Update tiny models for OneFormerForUniversalSegmentation

config.json

@@ -0,0 +1,118 @@
+{
+  "architectures": [
+    "OneFormerForUniversalSegmentation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "drop_path_rate": 0.3,
+    "embed_dim": 16,
+    "encoder_stride": 32,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 16,
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "num_channels": 3,
+    "num_heads": [
+      1,
+      1,
+      2,
+      2
+    ],
+    "num_layers": 4,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "patch_size": 4,
+    "qkv_bias": true,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "use_absolute_embeddings": false,
+    "window_size": 7
+  },
+  "class_weight": 2.0,
+  "common_stride": 4,
+  "contrastive_temperature": 0.07,
+  "contrastive_weight": 0.5,
+  "conv_dim": 64,
+  "decoder_layers": 2,
+  "dice_weight": 5.0,
+  "dim_feedforward": 64,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_feedforward_dim": 32,
+  "encoder_layers": 2,
+  "enforce_input_proj": false,
+  "hidden_dim": 64,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "ignore_value": 255,
+  "importance_sample_ratio": 0.75,
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_training": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_dim": 64,
+  "mask_weight": 5.0,
+  "max_seq_len": 77,
+  "model_type": "oneformer",
+  "no_object_weight": 0.1,
+  "norm": "GN",
+  "num_attention_heads": 8,
+  "num_queries": 10,
+  "output_auxiliary_logits": true,
+  "oversample_ratio": 3.0,
+  "pre_norm": false,
+  "query_dec_layers": 2,
+  "strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "task_seq_len": 77,
+  "text_encoder_context_length": 77,
+  "text_encoder_n_ctx": 4,
+  "text_encoder_num_layers": 6,
+  "text_encoder_proj_layers": 2,
+  "text_encoder_vocab_size": 99,
+  "text_encoder_width": 64,
+  "train_num_points": 12544,
+  "transformers_version": "5.16.0.dev0",
+  "use_auxiliary_loss": true,
+  "use_task_norm": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c918dc1578dd2d15aee2bd7d2f2b65c2e3d9718821529f498cd394665209f1c1
+size 2368144

preprocessor_config.json

@@ -0,0 +1,436 @@
+{
+  "_max_size": 2048,
+  "class_info_file": "ade20k_panoptic.json",
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "ignore_index": 255,
+  "image_mean": [
+    0.48500001430511475,
+    0.4560000002384186,
+    0.4059999883174896
+  ],
+  "image_processor_type": "OneFormerImageProcessor",
+  "image_std": [
+    0.2290000021457672,
+    0.2239999920129776,
+    0.22499999403953552
+  ],
+  "metadata": {
+    "0": "wall",
+    "1": "building",
+    "10": "cabinet",
+    "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",
+    "11": "sidewalk, pavement",
+    "110": "stool",
+    "111": "barrel, cask",
+    "112": "basket, handbasket",
+    "113": "falls",
+    "114": "tent",
+    "115": "bag",
+    "116": "minibike, motorbike",
+    "117": "cradle",
+    "118": "oven",
+    "119": "ball",
+    "12": "person",
+    "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",
+    "13": "earth, ground",
+    "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",
+    "14": "door",
+    "140": "pier",
+    "141": "crt screen",
+    "142": "plate",
+    "143": "monitor",
+    "144": "bulletin board",
+    "145": "shower",
+    "146": "radiator",
+    "147": "glass, drinking glass",
+    "148": "clock",
+    "149": "flag",
+    "15": "table",
+    "16": "mountain, mount",
+    "17": "plant",
+    "18": "curtain",
+    "19": "chair",
+    "2": "sky",
+    "20": "car",
+    "21": "water",
+    "22": "painting, picture",
+    "23": "sofa",
+    "24": "shelf",
+    "25": "house",
+    "26": "sea",
+    "27": "mirror",
+    "28": "rug",
+    "29": "field",
+    "3": "floor",
+    "30": "armchair",
+    "31": "seat",
+    "32": "fence",
+    "33": "desk",
+    "34": "rock, stone",
+    "35": "wardrobe, closet, press",
+    "36": "lamp",
+    "37": "tub",
+    "38": "rail",
+    "39": "cushion",
+    "4": "tree",
+    "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",
+    "5": "ceiling",
+    "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",
+    "6": "road, route",
+    "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",
+    "7": "bed",
+    "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",
+    "8": "window ",
+    "80": "bus",
+    "81": "towel",
+    "82": "light",
+    "83": "truck",
+    "84": "tower",
+    "85": "chandelier",
+    "86": "awning, sunshade, sunblind",
+    "87": "street lamp",
+    "88": "booth",
+    "89": "tv",
+    "9": "grass",
+    "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",
+    "class_names": [
+      "wall",
+      "building",
+      "sky",
+      "floor",
+      "tree",
+      "ceiling",
+      "road, route",
+      "bed",
+      "window ",
+      "grass",
+      "cabinet",
+      "sidewalk, pavement",
+      "person",
+      "earth, ground",
+      "door",
+      "table",
+      "mountain, mount",
+      "plant",
+      "curtain",
+      "chair",
+      "car",
+      "water",
+      "painting, picture",
+      "sofa",
+      "shelf",
+      "house",
+      "sea",
+      "mirror",
+      "rug",
+      "field",
+      "armchair",
+      "seat",
+      "fence",
+      "desk",
+      "rock, stone",
+      "wardrobe, closet, press",
+      "lamp",
+      "tub",
+      "rail",
+      "cushion",
+      "base, pedestal, stand",
+      "box",
+      "column, pillar",
+      "signboard, sign",
+      "chest of drawers, chest, bureau, dresser",
+      "counter",
+      "sand",
+      "sink",
+      "skyscraper",
+      "fireplace",
+      "refrigerator, icebox",
+      "grandstand, covered stand",
+      "path",
+      "stairs",
+      "runway",
+      "case, display case, showcase, vitrine",
+      "pool table, billiard table, snooker table",
+      "pillow",
+      "screen door, screen",
+      "stairway, staircase",
+      "river",
+      "bridge, span",
+      "bookcase",
+      "blind, screen",
+      "coffee table",
+      "toilet, can, commode, crapper, pot, potty, stool, throne",
+      "flower",
+      "book",
+      "hill",
+      "bench",
+      "countertop",
+      "stove",
+      "palm, palm tree",
+      "kitchen island",
+      "computer",
+      "swivel chair",
+      "boat",
+      "bar",
+      "arcade machine",
+      "hovel, hut, hutch, shack, shanty",
+      "bus",
+      "towel",
+      "light",
+      "truck",
+      "tower",
+      "chandelier",
+      "awning, sunshade, sunblind",
+      "street lamp",
+      "booth",
+      "tv",
+      "plane",
+      "dirt track",
+      "clothes",
+      "pole",
+      "land, ground, soil",
+      "bannister, banister, balustrade, balusters, handrail",
+      "escalator, moving staircase, moving stairway",
+      "ottoman, pouf, pouffe, puff, hassock",
+      "bottle",
+      "buffet, counter, sideboard",
+      "poster, posting, placard, notice, bill, card",
+      "stage",
+      "van",
+      "ship",
+      "fountain",
+      "conveyer belt, conveyor belt, conveyer, conveyor, transporter",
+      "canopy",
+      "washer, automatic washer, washing machine",
+      "plaything, toy",
+      "pool",
+      "stool",
+      "barrel, cask",
+      "basket, handbasket",
+      "falls",
+      "tent",
+      "bag",
+      "minibike, motorbike",
+      "cradle",
+      "oven",
+      "ball",
+      "food, solid food",
+      "step, stair",
+      "tank, storage tank",
+      "trade name",
+      "microwave",
+      "pot",
+      "animal",
+      "bicycle",
+      "lake",
+      "dishwasher",
+      "screen",
+      "blanket, cover",
+      "sculpture",
+      "hood, exhaust hood",
+      "sconce",
+      "vase",
+      "traffic light",
+      "tray",
+      "trash can",
+      "fan",
+      "pier",
+      "crt screen",
+      "plate",
+      "monitor",
+      "bulletin board",
+      "shower",
+      "radiator",
+      "glass, drinking glass",
+      "clock",
+      "flag"
+    ],
+    "thing_ids": [
+      7,
+      8,
+      10,
+      12,
+      14,
+      15,
+      18,
+      19,
+      20,
+      22,
+      23,
+      24,
+      27,
+      30,
+      31,
+      32,
+      33,
+      35,
+      36,
+      37,
+      38,
+      39,
+      41,
+      42,
+      43,
+      44,
+      45,
+      47,
+      49,
+      50,
+      53,
+      55,
+      56,
+      57,
+      58,
+      62,
+      64,
+      65,
+      66,
+      67,
+      69,
+      70,
+      71,
+      72,
+      73,
+      74,
+      75,
+      76,
+      78,
+      80,
+      81,
+      82,
+      83,
+      85,
+      86,
+      87,
+      88,
+      89,
+      90,
+      92,
+      93,
+      95,
+      97,
+      98,
+      102,
+      103,
+      104,
+      107,
+      108,
+      110,
+      111,
+      112,
+      115,
+      116,
+      118,
+      119,
+      120,
+      121,
+      123,
+      124,
+      125,
+      126,
+      127,
+      129,
+      130,
+      132,
+      133,
+      134,
+      135,
+      136,
+      137,
+      138,
+      139,
+      142,
+      143,
+      144,
+      146,
+      147,
+      148,
+      149
+    ]
+  },
+  "num_labels": 150,
+  "reduce_labels": false,
+  "repo_path": "shi-labs/oneformer_demo",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 2048,
+    "shortest_edge": 512
+  }
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "OneFormerProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}