpy.py", line 263, in run_path pkg_name=pkg_name, script_name=fname) File "D:\Newfolder\envs\venv_vibe\lib\runpy.py", line 96, in _run_module_code mod_name, mod_spec, pkg_name, script_name) File "D:\Newfolder\envs\venv_vibe\lib\runpy.py", line 85, in run_code exec(code, run_globals) File "D:\video\3\4\demo_alter.py", line 22, in import torch File "D:\Newfolder\envs\venv_vibe\lib\site-packages\torch_init.py", line 81, in from torch._C import * ImportError: DLL load failed: The paging file is too small for this operation to complete. return _MultiProcessingDataLoaderIter(self) File "D:\Newfolder\envs\venv_vibe\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init w.start() File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\process.py", line 112, in start self._popen = self._Popen(self) File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\popen_spawn_win32.py", line 89, in init reduction.dump(process_obj, to_child) File "D:\Newfolder\envs\venv_vibe\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) BrokenPipeError: [Errno 32] Broken pipe Exception ignored in: <function tqdm.del at 0x000001C902E0D558> Traceback (most recent call last): File "D:\Newfolder\envs\venv_vibe\lib\site-packages\tqdm_tqdm.py", line 931, in del self.close() File "D:\Newfolder\envs\venv_vibe\lib\site-packages\tqdm_tqdm.py", line 1133, in close self._decr_instances(self) File "D:\Newfolder\envs\venv_vibe\lib\site-packages\tqdm_tqdm.py", line 496, in _decr_instances cls.monitor.exit() File "D:\Newfolder\envs\venv_vibe\lib\site-packages\tqdm_monitor.py", line 52, in exit self.join() File "D:\Newfolder\envs\venv_vibe\lib\threading.py", line 1041, in join raise RuntimeError("cannot join current thread") RuntimeError: cannot join current thread

[carlosedubarreto]

Sorry, I didnt encontered this error before... or I dont remember it. I suggest to take a look at vibes github page, because it seems that it is an issue related to the use of their code. I'm just trying to make easier to install the dependencies...

link to their issue page https://github.com/mkocabas/VIBE/issues

[usernamex1x23]

thks mate

[h0000c]

I also encountered a similar problem, I am sure I have added the ffmpeg executable folder to windows path.

1. Are you running on win10?
2. How to delete and recreate the .torch folder? Thank you very much if you can spend your precious time advising you.

[carlosedubarreto]

Hi @h0000c , sorry for the late answer... Today my day is very busy 😅

I saw your previous question, maybe solving that other problem might resolve this issue you are having here.

I added the answer on the other question, but to help other people in the future, I'll also leave it here https://github.com/carlosedubarreto/vibe_win_install/issues/5

[doyoumissme]

I encountered the same problem, did you solve it?