You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I would like to train a model for instance segmentation to detect instances that haven't been trained on yet (e.g. like the balloon example on the Detectron2 Tutorial colab). The one difference between the balloon example and what I'd like to accomplish is that I want to add to the existing thing_classes from the model zoo. Is this feasible?
For example, in this image I've attached below, the balloons are nicely identified, but the people, bottles, chairs, etc. are not.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I would like to train a model for instance segmentation to detect instances that haven't been trained on yet (e.g. like the balloon example on the Detectron2 Tutorial colab). The one difference between the balloon example and what I'd like to accomplish is that I want to add to the existing
thing_classes
from the model zoo. Is this feasible?For example, in this image I've attached below, the balloons are nicely identified, but the people, bottles, chairs, etc. are not.

Beta Was this translation helpful? Give feedback.
All reactions