yoxu515 / aot-benchmark

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
BSD 3-Clause "New" or "Revised" License
600 stars 108 forks source link

How to run only main training without pre-training #43

Closed fiskrt closed 1 year ago

fiskrt commented 1 year ago

I would like to train a model purely on ytVOS and DAVIS. I.e I would like a stage ytb_dav. Is this possible?

yoxu515 commented 1 year ago

Yes, you might do this by adding a new config. Similar to configs/ytb.py, a ytb_dav.py may meet your demond. self.STAGE_NAME = 'YTB_DAV' self.DATASETS = ['youtubevos', 'davis2017']