config.json

{
  "_commit_hash": null,
  "activation_function": "relu",
  "architectures": [
    "VideoMask2FormerForVideoSegmentation"
  ],
  "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"
    ],
    "out_indices": [
      1,
      2,
      3,
      4
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 4,
    "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": "4.29.0.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": "airplane",
    "1": "bear",
    "2": "bird",
    "3": "boat",
    "4": "car",
    "5": "cat",
    "6": "cow",
    "7": "deer",
    "8": "dog",
    "9": "duck",
    "10": "earless_seal",
    "11": "elephant",
    "12": "fish",
    "13": "flying_disc",
    "14": "fox",
    "15": "frog",
    "16": "giant_panda",
    "17": "giraffe",
    "18": "horse",
    "19": "leopard",
    "20": "lizard",
    "21": "monkey",
    "22": "motorbike",
    "23": "mouse",
    "24": "parrot",
    "25": "person",
    "26": "rabbit",
    "27": "shark",
    "28": "skateboard",
    "29": "snake",
    "30": "snowboard",
    "31": "squirrel",
    "32": "surfboard",
    "33": "tennis_racket",
    "34": "tiger",
    "35": "train",
    "36": "truck",
    "37": "turtle",
    "38": "whale",
    "39": "zebra"
  },
  "ignore_value": 255,
  "importance_sample_ratio": 0.75,
  "init_std": 0.02,
  "init_xavier_std": 1.0,
  "label2id": {
    "airplane": 0,
    "bear": 1,
    "bird": 2,
    "boat": 3,
    "car": 4,
    "cat": 5,
    "cow": 6,
    "deer": 7,
    "dog": 8,
    "duck": 9,
    "earless_seal": 10,
    "elephant": 11,
    "fish": 12,
    "flying_disc": 13,
    "fox": 14,
    "frog": 15,
    "giant_panda": 16,
    "giraffe": 17,
    "horse": 18,
    "leopard": 19,
    "lizard": 20,
    "monkey": 21,
    "motorbike": 22,
    "mouse": 23,
    "parrot": 24,
    "person": 25,
    "rabbit": 26,
    "shark": 27,
    "skateboard": 28,
    "snake": 29,
    "snowboard": 30,
    "squirrel": 31,
    "surfboard": 32,
    "tennis_racket": 33,
    "tiger": 34,
    "train": 35,
    "truck": 36,
    "turtle": 37,
    "whale": 38,
    "zebra": 39
  },
  "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
}