test

.gitattributes

@@ -1,35 +1,27 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,75 @@
 ---
-title: Homework2
-emoji: 😻
-colorFrom: gray
-colorTo: yellow
-sdk: gradio
-sdk_version: 4.2.0
-app_file: app.py
-pinned: false
+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
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 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

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "road",
+    "1": "sidewalk",
+    "2": "building",
+    "3": "wall",
+    "4": "fence",
+    "5": "pole",
+    "6": "traffic light",
+    "7": "traffic sign",
+    "8": "vegetation",
+    "9": "terrain",
+    "10": "sky",
+    "11": "person",
+    "12": "rider",
+    "13": "car",
+    "14": "truck",
+    "15": "bus",
+    "16": "train",
+    "17": "motorcycle",
+    "18": "bicycle"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "bicycle": 18,
+    "building": 2,
+    "bus": 15,
+    "car": 13,
+    "fence": 4,
+    "motorcycle": 17,
+    "person": 11,
+    "pole": 5,
+    "rider": 12,
+    "road": 0,
+    "sidewalk": 1,
+    "sky": 10,
+    "terrain": 9,
+    "traffic light": 6,
+    "traffic sign": 7,
+    "train": 16,
+    "truck": 14,
+    "vegetation": 8,
+    "wall": 3
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "SegformerFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "reduce_labels": false,
+  "resample": 2,
+  "size": 1024
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7c40538e41d92f93ad6501d54e6333833a1d96bda7b0906c7255240e927832
+size 54810145

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a35d0c9e60f4b22d61048dcdce7f7b0b2d9b10ad60da852ace2b4ccf541bfe
+size 55007948