-
Hi Ayush and Sayak,
I read your blog on wandb and find it interesting to see the performance on a relatively small dataset. Great work!
I am trying to reproduce your results with the official swAV…
-
This is definitely a topic where it will come down to your personal preference.
_In my opinion_, I would remove the initialization of the augmentation functions in the callbacks.
### From a new us…
-
Hi! Thanks for sharing this repo -- really clean and easy to use.
When training using the PyTorch Lightning script from the repo, my loss is negative (and gets more negative over time) when trainin…
-
Hi, I used your example on my own data. The training loss decreased and then increased after 100 epochs, which is wired. Did you meet similar situations? Is it hard to train the model?
the batchsize …
-
Hi,
Thanks for open sourcing this. It is very helpful. I am in the process of converting the BYOL R50x1 weights to PyTorch. I have been able to get the dimensions of the weights to match with the s…
-
https://github.com/deepmind/deepmind-research/tree/master/byol#running-a-short-pre-training-locally
In the case of byol trained on 40 epochs, what performance can you expect from linear evaluation?
-
## Do you already have an issue opened with F5 support?
Yes, but they said they could not help: C3358308
## Description
Describe the problem you're having or the enhancement you'd like to reque…
-
This is an outstanding project and sorry to bother you again.
I notice that the hyparameters setting reported in byol paper are different between training in 1000 epochs and training in 300 epochs (0…
-
Most (okt. 8) csütörtökön 15h-tól Intézeti értekezlet lesz, az intézetigazgató jelöltek meghallgatása, illik ott lennem. H avan téma, tarthatjátok nélkülem is, vagy ha alkalmas mindenkinek, kivételese…
-
Hi Kerem,
Thanks for sharing your code and results on imagewang. It was motivating to see positive results on a smaller dataset.
In the last week, I was comparing your swav implementation with the…