Upload SegformerForSemanticSegmentation

README.md

@@ -0,0 +1,201 @@
+---
+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 +1,374 @@
+{
+ "_name_or_path": "nvidia/mit-b0",
+ "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,
+ "semantic_loss_ignore_index": 255,
+ "sr_ratios": [
+ 8,
+ 4,
+ 2,
+ 1
+ ],
+ "strides": [
+ 4,
+ 2,
+ 2,
+ 2
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaa4ae03b39c7e46581f6c1b1e82dc0aa1ef0932a8b12f942dd7ad03662989a
+size 17303528