{
  "modelname" : "groundingdino",
  "backbone" : "swin_T_224_1k",
  "position_embedding" : "sine",
  "pe_temperatureH" : 20,
  "pe_temperatureW" : 20,
  "return_interm_indices" : [1, 2, 3],
  "backbone_freeze_keywords" : null,
  "enc_layers" : 6,
  "dec_layers" : 6,
  "pre_norm" : false,
  "dim_feedforward" : 2048,
  "hidden_dim" : 256,
  "dropout" : 0.0,
  "nheads" : 8,
  "num_queries" : 900,
  "query_dim" : 4,
  "num_patterns" : 0,
  "num_feature_levels" : 4,
  "enc_n_points" : 4,
  "dec_n_points" : 4,
  "two_stage_type" : "standard",
  "two_stage_bbox_embed_share" : false,
  "two_stage_class_embed_share" : false,
  "transformer_activation" : "relu",
  "dec_pred_bbox_embed_share" : true,
  "dn_box_noise_scale" : 1.0,
  "dn_label_noise_ratio" : 0.5,
  "dn_label_coef" : 1.0,
  "dn_bbox_coef" : 1.0,
  "embed_init_tgt" :true,
  "dn_labelbook_size" : 2000,
  "max_text_len" : 256,
  "text_encoder_type" : "bert-base-uncased",
  "use_text_enhancer" : true,
  "use_fusion_layer" : true,
  "use_checkpoint" : false,
  "use_transformer_ckpt" : false,
  "use_text_cross_attention" : true,
  "text_dropout" : 0.0,
  "fusion_dropout" : 0.0,
  "fusion_droppath" : 0.1,
  "sub_sentence_present" : true
}
