plotted points are not matching what is known from DLC analyze_videos #7

Activity

1. MMathisLab

   added

   bugSomething isn't workingSomething isn't working

   on Jul 10, 2020
2. MMathisLab

   assigned

   AlexEMG

   and

   jeylau

   on Jul 10, 2020
3. MMathisLab commented on Jul 10, 2020

   

   MMathisLab

   on Jul 10, 2020

   MemberAuthor

   More actions

   you can test this with any model zoo, simple download by:

   import deeplabcut
   import urllib.request
   import tarfile
   from tqdm import tqdm
   from deeplabcut.utils import auxiliaryfunctions
   modelname = 'full_cat'
   deeplabcut.utils.auxfun_models.DownloadModel(modelname, '/content/')

   👀React with 👀1Reacted by Jessy Lauer
4. MMathisLab commented on Jul 10, 2020

   

   MMathisLab

   on Jul 10, 2020

   MemberAuthor

   More actions

   @gkane26 can you elaborate how you've tried to fix this? WE said try the non-pb files, right, but how do I point to only those, as in dlclive.anv you point to a folder
5. gkane26 commented on Jul 10, 2020

   

   gkane26

   on Jul 10, 2020

   Collaborator

   More actions

   I haven't yet tried loading the snapshot file -- can't do that in DLC-live because you need a lot of DLC functions to recreate the network, then load the weights. I can try doing so this afternoon, but what that amounts to is essentially just running DLC's analyze_videos. I think the issue has to be that we're either choosing the wrong input/output nodes in DLC export.py or in dlclive.graph.py. I've tried some different combinations of but I'm pretty sure it's using the correct ones now
6. MMathisLab commented on Jul 10, 2020

   

   MMathisLab

   on Jul 10, 2020

   MemberAuthor

   More actions

   I think @AlexEMG is looking into the TF graph business now
7. MMathisLab

   closed this as completedon Jul 13, 2020
8. sneakers-the-rat commented on Jul 14, 2020

   

   sneakers-the-rat

   on Jul 14, 2020

   Collaborator

   More actions

   I think this needs a fix! I was experiencing this all day today and had resigned myself to thinking I was doing something wrong -- the numbers from dlc proper (specifically those in the plot.png generated from plot trajectories) were pretty consistently wrong from the numbers dlclive was giving across multiple models and retraining even when my camera and imaging plane were firmly clamped in place and unchanging. I think it might be an indexing error
9. MMathisLab commented on Jul 14, 2020

   

   MMathisLab

   on Jul 14, 2020

   MemberAuthor

   More actions

   It was fixed in the PR #1 from GK, see discussion