| The zero-index is replaced by 255 so it's ignored by SegFormer's loss function: | |
| from transformers import AutoImageProcessor | |
| checkpoint = "nvidia/mit-b0" | |
| image_processor = AutoImageProcessor.from_pretrained(checkpoint, reduce_labels=True) | |
| It is common to apply some data augmentations to an image dataset to make a model more robust against overfitting. |