config.json

{
  "activation_dropout": 0.0,
  "activation_function": "silu",
  "anchor_image_size": null,
  "attention_dropout": 0.0,
  "auxiliary_loss": true,
  "backbone_config": {
    "arch": "L",
    "depths": [
      3,
      4,
      6,
      3
    ],
    "embedding_size": 64,
    "hidden_act": "relu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "initializer_range": 0.02,
    "model_type": "hgnet_v2",
    "num_channels": 3,
    "out_features": [
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      2,
      3,
      4
    ],
    "stage_downsample": [
      false,
      true,
      true,
      true
    ],
    "stage_downsample_strides": [
      2,
      2,
      2,
      2
    ],
    "stage_in_channels": [
      48,
      128,
      512,
      1024
    ],
    "stage_kernel_size": [
      3,
      3,
      5,
      5
    ],
    "stage_light_block": [
      false,
      false,
      true,
      true
    ],
    "stage_mid_channels": [
      48,
      96,
      192,
      384
    ],
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "stage_num_blocks": [
      1,
      1,
      3,
      1
    ],
    "stage_numb_of_layers": [
      6,
      6,
      6,
      6
    ],
    "stage_out_channels": [
      128,
      512,
      1024,
      2048
    ],
    "stem_channels": [
      3,
      32,
      48
    ],
    "stem_strides": [
      2,
      1,
      1,
      2,
      1
    ],
    "use_learnable_affine_block": false,
    "return_idx": [
      1,
      2,
      3
    ],
    "freeze_stem_only": true,
    "freeze_at": 0,
    "freeze_norm": false,
    "lr_mult_list": [
      0.05,
      0.05,
      0.1,
      0.15,
      0.2
    ]
  },
  "batch_norm_eps": 1e-05,
  "box_noise_scale": 1.0,
  "d_model": 256,
  "decoder_activation_function": "relu",
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 1024,
  "decoder_in_channels": [
    256,
    256,
    256
  ],
  "decoder_layers": 6,
  "decoder_n_points": 4,
  "disable_custom_kernels": true,
  "dropout": 0.0,
  "encode_proj_layers": [
    2
  ],
  "encoder_activation_function": "gelu",
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 1024,
  "encoder_hidden_dim": 256,
  "encoder_in_channels": [
    512,
    1024,
    2048
  ],
  "encoder_layers": 1,
  "eos_coefficient": 0.0001,
  "eval_size": null,
  "feat_strides": [
    8,
    16,
    32
  ],
  "focal_loss_alpha": 0.75,
  "focal_loss_gamma": 2.0,
  "freeze_backbone_batch_norms": true,
  "hidden_expansion": 1.0,
  "id2label": {
    "0": "Region"
  },
  "initializer_bias_prior_prob": null,
  "initializer_range": 0.01,
  "is_encoder_decoder": true,
  "label2id": {
    "Region": 0
  },
  "label_noise_ratio": 0.5,
  "layer_norm_eps": 1e-05,
  "learn_initial_query": false,
  "matcher_alpha": 0.25,
  "matcher_bbox_cost": 5.0,
  "matcher_class_cost": 2.0,
  "matcher_gamma": 2.0,
  "matcher_giou_cost": 2.0,
  "model_type": "rt_detr",
  "normalize_before": false,
  "num_denoising": 100,
  "num_feature_levels": 3,
  "num_queries": 300,
  "positional_encoding_temperature": 10000,
  "transformers_version": "5.3.0.dev0",
  "use_focal_loss": true,
  "weight_loss_bbox": 5.0,
  "weight_loss_giou": 2.0,
  "weight_loss_vfl": 1.0,
  "with_box_refine": true
}