Why do the masks' positions on the visualized images are same? about mae HOT 4 CLOSED

Yes, these images are just the first 16 images on the cifar10 validation dataset. I didn't shuffle the dataset since I want to see how reconstruction gets better as we trained longer.

from mae.

Yes, these images are just the first 16 images on the cifar10 validation dataset. I didn't shuffle the dataset since I want to see how reconstruction gets better as we trained longer.

Sorry, maybe I didn't express the question clearly. My question is not about the selected 16 images from the dataset, but the reason why are those masks positions same? Theoretically, these masked patches should be shuffled randomly.

from mae.

Oh, I see.

Yes, the patches are shuffled randomly, and you can verify that by checking the visualization for different epochs (just scroll the tensorboard).

However, you get the same result as mine is because we fix the random seed at the beginning, which controls all the randomness. That is, if you run the code without changing the default random seed, you get exactly the same result I got, even for the positions that were masked in the last visualization.

from mae.

Oh, I see.

Yes, the patches are shuffled randomly, and you can verify that by checking the visualization for different epochs (just scroll the tensorboard).

However, you get the same result as mine is because we fix the random seed at the beginning, which controls all the randomness. That is, if you run the code without changing the default random seed, you get exactly the same result I got, even for the positions that were masked in the last visualization.

I see. Thank you very much!

from mae.