How do you train Huggingface Maskformer for instance segmentation?
Question:
I can see an example to train for semantic segmentation but I’m unclear how to fine tune a model for instance segmentation. Specifically how to calculate the loss function assuming the data is in COCO format?
Answers:
I found a bunch of examples that are uploaded here: https://github.com/NielsRogge/Transformers-Tutorials
I can see an example to train for semantic segmentation but I’m unclear how to fine tune a model for instance segmentation. Specifically how to calculate the loss function assuming the data is in COCO format?
I found a bunch of examples that are uploaded here: https://github.com/NielsRogge/Transformers-Tutorials