search

microsoft / ProDA

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)
https://arxiv.org/abs/2101.10979
MIT License
286 stars 44 forks source link

Amount of epochs for both source only and warm-up stage #21

Closed fabriziojpiva closed 3 years ago

fabriziojpiva commented 3 years ago

Hi, I am trying to reproduce the full pipeline from the very beginning, i.e. starting from training the model only with the source dataset, then doing the warm-up stage and so on.

Could you provide more information about the amount of epochs or iterations that you trained the model for the following stages:

  1. Source only
  2. Warm-up

Thanks for the help.

panzhang0212 commented 3 years ago

Hi, the training iterations of the two stages are the same with the stage 1/2/3. In my experience, you could directly train the warm-up stage (init from ImageNet), which is comparable with Source only + Warm-up.

valencebond commented 3 years ago

hi, @fabriziojpiva @panzhang0212 how can I train a model only with the source datasets? Can you provide some scripts that I can refer to? thanks