Problems in the inference stage

[italosalgado14]

Hello and thanks for the code! I am trying to run the sample code of the algorithm, but I find problems at the inference stage. I can't track it because it doesn't throw me any associated errors.

(env) laila@laila:~/MEVA$ python scripts/run_meva_on_video.py --cfg train_meva_2 --vid_file zen_talking_phone.mp4 --output_folder results/output --exp train_meva_2 /home/laila/Nexar/MEVA/meva/utils/transformations.py:1927: UserWarning: No module named 'meva.utils._transformations' warnings.warn(str(err)) Running "ffmpeg -i zen_talking_phone.mp4 -f image2 -v error /tmp/zen_talking_phone_mp4/%06d.png" Images saved to "/tmp/zen_talking_phone_mp4" Input video number of frames 900 Running Multi-Person-Tracker 100%|███████████████████████████████████████████| 75/75 [00:44<00:00, 1.70it/s] Finished. Detection + Tracking FPS 20.40 loading VAErecV2 model from checkpoint: results/meva/vae_rec_2/models/model_1000.p Loaded pretrained weights from "results/meva/train_meva_2/model_best.pth.tar" Running MEVA on each tracklet... 0%| | 0/1 [00:00<?, ?it/s]Terminado (killed)

If anyone has any idea why this error is due, or how to show in more detail that it does not work, I would be grateful!