config.json

{
  "activation": "relu",
  "alpha": 0.25,
  "backbone": "resnet50",
  "backbone_config": null,
  "backbone_kwargs": {
    "in_chans": 3,
    "out_indices": [
      1,
      2,
      3,
      4
    ]
  },
  "backbone_multiplier": 1.0,
  "class_weight": 2.0,
  "deep_supervision": true,
  "dilation": false,
  "dim_dynamic": 64,
  "dim_feedforward": 2048,
  "dropout": 0.0,
  "fpn_out_channels": 256,
  "gamma": 2.0,
  "giou_weight": 2.0,
  "hidden_dim": 256,
  "l1_weight": 5.0,
  "model_type": "diffusiondet",
  "no_object_weight": 0.1,
  "num_attn_heads": 8,
  "num_channels": 3,
  "num_cls": 1,
  "num_dynamic": 2,
  "num_heads": 6,
  "num_proposals": 300,
  "num_reg": 3,
  "optimizer": "ADAMW",
  "ota_k": 5,
  "pixel_mean": [
    123.675,
    116.28,
    103.53
  ],
  "pixel_std": [
    58.395,
    57.12,
    57.375
  ],
  "pooler_resolution": 7,
  "prior_prob": 0.01,
  "resnet_in_features": [
    "res2",
    "res3",
    "res4",
    "res5"
  ],
  "resnet_out_features": [
    "res2",
    "res3",
    "res4",
    "res5"
  ],
  "roi_head_in_features": [
    "p2",
    "p3",
    "p4",
    "p5"
  ],
  "sample_step": 1,
  "sampling_ratio": 2,
  "snr_scale": 2.0,
  "swin_out_features": [
    0,
    1,
    2,
    3
  ],
  "swin_size": "B",
  "transformers_version": "4.47.0.dev0",
  "use_fed_loss": false,
  "use_focal": true,
  "use_nms": true,
  "use_pretrained_backbone": true,
  "use_swin_checkpoint": false,
  "use_timm_backbone": true
}