config.json

{
  "_name_or_path": "hustvl/yolos-small",
  "architectures": [
    "YolosForObjectDetection"
  ],
  "attention_probs_dropout_prob": 0.0,
  "auxiliary_loss": false,
  "bbox_cost": 5,
  "bbox_loss_coefficient": 5,
  "class_cost": 1,
  "eos_coefficient": 0.1,
  "giou_cost": 2,
  "giou_loss_coefficient": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 384,
  "id2label": {
    "0": "hop_dln",
    "1": "hop_jn",
    "2": "hop_vtg",
    "3": "hop_ytv",
    "4": "lo_kids",
    "5": "lo_ytv",
    "6": "loc_dln",
    "7": "loc_jn",
    "8": "loc_kids",
    "9": "loc_ytv"
  },
  "image_size": [
    512,
    864
  ],
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "label2id": {
    "hop_dln": 0,
    "hop_jn": 1,
    "hop_vtg": 2,
    "hop_ytv": 3,
    "lo_kids": 4,
    "lo_ytv": 5,
    "loc_dln": 6,
    "loc_jn": 7,
    "loc_kids": 8,
    "loc_ytv": 9
  },
  "layer_norm_eps": 1e-12,
  "model_type": "yolos",
  "num_attention_heads": 6,
  "num_channels": 3,
  "num_detection_tokens": 100,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "use_mid_position_embeddings": true
}