search

KMnP / vpt

❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119
Other
1k stars 91 forks source link

Is train.py not for pretraining ? #33

Closed HuangChiEn closed 8 months ago

HuangChiEn commented 1 year ago

I have saw the issue, so I wonder that this repo did not provide any script or code for pretraining (supervised pretraining, or MAE, MoCo pretraining for imagenet22k) ?

Instead, this repo directly load the pretrained weights and apply for various kind of tuning ? So, train.py is the script for Tuning on VTAB-Structured, VTAB-Natural, VTAB-Specialized subset ? And, tune_vtab.py, tune_fgvc.py are also for Tuning on VTAB-caltech101 subset and CUB dataset, respectively ?

Any clarification will be appreciated!!

KMnP commented 1 year ago

thanks for the question. tune_*.py here, tune means hyper-parameter tuning. This is different from the notion of fine-tuning or visual prompt tuning.

You are correct that this paper does not do any pre-training process.