config.json

{
  "_name_or_path": "PekingU/rtdetr_r50vd_coco_o365",
  "activation_dropout": 0.0,
  "activation_function": "silu",
  "anchor_image_size": null,
  "architectures": [
    "DetrForObjectDetection"
  ],
  "attention_dropout": 0.0,
  "auxiliary_loss": true,
  "backbone": null,
  "backbone_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "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": [
      3,
      4,
      6,
      3
    ],
    "diversity_penalty": 0.0,
    "do_sample": false,
    "downsample_in_bottleneck": false,
    "downsample_in_first_stage": false,
    "early_stopping": false,
    "embedding_size": 64,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "relu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_type": "bottleneck",
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "rt_detr_resnet",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_return_sequences": 1,
    "out_features": [
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      2,
      3,
      4
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "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,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "backbone_kwargs": null,
  "batch_norm_eps": 1e-05,
  "bbox_cost": 5,
  "bbox_loss_coefficient": 5,
  "box_noise_scale": 1.0,
  "class_cost": 1,
  "d_model": 256,
  "decoder_activation_function": "relu",
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 1024,
  "decoder_in_channels": [
    256,
    256,
    256
  ],
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_n_points": 4,
  "dice_loss_coefficient": 1,
  "dilation": null,
  "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_layerdrop": 0.0,
  "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,
  "giou_cost": 2,
  "giou_loss_coefficient": 2,
  "hidden_expansion": 1.0,
  "init_std": 0.02,
  "init_xavier_std": 1.0,
  "initializer_range": 0.01,
  "is_encoder_decoder": true,
  "label_noise_ratio": 0.5,
  "layer_norm_eps": 1e-05,
  "learn_initial_query": false,
  "mask_loss_coefficient": 1,
  "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": "detr",
  "normalize_before": false,
  "num_channels": 3,
  "num_denoising": 100,
  "num_feature_levels": 3,
  "num_hidden_layers": 1,
  "num_queries": 300,
  "position_embedding_type": "sine",
  "positional_encoding_temperature": 10000,
  "torch_dtype": "float32",
  "transformers_version": "4.47.0",
  "use_focal_loss": true,
  "use_pretrained_backbone": false,
  "use_timm_backbone": false,
  "weight_loss_bbox": 5.0,
  "weight_loss_giou": 2.0,
  "weight_loss_vfl": 1.0,
  "with_box_refine": true
}