search

mlfpm / deepof

DeepLabCut based data analysis package including pose estimation and representation learning mediated behavior recognition
MIT License
39 stars 6 forks source link

Tutorial stalls on Google Colab #18

Closed cellistigs closed 1 year ago

cellistigs commented 1 year ago

Hello,

When I attempt to run the tutorial depot_preprocessing.ipynb, the step my_deepof_project = my_deepof_project.create(force=True) is extremely slow (currently has been running for 30 minutes). My assumption is that this is not the intended behavior of this code: if it is, it would be good to indicate somewhere that this step can be very time consuming (I've had 2 previous timeouts of my google colab session on this step).

Screen Shot 2023-05-29 at 4 43 29 PM
cellistigs commented 1 year ago

https://github.com/openjournals/joss-reviews/issues/5394

lucasmiranda42 commented 1 year ago

The code is behaving as intended, but area computing is indeed slow. The cell takes around 6 min to run locally on a MacBook Pro 2022, but it's too slow in colab. I added a warning in the tutorial. Bear in mind that results can be loaded a few cells below (using deepof.data.load_project()).

Best, and hope this helps! I'm closing the issue, but let me know if you have further demands in this regard :)