search

OpenGVLab / VideoMAEv2

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

How to train my own dataset? #30

Closed wang9danzuishuai closed 1 year ago

wang9danzuishuai commented 1 year ago

I want to do some experiments on my own dataset, using the fine-tuning method. But in the training script, the param 'data_set' only contains some open datasets. My dataset only has 10 classes. If I changed the --nb_class to 10, an AssertionERROR will raise. After skipping this assertion, my dataset starts to train but the ACC@1 is always 0%. So is there something that I should do correctly train my own dataset?

wang9danzuishuai commented 1 year ago

Sorry to bother you, I have found the way:)

Muhammad-k02 commented 1 year ago

Sorry to bother you, I have found the way:)

Do you mind elaborating on how you got your custom dataset trained?