Upload MaskFormerForInstanceSegmentation

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 +1,371 @@
+{
+  "architectures": [
+    "MaskFormerForInstanceSegmentation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
+    "drop_path_rate": 0.3,
+    "embed_dim": 128,
+    "encoder_stride": 32,
+    "hidden_size": 1024,
+    "image_size": 384,
+    "in_channels": 3,
+    "model_type": "maskformer-swin",
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "path_norm": true,
+    "pretrain_img_size": 384,
+    "window_size": 12
+  },
+  "backbone_kwargs": null,
+  "ce_weight": 1.0,
+  "cross_entropy_weight": 1.0,
+  "decoder_config": {
+    "max_position_embeddings": 1024,
+    "model_type": "detr",
+    "scale_embedding": false
+  },
+  "dice_weight": 1.0,
+  "fpn_feature_size": 256,
+  "id2label": {
+    "0": "wall",
+    "1": "building",
+    "2": "sky",
+    "3": "floor",
+    "4": "tree",
+    "5": "ceiling",
+    "6": "road, route",
+    "7": "bed",
+    "8": "window ",
+    "9": "grass",
+    "10": "cabinet",
+    "11": "sidewalk, pavement",
+    "12": "person",
+    "13": "earth, ground",
+    "14": "door",
+    "15": "table",
+    "16": "mountain, mount",
+    "17": "plant",
+    "18": "curtain",
+    "19": "chair",
+    "20": "car",
+    "21": "water",
+    "22": "painting, picture",
+    "23": "sofa",
+    "24": "shelf",
+    "25": "house",
+    "26": "sea",
+    "27": "mirror",
+    "28": "rug",
+    "29": "field",
+    "30": "armchair",
+    "31": "seat",
+    "32": "fence",
+    "33": "desk",
+    "34": "rock, stone",
+    "35": "wardrobe, closet, press",
+    "36": "lamp",
+    "37": "tub",
+    "38": "rail",
+    "39": "cushion",
+    "40": "base, pedestal, stand",
+    "41": "box",
+    "42": "column, pillar",
+    "43": "signboard, sign",
+    "44": "chest of drawers, chest, bureau, dresser",
+    "45": "counter",
+    "46": "sand",
+    "47": "sink",
+    "48": "skyscraper",
+    "49": "fireplace",
+    "50": "refrigerator, icebox",
+    "51": "grandstand, covered stand",
+    "52": "path",
+    "53": "stairs",
+    "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",
+    "65": "toilet, can, commode, crapper, pot, potty, stool, throne",
+    "66": "flower",
+    "67": "book",
+    "68": "hill",
+    "69": "bench",
+    "70": "countertop",
+    "71": "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",
+    "81": "towel",
+    "82": "light",
+    "83": "truck",
+    "84": "tower",
+    "85": "chandelier",
+    "86": "awning, sunshade, sunblind",
+    "87": "street lamp",
+    "88": "booth",
+    "89": "tv",
+    "90": "plane",
+    "91": "dirt track",
+    "92": "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": "pool",
+    "110": "stool",
+    "111": "barrel, cask",
+    "112": "basket, handbasket",
+    "113": "falls",
+    "114": "tent",
+    "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",
+    "124": "microwave",
+    "125": "pot",
+    "126": "animal",
+    "127": "bicycle",
+    "128": "lake",
+    "129": "dishwasher",
+    "130": "screen",
+    "131": "blanket, cover",
+    "132": "sculpture",
+    "133": "hood, exhaust hood",
+    "134": "sconce",
+    "135": "vase",
+    "136": "traffic light",
+    "137": "tray",
+    "138": "trash can",
+    "139": "fan",
+    "140": "pier",
+    "141": "crt screen",
+    "142": "plate",
+    "143": "monitor",
+    "144": "bulletin board",
+    "145": "shower",
+    "146": "radiator",
+    "147": "glass, drinking glass",
+    "148": "clock",
+    "149": "flag"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "label2id": {
+    "animal": 126,
+    "arcade machine": 78,
+    "armchair": 30,
+    "awning, sunshade, sunblind": 86,
+    "bag": 115,
+    "ball": 119,
+    "bannister, banister, balustrade, balusters, handrail": 95,
+    "bar": 77,
+    "barrel, cask": 111,
+    "base, pedestal, stand": 40,
+    "basket, handbasket": 112,
+    "bed": 7,
+    "bench": 69,
+    "bicycle": 127,
+    "blanket, cover": 131,
+    "blind, screen": 63,
+    "boat": 76,
+    "book": 67,
+    "bookcase": 62,
+    "booth": 88,
+    "bottle": 98,
+    "box": 41,
+    "bridge, span": 61,
+    "buffet, counter, sideboard": 99,
+    "building": 1,
+    "bulletin board": 144,
+    "bus": 80,
+    "cabinet": 10,
+    "canopy": 106,
+    "car": 20,
+    "case, display case, showcase, vitrine": 55,
+    "ceiling": 5,
+    "chair": 19,
+    "chandelier": 85,
+    "chest of drawers, chest, bureau, dresser": 44,
+    "clock": 148,
+    "clothes": 92,
+    "coffee table": 64,
+    "column, pillar": 42,
+    "computer": 74,
+    "conveyer belt, conveyor belt, conveyer, conveyor, transporter": 105,
+    "counter": 45,
+    "countertop": 70,
+    "cradle": 117,
+    "crt screen": 141,
+    "curtain": 18,
+    "cushion": 39,
+    "desk": 33,
+    "dirt track": 91,
+    "dishwasher": 129,
+    "door": 14,
+    "earth, ground": 13,
+    "escalator, moving staircase, moving stairway": 96,
+    "falls": 113,
+    "fan": 139,
+    "fence": 32,
+    "field": 29,
+    "fireplace": 49,
+    "flag": 149,
+    "floor": 3,
+    "flower": 66,
+    "food, solid food": 120,
+    "fountain": 104,
+    "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": 82,
+    "microwave": 124,
+    "minibike, motorbike": 116,
+    "mirror": 27,
+    "monitor": 143,
+    "mountain, mount": 16,
+    "ottoman, pouf, pouffe, puff, hassock": 97,
+    "oven": 118,
+    "painting, picture": 22,
+    "palm, palm tree": 72,
+    "path": 52,
+    "person": 12,
+    "pier": 140,
+    "pillow": 57,
+    "plane": 90,
+    "plant": 17,
+    "plate": 142,
+    "plaything, toy": 108,
+    "pole": 93,
+    "pool": 109,
+    "pool table, billiard table, snooker table": 56,
+    "poster, posting, placard, notice, bill, card": 100,
+    "pot": 125,
+    "radiator": 146,
+    "rail": 38,
+    "refrigerator, icebox": 50,
+    "river": 60,
+    "road, route": 6,
+    "rock, stone": 34,
+    "rug": 28,
+    "runway": 54,
+    "sand": 46,
+    "sconce": 134,
+    "screen": 130,
+    "screen door, screen": 58,
+    "sculpture": 132,
+    "sea": 26,
+    "seat": 31,
+    "shelf": 24,
+    "ship": 103,
+    "shower": 145,
+    "sidewalk, pavement": 11,
+    "signboard, sign": 43,
+    "sink": 47,
+    "sky": 2,
+    "skyscraper": 48,
+    "sofa": 23,
+    "stage": 101,
+    "stairs": 53,
+    "stairway, staircase": 59,
+    "step, stair": 121,
+    "stool": 110,
+    "stove": 71,
+    "street lamp": 87,
+    "swivel chair": 75,
+    "table": 15,
+    "tank, storage tank": 122,
+    "tent": 114,
+    "toilet, can, commode, crapper, pot, potty, stool, throne": 65,
+    "towel": 81,
+    "tower": 84,
+    "trade name": 123,
+    "traffic light": 136,
+    "trash can": 138,
+    "tray": 137,
+    "tree": 4,
+    "truck": 83,
+    "tub": 37,
+    "tv": 89,
+    "van": 102,
+    "vase": 135,
+    "wall": 0,
+    "wardrobe, closet, press": 35,
+    "washer, automatic washer, washing machine": 107,
+    "water": 21,
+    "window ": 8
+  },
+  "mask_feature_size": 256,
+  "mask_weight": 20.0,
+  "model_type": "maskformer",
+  "no_object_weight": 0.1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "output_auxiliary_logits": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.0.dev0",
+  "use_auxiliary_loss": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f029857d7e180f397f01f6812e66e843e18974c0484798ca8a0f2beed50186
+size 411406320