guarin
guarin
@JanumalaAkhilendra did you already have time to look into this?
@pearguacamole this issue would be free again if you are still interested in working on it. You can follow the structure from this PR #1694 but instead of modifying the...
Hi! Thanks for looking into this! Transforms should be added to `lightly/transforms`. The gaussian blur transform is a good example: https://github.com/lightly-ai/lightly/blob/master/lightly/transforms/gaussian_blur.py Please also add minimal tests to `tests/transforms`. It can...
Hi! None of the transforms have been implemented so far, so all of them are still up for grabs. @KekmaTime did you already have time to look into this?
Hi, I created issues for the different transforms. Please indicate which transform you would like to work on and I can assign the issue to you :) Will add more...
@belloibrahv I added some more information to the issue description, hopefully this clarifies your questions :) Regarding edge cases I wouldn't worry too much, as long as it works for...
Hi, batch size 8192 is quite big even for 4 GPUs (the original paper used batch size 4096 on 128 TPUs). Are you using CIFAR (32x32) or normal ImageNet sized...
I just tested it on 4x24GB GPUs and it indeed fails with OOM. I had to reduce the batch size to 4096 for it to succeed. I think this is...
Feel also free to open a PR if you would like to contribute. Loss functions and transforms are usually a great start. Once we have those we can put everything...
Hi and thanks for working on this! Could you quickly indicate on which files you would work?