MCG-NJU / VideoMAE

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://arxiv.org/abs/2203.12602
Other
1.39k stars 137 forks source link

[Fix] fix two bugs about training and test #82

Closed congee524 closed 1 year ago

congee524 commented 1 year ago

Fix two bugs 1) wrong num_training_steps_per_epoch: Early termination of training due to integer rounding problems 2) only save top1 result when testing