architecture: DETR
pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
hidden_dim: 256
use_focal_loss: True


DETR:
  backbone: ResNet
  transformer: DINOTransformer
  detr_head: DINOHead
  post_process: DETRBBoxPostProcess

ResNet:
  # index 0 stands for res2
  depth: 50
  norm_type: bn
  freeze_at: 0
  return_idx: [1, 2, 3]
  lr_mult_list: [0.0, 0.1, 0.1, 0.1]
  num_stages: 4

DINOTransformer:
  num_queries: 900
  position_embed_type: sine
  num_levels: 4
  nhead: 8
  num_encoder_layers: 6
  num_decoder_layers: 6
  dim_feedforward: 2048
  dropout: 0.0
  activation: relu
  pe_temperature: 20
  pe_offset: 0.0
  num_denoising: 100
  label_noise_ratio: 0.5
  box_noise_scale: 1.0
  learnt_init_query: True

DINOHead:
  loss:
    name: DINOLoss
    loss_coeff: {class: 1, bbox: 5, giou: 2}
    aux_loss: True
    matcher:
      name: HungarianMatcher
      matcher_coeff: {class: 2, bbox: 5, giou: 2}

DETRBBoxPostProcess:
  num_top_queries: 300