architecture: YOLOv3
train_feed: YoloTrainFeed
eval_feed: YoloEvalFeed
test_feed: YoloTestFeed
use_gpu: true
max_iters: 55000
log_smooth_window: 20
save_dir: output
snapshot_iter: 10000
metric: COCO
pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/ResNet50_vd_obj365_pretrained.tar 
weights: output/yolov3_r50vd_dcn_obj365_pretrained_coco/model_final
num_classes: 80

YOLOv3:
  backbone: ResNet
  yolo_head: YOLOv3Head

ResNet:
  norm_type: sync_bn
  freeze_at: 0
  freeze_norm: false
  norm_decay: 0.
  depth: 50
  feature_maps: [3, 4, 5]
  variant: d
  dcn_v2_stages: [5]

YOLOv3Head:
  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
  anchors: [[10, 13], [16, 30], [33, 23],
            [30, 61], [62, 45], [59, 119],
            [116, 90], [156, 198], [373, 326]]
  norm_decay: 0.
  ignore_thresh: 0.7
  label_smooth: true
  nms:
    background_label: -1
    keep_top_k: 100
    nms_threshold: 0.45
    nms_top_k: 1000
    normalized: false
    score_threshold: 0.01

LearningRate:
  base_lr: 0.001
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 40000
    - 50000
  - !LinearWarmup
    start_factor: 0.
    steps: 4000

OptimizerBuilder:
  optimizer:
    momentum: 0.9
    type: Momentum
  regularizer:
    factor: 0.0005
    type: L2

YoloTrainFeed:
  batch_size: 8
  dataset:
    dataset_dir: dataset/coco
    annotation: annotations/instances_train2017.json
    image_dir: train2017
  sample_transforms:
    - !DecodeImage
      to_rgb: True
      with_mixup: False
    - !NormalizeBox {}
    - !CropImage
      batch_sampler: [[1, 1, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.1, 1.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.3, 1.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.5, 1.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.7, 1.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.9, 1.0],
        [1, 50, 0.3, 1.0, 0.5, 2.0, 0.0, 1.0]]
    - !RandomInterpImage
      target_size: 608
    - !RandomFlipImage
      is_normalized: True
    - !NormalizeImage
      mean:
      - 0.485
      - 0.456
      - 0.406
      std:
      - 0.229
      - 0.224
      - 0.225
      is_scale: False
      is_channel_first: False      
    - !Permute
      to_bgr: False
  num_workers: 8
  bufsize: 128
  use_process: true

YoloEvalFeed:
  batch_size: 8
  image_shape: [3, 608, 608]
  dataset:
    dataset_dir: dataset/coco
    annotation: annotations/instances_val2017.json
    image_dir: val2017
  sample_transforms:
    - !DecodeImage
      to_rgb: True
      with_mixup: False
    - !ResizeImage
      interp: 2 
      target_size: 608
    - !NormalizeImage
      mean:
      - 0.485
      - 0.456
      - 0.406
      std:
      - 0.229
      - 0.224
      - 0.225
      is_scale: False
      is_channel_first: False      
    - !Permute
      to_bgr: False


YoloTestFeed:
  batch_size: 1
  image_shape: [3, 608, 608]
  dataset:
    annotation: dataset/coco/annotations/instances_val2017.json
  sample_transforms:
    - !DecodeImage
      to_rgb: True
      with_mixup: False
    - !ResizeImage
      interp: 2 
      target_size: 608
    - !NormalizeImage
      mean:
      - 0.485
      - 0.456
      - 0.406
      std:
      - 0.229
      - 0.224
      - 0.225
      is_scale: False
      is_channel_first: False      
    - !Permute
      to_bgr: False