Upload SegformerForSemanticSegmentation

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,406 @@
+{
+  "_name_or_path": "nvidia/mit-b3",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    4,
+    18,
+    3
+  ],
+  "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": "wall",
+    "1": "building;edifice",
+    "2": "sky",
+    "3": "floor",
+    "4": "tree",
+    "5": "ceiling",
+    "6": "road;route",
+    "7": "bed",
+    "8": "windowpane;window",
+    "9": "grass",
+    "10": "cabinet",
+    "11": "sidewalk;pavement",
+    "12": "person;individual;someone;somebody;mortal;soul",
+    "13": "earth;ground",
+    "14": "door;double;door",
+    "15": "table",
+    "16": "mountain;mount",
+    "17": "plant;flora;plant;life",
+    "18": "curtain;drape;drapery;mantle;pall",
+    "19": "chair",
+    "20": "car;auto",
+    "21": "water",
+    "22": "painting;picture",
+    "23": "sofa;couch;lounge",
+    "24": "rack",
+    "25": "house",
+    "26": "sea",
+    "27": "mirror",
+    "28": "rug;carpet;carpeting",
+    "29": "field",
+    "30": "armchair",
+    "31": "seat",
+    "32": "fence;fencing",
+    "33": "desk",
+    "34": "rock;stone",
+    "35": "wardrobe;closet;press",
+    "36": "lamp",
+    "37": "bathtub;bathing;tub;bath;tub",
+    "38": "railing;rail",
+    "39": "cushion",
+    "40": "base;pedestal;stand",
+    "41": "box",
+    "42": "pillar",
+    "43": "sign",
+    "44": "chest;of;drawers;chest;bureau;dresser",
+    "45": "counter",
+    "46": "sand",
+    "47": "sink",
+    "48": "skyscraper",
+    "49": "fireplace;hearth;open;fireplace",
+    "50": "refrigerator;icebox",
+    "51": "grandstand;covered;stand",
+    "52": "path",
+    "53": "stairs;steps",
+    "54": "runway",
+    "55": "case;display;case;showcase;vitrine",
+    "56": "pool;table;billiard;table;snooker;table",
+    "57": "pillow",
+    "58": "screen;door;screen",
+    "59": "stairway;staircase",
+    "60": "river",
+    "61": "bridge;span",
+    "62": "bookcase",
+    "63": "blind;screen",
+    "64": "coffee;table;cocktail;table",
+    "65": "toilet;can;commode;crapper;pot;potty;stool;throne",
+    "66": "flower",
+    "67": "book",
+    "68": "hill",
+    "69": "bench",
+    "70": "countertop",
+    "71": "stove;kitchen;stove;range;kitchen;range;cooking;stove",
+    "72": "palm;palm;tree",
+    "73": "kitchen;island",
+    "74": "computer",
+    "75": "swivel;chair",
+    "76": "boat",
+    "77": "bar",
+    "78": "arcade;machine",
+    "79": "hovel;hut;hutch;shack;shanty",
+    "80": "bus;autobus",
+    "81": "towel",
+    "82": "light;light;source",
+    "83": "truck;motortruck",
+    "84": "tower",
+    "85": "chandelier;pendant;pendent",
+    "86": "awning;sunshade;sunblind",
+    "87": "streetlight;street;lamp",
+    "88": "booth;cubicle;stall;kiosk",
+    "89": "television",
+    "90": "airplane;aeroplane;plane",
+    "91": "dirt;track",
+    "92": "apparel;wearing;apparel;dress;clothes",
+    "93": "pole",
+    "94": "land;ground;soil",
+    "95": "bannister;banister;balustrade;balusters;handrail",
+    "96": "escalator;moving;staircase;moving;stairway",
+    "97": "ottoman;pouf;pouffe;puff;hassock",
+    "98": "bottle",
+    "99": "buffet;counter;sideboard",
+    "100": "poster;posting;placard;notice;bill;card",
+    "101": "stage",
+    "102": "van",
+    "103": "ship",
+    "104": "fountain",
+    "105": "conveyer;belt;conveyor;belt;conveyer;conveyor;transporter",
+    "106": "canopy",
+    "107": "washer;automatic;washer;washing;machine",
+    "108": "plaything;toy",
+    "109": "swimming;pool;swimming;bath;natatorium",
+    "110": "stool",
+    "111": "barel",
+    "112": "basket;handbasket",
+    "113": "waterfall;falls",
+    "114": "tent;collapsible;shelter",
+    "115": "bag",
+    "116": "minibike;motorbike",
+    "117": "cradle",
+    "118": "oven",
+    "119": "ball",
+    "120": "food;solid;food",
+    "121": "step;stair",
+    "122": "tank;storage;tank",
+    "123": "trade;name;brand;name;brand;marque",
+    "124": "microwave;microwave;oven",
+    "125": "pot;flowerpot",
+    "126": "animal;animate;being;beast;brute;creature;fauna",
+    "127": "bicycle;bike;wheel;cycle",
+    "128": "lake",
+    "129": "dishwasher;dish;washer;dishwashing;machine",
+    "130": "screen;silver;screen;projection;screen",
+    "131": "blanket;cover",
+    "132": "sculpture",
+    "133": "hood;exhaust;hood",
+    "134": "sconce",
+    "135": "vase",
+    "136": "traffic;light;traffic;signal;stoplight",
+    "137": "tray",
+    "138": "ashcan;trash;can;garbage;wastebin",
+    "139": "fan",
+    "140": "pier;wharf;wharfage;dock",
+    "141": "crt;screen",
+    "142": "plate",
+    "143": "monitor;monitoring;device",
+    "144": "bulletin;board;notice;board",
+    "145": "emergency_board",
+    "146": "radiator",
+    "147": "glass;drinking;glass",
+    "148": "clock",
+    "149": "flag",
+    "150": "BACKGROUND",
+    "151": "paper_note",
+    "152": "pallet",
+    "153": "UNLABELLED",
+    "154": "floor_decal",
+    "155": "fire_extinguisher",
+    "156": "crate",
+    "157": "wire",
+    "158": "bracket",
+    "159": "fuse_box",
+    "160": "forklift",
+    "161": "cone",
+    "162": "cart",
+    "163": "bucket",
+    "164": "paper_shortcut",
+    "165": "barcode"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "BACKGROUND": 150,
+    "UNLABELLED": 153,
+    "airplane;aeroplane;plane": 90,
+    "animal;animate;being;beast;brute;creature;fauna": 126,
+    "apparel;wearing;apparel;dress;clothes": 92,
+    "arcade;machine": 78,
+    "armchair": 30,
+    "ashcan;trash;can;garbage;wastebin": 138,
+    "awning;sunshade;sunblind": 86,
+    "bag": 115,
+    "ball": 119,
+    "bannister;banister;balustrade;balusters;handrail": 95,
+    "bar": 77,
+    "barcode": 165,
+    "barel": 111,
+    "base;pedestal;stand": 40,
+    "basket;handbasket": 112,
+    "bathtub;bathing;tub;bath;tub": 37,
+    "bed": 7,
+    "bench": 69,
+    "bicycle;bike;wheel;cycle": 127,
+    "blanket;cover": 131,
+    "blind;screen": 63,
+    "boat": 76,
+    "book": 67,
+    "bookcase": 62,
+    "booth;cubicle;stall;kiosk": 88,
+    "bottle": 98,
+    "box": 41,
+    "bracket": 158,
+    "bridge;span": 61,
+    "bucket": 163,
+    "buffet;counter;sideboard": 99,
+    "building;edifice": 1,
+    "bulletin;board;notice;board": 144,
+    "bus;autobus": 80,
+    "cabinet": 10,
+    "canopy": 106,
+    "car;auto": 20,
+    "cart": 162,
+    "case;display;case;showcase;vitrine": 55,
+    "ceiling": 5,
+    "chair": 19,
+    "chandelier;pendant;pendent": 85,
+    "chest;of;drawers;chest;bureau;dresser": 44,
+    "clock": 148,
+    "coffee;table;cocktail;table": 64,
+    "computer": 74,
+    "cone": 161,
+    "conveyer;belt;conveyor;belt;conveyer;conveyor;transporter": 105,
+    "counter": 45,
+    "countertop": 70,
+    "cradle": 117,
+    "crate": 156,
+    "crt;screen": 141,
+    "curtain;drape;drapery;mantle;pall": 18,
+    "cushion": 39,
+    "desk": 33,
+    "dirt;track": 91,
+    "dishwasher;dish;washer;dishwashing;machine": 129,
+    "door;double;door": 14,
+    "earth;ground": 13,
+    "emergency_board": 145,
+    "escalator;moving;staircase;moving;stairway": 96,
+    "fan": 139,
+    "fence;fencing": 32,
+    "field": 29,
+    "fire_extinguisher": 155,
+    "fireplace;hearth;open;fireplace": 49,
+    "flag": 149,
+    "floor": 3,
+    "floor_decal": 154,
+    "flower": 66,
+    "food;solid;food": 120,
+    "forklift": 160,
+    "fountain": 104,
+    "fuse_box": 159,
+    "glass;drinking;glass": 147,
+    "grandstand;covered;stand": 51,
+    "grass": 9,
+    "hill": 68,
+    "hood;exhaust;hood": 133,
+    "house": 25,
+    "hovel;hut;hutch;shack;shanty": 79,
+    "kitchen;island": 73,
+    "lake": 128,
+    "lamp": 36,
+    "land;ground;soil": 94,
+    "light;light;source": 82,
+    "microwave;microwave;oven": 124,
+    "minibike;motorbike": 116,
+    "mirror": 27,
+    "monitor;monitoring;device": 143,
+    "mountain;mount": 16,
+    "ottoman;pouf;pouffe;puff;hassock": 97,
+    "oven": 118,
+    "painting;picture": 22,
+    "pallet": 152,
+    "palm;palm;tree": 72,
+    "paper_note": 151,
+    "paper_shortcut": 164,
+    "path": 52,
+    "person;individual;someone;somebody;mortal;soul": 12,
+    "pier;wharf;wharfage;dock": 140,
+    "pillar": 42,
+    "pillow": 57,
+    "plant;flora;plant;life": 17,
+    "plate": 142,
+    "plaything;toy": 108,
+    "pole": 93,
+    "pool;table;billiard;table;snooker;table": 56,
+    "poster;posting;placard;notice;bill;card": 100,
+    "pot;flowerpot": 125,
+    "rack": 24,
+    "radiator": 146,
+    "railing;rail": 38,
+    "refrigerator;icebox": 50,
+    "river": 60,
+    "road;route": 6,
+    "rock;stone": 34,
+    "rug;carpet;carpeting": 28,
+    "runway": 54,
+    "sand": 46,
+    "sconce": 134,
+    "screen;door;screen": 58,
+    "screen;silver;screen;projection;screen": 130,
+    "sculpture": 132,
+    "sea": 26,
+    "seat": 31,
+    "ship": 103,
+    "sidewalk;pavement": 11,
+    "sign": 43,
+    "sink": 47,
+    "sky": 2,
+    "skyscraper": 48,
+    "sofa;couch;lounge": 23,
+    "stage": 101,
+    "stairs;steps": 53,
+    "stairway;staircase": 59,
+    "step;stair": 121,
+    "stool": 110,
+    "stove;kitchen;stove;range;kitchen;range;cooking;stove": 71,
+    "streetlight;street;lamp": 87,
+    "swimming;pool;swimming;bath;natatorium": 109,
+    "swivel;chair": 75,
+    "table": 15,
+    "tank;storage;tank": 122,
+    "television": 89,
+    "tent;collapsible;shelter": 114,
+    "toilet;can;commode;crapper;pot;potty;stool;throne": 65,
+    "towel": 81,
+    "tower": 84,
+    "trade;name;brand;name;brand;marque": 123,
+    "traffic;light;traffic;signal;stoplight": 136,
+    "tray": 137,
+    "tree": 4,
+    "truck;motortruck": 83,
+    "van": 102,
+    "vase": 135,
+    "wall": 0,
+    "wardrobe;closet;press": 35,
+    "washer;automatic;washer;washing;machine": 107,
+    "water": 21,
+    "waterfall;falls": 113,
+    "windowpane;window": 8,
+    "wire": 157
+  },
+  "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,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c6211a6b332aa6b66978770066fc7dce3489eae381cb950cf337c0d859dac7
+size 189484256