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


DETR:
  backbone: ResNet
  transformer: DETRTransformer
  detr_head: DETRHead
  post_process: DETRBBoxPostProcess


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


DETRTransformer:
  num_queries: 100
  position_embed_type: sine
  nhead: 8
  num_encoder_layers: 6
  num_decoder_layers: 6
  dim_feedforward: 2048
  dropout: 0.1
  activation: relu


DETRHead:
  num_mlp_layers: 3


DETRLoss:
  loss_coeff: {class: 1, bbox: 5, giou: 2, no_object: 0.1, mask: 1, dice: 1}
  aux_loss: True


HungarianMatcher:
  matcher_coeff: {class: 1, bbox: 5, giou: 2}