Finetune on new data
Closed this issue · 3 comments
HM102 commented
Very good paper, thank you for the release.
How much data do you need to fine tune the model to work on new environment and task?
Jdvakil commented
To fine-tune a pre-trained model, ~25-75 trajectories should be good enough.
We were able to get a new task in a new environment to work with ~25 trajectories fine-tuned
HM102 commented
Thank you for the answer. This was with 4 cameras? did you try with 1 camera on real world data, how was the performance?
Jdvakil commented
We ran exps with 2 cameras + new setup/location and the performance loss was less than 10%