Hello, I am trying to train segformer model with my custom dataset. I have 46 different classes. My problem is my dataset labels are encoded pixel and there is multiple classes in one image. How I will generate the mask images for segformer like the example they share?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| SegformerFeatureExtractor not working as expected - Feature extractor not returning the label object | 0 | 280 | August 26, 2023 | |
| Fine Tuning Segformer on Custom Dataset, getting negative loss | 1 | 510 | October 20, 2023 | |
| SegformerFeatureExtractor - Feature extractor not returning the label object | 0 | 328 | August 29, 2023 | |
| SegFormer fine-tuned on personal dataset problem on loss computation | 0 | 188 | September 9, 2023 | |
| How do I create a Image Segmentation Dataset | 26 | 9014 | April 11, 2024 |