-
Hi!
I had tried a slightly modified version of BYOL on cifar-10/100. The results of additional class-classifier used in pretraining are 1% (cifar-10) and 6% (cifar-100) better than the classifier t…
-
Related to #712
Below I've gone through all the different modules available, and come up with a list of deprecated modules. I've been lenient in my choices, primarily to allow some discussions if …
-
Hi, thanks for your impressive work!
During the BYOL experiment on your codes(Imagenet-100, resnet18, 200epochs, same hyper-params as bash_files), it seems that the performance degenerated a lot i…
-
Thanks for your excellent work!
And in your paper, you made a lot of comparisons with BYOL, Moco and Swav,
I am grateful if you can release your implement code of BYOL, moco and swav.
-
Hello, thanks for sharing your library.
I was trying to toy with DALI and I didn't succeed to retrieve the results as in torchvision when I found your very well structured code. When I checked your…
-
- [x] Metrics @gabeorlanski
- [x] Tensorboard #55
- [x] Logging
- [x] DynamicScaling @ryanccarelli #52
- [x] Gradient Accumulation @AkashGanesan #56
- [x] Checkpointing @ryanccarelli #55
- […
-
This is the template parameter file location
https://github.com/F5Networks/f5-azure-arm-templates/blob/main/supported/failover/same-net/via-api/n-nic/existing-stack/byol/azuredeploy.parameters.json
…
-
I use byol-pytorch-master/examples/lightning/train.py to generate ckpt locally after training, but when I load ckpt, there will be the following errors. How should I load it? Thanks a lot!
-
Thank you so much for open-sourcing! The code looks extremely clean and nice. It is a great service to the community!
Would you also open-source the improved implementations of BYOL, SWAV, SimCLR …
-
Thanks for your great work! Now I encounter a tricky problem:
Size of input x is [1024, 12, 7500], but after running 'image_one, image_two = self.augment1(x), self.augment2(x)' in line 195 of byol_p…