New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Number of classes much greater than the number of unique predictions obtained #66
Comments
Hi @deshanadesai, Thank you for your interest. Hard to say since I don't know which dataset you're using. In order to discover what the model has learned I would take a look at few clusters and a few neighbors. You can also compare it to KMeans clustering. It might be that you don't have enough images in your dataset to find reliable clusters or that the settings for the pretext task are not ideal (i.e. duration of training, augmentation strategy, etc.) for your particular problem. |
I'm having this probem too, and I've found out that neighbors after runing pretext task are incorrect. Just don't know how to adjust it.(I'm using moco.py, image size is larger than 224*224) |
I am also experiencing the same issue @wvangansbeke can you please skim through my pretext config file. Setupsetup: simclr Modelbackbone: resnet50 Datasettrain_db_name: batsnet Losscriterion: simclr Hyperparametersepochs: 30 Transformationsaugmentation_strategy: batsnet_strategy transformation_kwargs: |
and good luck with NeurIPS. :-) |
Hi @arbab97, That looks okay. Since the amount classes is only 5 in your dataset I don't think this should really be a problem then. What are the entropy loss and consistency loss? Are the losses going down? What kind of data are you using? What do you get with KMeans? |
If there are still issues, let me know. I'm closing this for now. |
Hi! Hope you are doing well, I enjoyed reading this paper and the code. I was trying to adapt this method to my own task on a custom dataset. Something strange i noticed for my task was:
Even with a high number of classes given as input to the model, eg. 1024, the predictions produced by the model had only 34 unique values:
Do you think this is possible when faced with a large amount of overclustering?
Would highly appreciate your input.
Thank you,
Deshana
The text was updated successfully, but these errors were encountered: