search

OpenGVLab / VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
https://arxiv.org/abs/2303.16727
MIT License
527 stars 63 forks source link

Clarification on published logs. #32

Closed SushantGautam closed 1 year ago

SushantGautam commented 1 year ago

In the log from the link in Google Sheets at vit_g_hybrid_pt_1200e_log.txt The epoch is only up to 300. It should be up to 1200, isn't it? The loss seems to have just been settled to ~0.52. Is this correct?

I would love it if you could publish the weight for the base variant as well.

congee524 commented 1 year ago

We use repeated augmentation (and set it to 4), so the model will see videos four times each epoch.

loss is correct.