first commit

.gitattributes

@@ -1,35 +1,16 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* 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
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz 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
-*.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
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,77 @@
 ---
-title: My Model
-emoji: 🦀
-colorFrom: yellow
-colorTo: green
-sdk: gradio
-sdk_version: 4.1.2
-app_file: app.py
-pinned: false
+license: other
+tags:
+- vision
+- image-segmentation
+datasets:
+- scene_parse_150
+widget:
+- src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg
+  example_title: House
+- src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000002.jpg
+  example_title: Castle
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# SegFormer (b0-sized) model fine-tuned on ADE20k
+
+SegFormer model fine-tuned on ADE20k at resolution 512x512. 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 SegformerImageProcessor, SegformerForSemanticSegmentation
+from PIL import Image
+import requests
+
+processor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
+model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
+
+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 +1,372 @@
+{
+  "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": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "wall",
+    "1": "building",
+    "2": "sky",
+    "3": "floor",
+    "4": "tree",
+    "5": "ceiling",
+    "6": "road",
+    "7": "bed ",
+    "8": "windowpane",
+    "9": "grass",
+    "10": "cabinet",
+    "11": "sidewalk",
+    "12": "person",
+    "13": "earth",
+    "14": "door",
+    "15": "table",
+    "16": "mountain",
+    "17": "plant",
+    "18": "curtain",
+    "19": "chair",
+    "20": "car",
+    "21": "water",
+    "22": "painting",
+    "23": "sofa",
+    "24": "shelf",
+    "25": "house",
+    "26": "sea",
+    "27": "mirror",
+    "28": "rug",
+    "29": "field",
+    "30": "armchair",
+    "31": "seat",
+    "32": "fence",
+    "33": "desk",
+    "34": "rock",
+    "35": "wardrobe",
+    "36": "lamp",
+    "37": "bathtub",
+    "38": "railing",
+    "39": "cushion",
+    "40": "base",
+    "41": "box",
+    "42": "column",
+    "43": "signboard",
+    "44": "chest of drawers",
+    "45": "counter",
+    "46": "sand",
+    "47": "sink",
+    "48": "skyscraper",
+    "49": "fireplace",
+    "50": "refrigerator",
+    "51": "grandstand",
+    "52": "path",
+    "53": "stairs",
+    "54": "runway",
+    "55": "case",
+    "56": "pool table",
+    "57": "pillow",
+    "58": "screen door",
+    "59": "stairway",
+    "60": "river",
+    "61": "bridge",
+    "62": "bookcase",
+    "63": "blind",
+    "64": "coffee table",
+    "65": "toilet",
+    "66": "flower",
+    "67": "book",
+    "68": "hill",
+    "69": "bench",
+    "70": "countertop",
+    "71": "stove",
+    "72": "palm",
+    "73": "kitchen island",
+    "74": "computer",
+    "75": "swivel chair",
+    "76": "boat",
+    "77": "bar",
+    "78": "arcade machine",
+    "79": "hovel",
+    "80": "bus",
+    "81": "towel",
+    "82": "light",
+    "83": "truck",
+    "84": "tower",
+    "85": "chandelier",
+    "86": "awning",
+    "87": "streetlight",
+    "88": "booth",
+    "89": "television receiver",
+    "90": "airplane",
+    "91": "dirt track",
+    "92": "apparel",
+    "93": "pole",
+    "94": "land",
+    "95": "bannister",
+    "96": "escalator",
+    "97": "ottoman",
+    "98": "bottle",
+    "99": "buffet",
+    "100": "poster",
+    "101": "stage",
+    "102": "van",
+    "103": "ship",
+    "104": "fountain",
+    "105": "conveyer belt",
+    "106": "canopy",
+    "107": "washer",
+    "108": "plaything",
+    "109": "swimming pool",
+    "110": "stool",
+    "111": "barrel",
+    "112": "basket",
+    "113": "waterfall",
+    "114": "tent",
+    "115": "bag",
+    "116": "minibike",
+    "117": "cradle",
+    "118": "oven",
+    "119": "ball",
+    "120": "food",
+    "121": "step",
+    "122": "tank",
+    "123": "trade name",
+    "124": "microwave",
+    "125": "pot",
+    "126": "animal",
+    "127": "bicycle",
+    "128": "lake",
+    "129": "dishwasher",
+    "130": "screen",
+    "131": "blanket",
+    "132": "sculpture",
+    "133": "hood",
+    "134": "sconce",
+    "135": "vase",
+    "136": "traffic light",
+    "137": "tray",
+    "138": "ashcan",
+    "139": "fan",
+    "140": "pier",
+    "141": "crt screen",
+    "142": "plate",
+    "143": "monitor",
+    "144": "bulletin board",
+    "145": "shower",
+    "146": "radiator",
+    "147": "glass",
+    "148": "clock",
+    "149": "flag"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "airplane": 90,
+    "animal": 126,
+    "apparel": 92,
+    "arcade machine": 78,
+    "armchair": 30,
+    "ashcan": 138,
+    "awning": 86,
+    "bag": 115,
+    "ball": 119,
+    "bannister": 95,
+    "bar": 77,
+    "barrel": 111,
+    "base": 40,
+    "basket": 112,
+    "bathtub": 37,
+    "bed ": 7,
+    "bench": 69,
+    "bicycle": 127,
+    "blanket": 131,
+    "blind": 63,
+    "boat": 76,
+    "book": 67,
+    "bookcase": 62,
+    "booth": 88,
+    "bottle": 98,
+    "box": 41,
+    "bridge": 61,
+    "buffet": 99,
+    "building": 1,
+    "bulletin board": 144,
+    "bus": 80,
+    "cabinet": 10,
+    "canopy": 106,
+    "car": 20,
+    "case": 55,
+    "ceiling": 5,
+    "chair": 19,
+    "chandelier": 85,
+    "chest of drawers": 44,
+    "clock": 148,
+    "coffee table": 64,
+    "column": 42,
+    "computer": 74,
+    "conveyer belt": 105,
+    "counter": 45,
+    "countertop": 70,
+    "cradle": 117,
+    "crt screen": 141,
+    "curtain": 18,
+    "cushion": 39,
+    "desk": 33,
+    "dirt track": 91,
+    "dishwasher": 129,
+    "door": 14,
+    "earth": 13,
+    "escalator": 96,
+    "fan": 139,
+    "fence": 32,
+    "field": 29,
+    "fireplace": 49,
+    "flag": 149,
+    "floor": 3,
+    "flower": 66,
+    "food": 120,
+    "fountain": 104,
+    "glass": 147,
+    "grandstand": 51,
+    "grass": 9,
+    "hill": 68,
+    "hood": 133,
+    "house": 25,
+    "hovel": 79,
+    "kitchen island": 73,
+    "lake": 128,
+    "lamp": 36,
+    "land": 94,
+    "light": 82,
+    "microwave": 124,
+    "minibike": 116,
+    "mirror": 27,
+    "monitor": 143,
+    "mountain": 16,
+    "ottoman": 97,
+    "oven": 118,
+    "painting": 22,
+    "palm": 72,
+    "path": 52,
+    "person": 12,
+    "pier": 140,
+    "pillow": 57,
+    "plant": 17,
+    "plate": 142,
+    "plaything": 108,
+    "pole": 93,
+    "pool table": 56,
+    "poster": 100,
+    "pot": 125,
+    "radiator": 146,
+    "railing": 38,
+    "refrigerator": 50,
+    "river": 60,
+    "road": 6,
+    "rock": 34,
+    "rug": 28,
+    "runway": 54,
+    "sand": 46,
+    "sconce": 134,
+    "screen": 130,
+    "screen door": 58,
+    "sculpture": 132,
+    "sea": 26,
+    "seat": 31,
+    "shelf": 24,
+    "ship": 103,
+    "shower": 145,
+    "sidewalk": 11,
+    "signboard": 43,
+    "sink": 47,
+    "sky": 2,
+    "skyscraper": 48,
+    "sofa": 23,
+    "stage": 101,
+    "stairs": 53,
+    "stairway": 59,
+    "step": 121,
+    "stool": 110,
+    "stove": 71,
+    "streetlight": 87,
+    "swimming pool": 109,
+    "swivel chair": 75,
+    "table": 15,
+    "tank": 122,
+    "television receiver": 89,
+    "tent": 114,
+    "toilet": 65,
+    "towel": 81,
+    "tower": 84,
+    "trade name": 123,
+    "traffic light": 136,
+    "tray": 137,
+    "tree": 4,
+    "truck": 83,
+    "van": 102,
+    "vase": 135,
+    "wall": 0,
+    "wardrobe": 35,
+    "washer": 107,
+    "water": 21,
+    "waterfall": 113,
+    "windowpane": 8
+  },
+  "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": true,
+  "resample": 2,
+  "size": 512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4df97633cbedd558ecffa3ad228ace5af37e082678390b45a9d22745787c61
+size 15092257

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38f99e2a8e73bbdb4635669be5bfcbbfc85b4b5c1ac75d36b47312c7fc5d06e
+size 15285696