You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, first of all thanks for your awesome repository. I was looking at the documentation but I couldn't find a list of training arguments or config files to train any given model.
I'm particularly interested in a CLI training script with the whole list of settings or yaml file to directly run and reproduce the training from:
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers -- https://arxiv.org/abs/2106.10270
For example this one (vit_base_patch16_224 with 84.526 top-1 accuracy)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello, first of all thanks for your awesome repository. I was looking at the documentation but I couldn't find a list of training arguments or config files to train any given model.
I found this in general:
https://rwightman.github.io/pytorch-image-models/scripts/
And this one for some specific examples:
https://rwightman.github.io/pytorch-image-models/training_hparam_examples/
But I'm wondering if is there anywhere I can find the whole list of hyperparameters used to train the models on this table (https://github.com/rwightman/pytorch-image-models/blob/master/results/results-imagenet.csv)
I'm particularly interested in a CLI training script with the whole list of settings or yaml file to directly run and reproduce the training from:
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers -- https://arxiv.org/abs/2106.10270
For example this one (vit_base_patch16_224 with 84.526 top-1 accuracy)
Thanks.
Beta Was this translation helpful? Give feedback.
All reactions