Documentation script for fine-tuning Mask2Former with Trainer does not support instance segmentation with superposed instances

John6666 · February 13, 2025, 2:15pm

Hmm… it seems that your understanding is correct.

github.com/NielsRogge/Transformers-Tutorials

How to train Mask2Former from a COCO json custom dataset?

opened 10:05PM - 20 May 23 UTC

I have my custom dataset as a json in COCO format. The tutorials for MaskForm…er and Mask2Former for Huggingface Vision work with a different custom dataset format (a weird RGB encoding with custom meaning of each channel). Is there a simple Dataset implementation that takes the coco.json file and outputs the data in a format Mask2Former from Huggingface can work with? If not, is there a tutorial to how to convert a COCO JSON custom dataset to a dataset format needed for Huggingface?

Topic		Replies	Views
Custom dataset for MaskFormer and Mask2Former Beginners	3	505	October 17, 2024
Custom dataset for Mask2Former finetuning 🤗Datasets	2	2243	November 23, 2023
Dataset for Mask2former 🤗Datasets	1	171	October 9, 2024
Can the image processor for instance segmentation be adapted to work with stacks of masks? 🤗Transformers	0	16	March 2, 2025
Custom dataset maskformer Intermediate	15	92	January 18, 2025

Documentation script for fine-tuning Mask2Former with Trainer does not support instance segmentation with superposed instances

Related topics