README.md

@@ -1,75 +0,0 @@
----
-license: other
-tags:
-- vision
-- image-segmentation
-datasets:
-- cityscapes
-widget:
-- src: https://cdn-media.huggingface.co/Inference-API/Sample-results-on-the-Cityscapes-dataset-The-above-images-show-how-our-method-can-handle.png
-  example_title: Road
----
-
-# SegFormer (b1-sized) model fine-tuned on CityScapes
-
-SegFormer model fine-tuned on CityScapes at resolution 1024x1024. It was introduced in the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203) by Xie et al. and first released in [this repository](https://github.com/NVlabs/SegFormer). 
-
-Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team.
-
-## Model description
-
-SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a downstream dataset.
-
-## Intended uses & limitations
-
-You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?other=segformer) to look for fine-tuned versions on a task that interests you.
-
-### How to use
-
-Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
-
-```python
-from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
-from PIL import Image
-import requests
-
-feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
-model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
-
-url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
-
-inputs = feature_extractor(images=image, return_tensors="pt")
-outputs = model(**inputs)
-logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
-```
-
-For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/segformer.html#).
-
-### License
-
-The license for this model can be found [here](https://github.com/NVlabs/SegFormer/blob/master/LICENSE).
-
-### BibTeX entry and citation info
-
-```bibtex
-@article{DBLP:journals/corr/abs-2105-15203,
-  author    = {Enze Xie and
-               Wenhai Wang and
-               Zhiding Yu and
-               Anima Anandkumar and
-               Jose M. Alvarez and
-               Ping Luo},
-  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
-               Transformers},
-  journal   = {CoRR},
-  volume    = {abs/2105.15203},
-  year      = {2021},
-  url       = {https://arxiv.org/abs/2105.15203},
-  eprinttype = {arXiv},
-  eprint    = {2105.15203},
-  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
-  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
-  bibsource = {dblp computer science bibliography, https://dblp.org}
-}
-```

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "SegformerForSemanticSegmentation"
+    "SegformerForImageSegmentation"
   ],
   "attention_probs_dropout_prob": 0.0,
   "classifier_dropout_prob": 0.1,

preprocessor_config.json

@@ -1,5 +1,12 @@
 {
+  "align": false,
+  "crop_size": [
+    512,
+    512
+  ],
   "do_normalize": true,
+  "do_pad": true,
+  "do_random_crop": false,
   "do_resize": true,
   "feature_extractor_type": "SegformerFeatureExtractor",
   "image_mean": [
@@ -7,12 +14,19 @@
     0.456,
     0.406
   ],
+  "image_scale": [
+    512,
+    512
+  ],
   "image_std": [
     0.229,
     0.224,
     0.225
   ],
-  "reduce_labels": false,
+  "keep_ratio": false,
+  "padding_value": 0,
+  "reduce_zero_label": false,
   "resample": 2,
-  "size": 1024
+  "segmentation_padding_value": -100,
+  "size_divisor": 32
 }