Upload Mask2FormerForUniversalSegmentation

config.json

@@ -0,0 +1,314 @@
+{
+  "_commit_hash": null,
+  "activation_function": "relu",
+  "architectures": [
+    "Mask2FormerForUniversalSegmentation"
+  ],
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.3,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 12
+  },
+  "class_weight": 2.0,
+  "common_stride": 4,
+  "decoder_layers": 10,
+  "dice_weight": 5.0,
+  "dim_feedforward": 2048,
+  "dropout": 0.0,
+  "encoder_feedforward_dim": 1024,
+  "encoder_layers": 6,
+  "enforce_input_proj": false,
+  "enforce_input_projection": false,
+  "feature_size": 256,
+  "feature_strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "hidden_dim": 256,
+  "id2label": {
+    "0": "person",
+    "1": "bicycle",
+    "2": "car",
+    "3": "motorbike",
+    "4": "aeroplane",
+    "5": "bus",
+    "6": "train",
+    "7": "truck",
+    "8": "boat",
+    "9": "traffic light",
+    "10": "fire hydrant",
+    "11": "stop sign",
+    "12": "parking meter",
+    "13": "bench",
+    "14": "bird",
+    "15": "cat",
+    "16": "dog",
+    "17": "horse",
+    "18": "sheep",
+    "19": "cow",
+    "20": "elephant",
+    "21": "bear",
+    "22": "zebra",
+    "23": "giraffe",
+    "24": "backpack",
+    "25": "umbrella",
+    "26": "handbag",
+    "27": "tie",
+    "28": "suitcase",
+    "29": "frisbee",
+    "30": "skis",
+    "31": "snowboard",
+    "32": "sports ball",
+    "33": "kite",
+    "34": "baseball bat",
+    "35": "baseball glove",
+    "36": "skateboard",
+    "37": "surfboard",
+    "38": "tennis racket",
+    "39": "bottle",
+    "40": "wine glass",
+    "41": "cup",
+    "42": "fork",
+    "43": "knife",
+    "44": "spoon",
+    "45": "bowl",
+    "46": "banana",
+    "47": "apple",
+    "48": "sandwich",
+    "49": "orange",
+    "50": "broccoli",
+    "51": "carrot",
+    "52": "hot dog",
+    "53": "pizza",
+    "54": "donut",
+    "55": "cake",
+    "56": "chair",
+    "57": "sofa",
+    "58": "pottedplant",
+    "59": "bed",
+    "60": "diningtable",
+    "61": "toilet",
+    "62": "tvmonitor",
+    "63": "laptop",
+    "64": "mouse",
+    "65": "remote",
+    "66": "keyboard",
+    "67": "cell phone",
+    "68": "microwave",
+    "69": "oven",
+    "70": "toaster",
+    "71": "sink",
+    "72": "refrigerator",
+    "73": "book",
+    "74": "clock",
+    "75": "vase",
+    "76": "scissors",
+    "77": "teddy bear",
+    "78": "hair drier",
+    "79": "toothbrush"
+  },
+  "ignore_value": 255,
+  "importance_sample_ratio": 0.75,
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "label2id": {
+    "aeroplane": 4,
+    "apple": 47,
+    "backpack": 24,
+    "banana": 46,
+    "baseball bat": 34,
+    "baseball glove": 35,
+    "bear": 21,
+    "bed": 59,
+    "bench": 13,
+    "bicycle": 1,
+    "bird": 14,
+    "boat": 8,
+    "book": 73,
+    "bottle": 39,
+    "bowl": 45,
+    "broccoli": 50,
+    "bus": 5,
+    "cake": 55,
+    "car": 2,
+    "carrot": 51,
+    "cat": 15,
+    "cell phone": 67,
+    "chair": 56,
+    "clock": 74,
+    "cow": 19,
+    "cup": 41,
+    "diningtable": 60,
+    "dog": 16,
+    "donut": 54,
+    "elephant": 20,
+    "fire hydrant": 10,
+    "fork": 42,
+    "frisbee": 29,
+    "giraffe": 23,
+    "hair drier": 78,
+    "handbag": 26,
+    "horse": 17,
+    "hot dog": 52,
+    "keyboard": 66,
+    "kite": 33,
+    "knife": 43,
+    "laptop": 63,
+    "microwave": 68,
+    "motorbike": 3,
+    "mouse": 64,
+    "orange": 49,
+    "oven": 69,
+    "parking meter": 12,
+    "person": 0,
+    "pizza": 53,
+    "pottedplant": 58,
+    "refrigerator": 72,
+    "remote": 65,
+    "sandwich": 48,
+    "scissors": 76,
+    "sheep": 18,
+    "sink": 71,
+    "skateboard": 36,
+    "skis": 30,
+    "snowboard": 31,
+    "sofa": 57,
+    "spoon": 44,
+    "sports ball": 32,
+    "stop sign": 11,
+    "suitcase": 28,
+    "surfboard": 37,
+    "teddy bear": 77,
+    "tennis racket": 38,
+    "tie": 27,
+    "toaster": 70,
+    "toilet": 61,
+    "toothbrush": 79,
+    "traffic light": 9,
+    "train": 6,
+    "truck": 7,
+    "tvmonitor": 62,
+    "umbrella": 25,
+    "vase": 75,
+    "wine glass": 40,
+    "zebra": 22
+  },
+  "mask_feature_size": 256,
+  "mask_weight": 5.0,
+  "model_type": "mask2former",
+  "no_object_weight": 0.1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 10,
+  "num_queries": 100,
+  "output_auxiliary_logits": null,
+  "oversample_ratio": 3.0,
+  "pre_norm": false,
+  "torch_dtype": "float32",
+  "train_num_points": 12544,
+  "transformers_version": null,
+  "use_auxiliary_loss": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d54e1ec1ae5cb5fee47758bf47356b4b73b04a8b013abf48cb67a2fb1351a2
+size 431878597