Skip to content

Problems in the inference stage #9

Description

@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!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions