config.json

{
  "_name_or_path": "mserrasa/yolo_finetuned_VinBigData",
  "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": 192,
  "id2label": {
    "0": "Aortic enlargement",
    "1": "Cardiomegaly",
    "2": "Nodule/Mass",
    "3": "Pleural thickening",
    "4": "Pulmonary fibrosis"
  },
  "image_size": [
    800,
    1333
  ],
  "initializer_range": 0.02,
  "intermediate_size": 768,
  "label2id": {
    "Aortic enlargement": 0,
    "Cardiomegaly": 1,
    "Nodule/Mass": 2,
    "Pleural thickening": 3,
    "Pulmonary fibrosis": 4
  },
  "layer_norm_eps": 1e-12,
  "model_type": "yolos",
  "num_attention_heads": 3,
  "num_channels": 3,
  "num_detection_tokens": 100,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.40.2",
  "use_mid_position_embeddings": false
}