rtdetr_focalnet_L_384_3x_coco.yml

_BASE_: [
  '../datasets/coco_detection.yml',
  '../runtime.yml',
  '_base_/optimizer_6x.yml',
  '_base_/rtdetr_r50vd.yml',
  '_base_/rtdetr_reader.yml',
]

weights: output/rtdetr_focalnet_L_384_3x_coco/model_final
find_unused_parameters: True
log_iter: 100
snapshot_epoch: 2

pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/focalnet_large_fl4_pretrained_on_o365.pdparams
DETR:
  backbone: FocalNet
  neck: HybridEncoder
  transformer: RTDETRTransformer
  detr_head: DINOHead
  post_process: DETRPostProcess

FocalNet:
  arch: 'focalnet_L_384_22k_fl4'
  out_indices: [1, 2, 3]

HybridEncoder:
  hidden_dim: 256
  use_encoder_idx: [2]
  num_encoder_layers: 6 #
  encoder_layer:
    name: TransformerLayer
    d_model: 256
    nhead: 8
    dim_feedforward: 2048
    dropout: 0.
    activation: 'gelu'
  expansion: 1.0


RTDETRTransformer:
  num_queries: 300
  position_embed_type: sine
  feat_strides: [8, 16, 32]
  num_levels: 3
  nhead: 8
  num_decoder_layers: 6
  dim_feedforward: 2048 #
  dropout: 0.0
  activation: relu
  num_denoising: 100
  label_noise_ratio: 0.5
  box_noise_scale: 1.0
  learnt_init_query: False
  query_pos_head_inv_sig: True #

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

DETRPostProcess:
  num_top_queries: 300


epoch: 36
LearningRate:
  base_lr: 0.0001
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones: [36]
    use_warmup: false

OptimizerBuilder:
  clip_grad_by_norm: 0.1
  regularizer: false
  optimizer:
    type: AdamW
    weight_decay: 0.0001
    param_groups:
      - params: ['absolute_pos_embed', 'relative_position_bias_table', 'norm']
        weight_decay: 0.0