[SegFormer] Remove unused attributes (#16285)

* Remove unused attributes

* Add link to blog and add clarification about input size

* Improve readability of the code

Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>

docs/source/model_doc/segformer.mdx

@@ -50,7 +50,8 @@ Tips:
   ADE20K, Cityscapes and COCO-stuff, which are important benchmarks for semantic segmentation. All checkpoints can be
   found on the [hub](https://huggingface.co/models?other=segformer).
 - The quickest way to get started with SegFormer is by checking the [example notebooks](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/SegFormer) (which showcase both inference and
-  fine-tuning on custom data).
+  fine-tuning on custom data). One can also check out the [blog post](https://huggingface.co/blog/fine-tune-segformer) introducing SegFormer and illustrating how it can be fine-tuned on custom data.
+- SegFormer works on any input size, as it pads the input to be divisible by `config.patch_sizes`. 
 - One can use [`SegformerFeatureExtractor`] to prepare images and corresponding segmentation maps
   for the model. Note that this feature extractor is fairly basic and does not include all data augmentations used in
   the original paper. The original preprocessing pipelines (for the ADE20k dataset for instance) can be found [here](https://github.com/NVlabs/SegFormer/blob/master/local_configs/_base_/datasets/ade20k_repeat.py). The most