Open TalalWasim opened 1 month ago
Hi,
I had a question regarding the augmentation strategy used between tiny and small variants. There are two different arguments used in tiny variant for the image model that are not used for the small variant as below:
--clip-grad 5.0 --no-repeated-aug --aa v0
Is there any particular reason for this?
Good question~ For the tiny model (<10M), the best practice is to use weaker augmentation.
As for the --clip-grad, it's not a key.
--clip-grad
Hi,
I had a question regarding the augmentation strategy used between tiny and small variants. There are two different arguments used in tiny variant for the image model that are not used for the small variant as below:
--clip-grad 5.0 --no-repeated-aug --aa v0
Is there any particular reason for this?