{
  "architectures": [
    "BevformerFor3DObjectDetection"
  ],
  "as_two_stage": false,
  "backbone_config": {
    "_name_or_path": "",
    "architectures": null,
    "chunk_size_feed_forward": 0,
    "depths": [
      3,
      4,
      6,
      3
    ],
    "downsample_in_bottleneck": false,
    "downsample_in_first_stage": false,
    "dtype": null,
    "embedding_size": 64,
    "hidden_act": "relu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_type": "bottleneck",
    "model_type": "resnet",
    "num_channels": 3,
    "out_features": [
      "stage4"
    ],
    "out_indices": [
      4
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "problem_type": null,
    "return_dict": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ]
  },
  "bev_height": 50,
  "bev_width": 50,
  "can_bus_dim": 18,
  "can_bus_norm": true,
  "d_model": 256,
  "dropout": 0.1,
  "dtype": "float32",
  "ffn_dim": 512,
  "hidden_act": "relu",
  "id2label": {
    "0": "car",
    "1": "truck",
    "2": "construction_vehicle",
    "3": "bus",
    "4": "trailer",
    "5": "barrier",
    "6": "motorcycle",
    "7": "bicycle",
    "8": "pedestrian",
    "9": "traffic_cone"
  },
  "label2id": null,
  "model_type": "bevformer",
  "num_attention_heads": 8,
  "num_cameras": 6,
  "num_decoder_layers": 6,
  "num_encoder_layers": 3,
  "num_feature_levels": 1,
  "num_points_in_bev": 8,
  "num_points_in_pillar": 4,
  "num_queries": 900,
  "point_cloud_range": [
    -51.2,
    -51.2,
    -5.0,
    51.2,
    51.2,
    3.0
  ],
  "rotate_center": [
    100.0,
    100.0
  ],
  "rotate_prev_bev": true,
  "transformers_version": "5.21.0.dev0",
  "use_can_bus": true,
  "use_shift": true,
  "with_box_refine": true
}