ppyolo_r18vd.yml

architecture: YOLOv3
use_gpu: true
max_iters: 250000
log_smooth_window: 20
log_iter: 20
save_dir: output
snapshot_iter: 10000
metric: COCO
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar
weights: output/ppyolo_tiny/model_final
num_classes: 80
use_fine_grained_loss: true
use_ema: true
ema_decay: 0.9998

YOLOv3:
  backbone: ResNet
  yolo_head: YOLOv3Head
  use_fine_grained_loss: true

ResNet:
  norm_type: sync_bn
  freeze_at: 0
  freeze_norm: false
  norm_decay: 0.
  depth: 18
  feature_maps: [4, 5]
  variant: d

YOLOv3Head:
  anchor_masks: [[3, 4, 5], [0, 1, 2]]
  anchors: [[10, 14], [23, 27], [37, 58],
            [81, 82], [135, 169], [344, 319]]
  norm_decay: 0.
  conv_block_num: 0
  scale_x_y: 1.05
  yolo_loss: YOLOv3Loss
  nms: MatrixNMS
  drop_block: true

YOLOv3Loss:
  ignore_thresh: 0.7
  scale_x_y: 1.05
  label_smooth: false
  use_fine_grained_loss: true
  iou_loss: IouLoss

IouLoss:
  loss_weight: 2.5
  max_height: 608
  max_width: 608

MatrixNMS:
    background_label: -1
    keep_top_k: 100
    normalized: false
    score_threshold: 0.01
    post_threshold: 0.01

LearningRate:
  base_lr: 0.004
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 150000
    - 200000
  - !LinearWarmup
    start_factor: 0.
    steps: 4000

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

_READER_: 'ppyolo_reader.yml'
TrainReader:
  inputs_def:
    fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
    num_max_boxes: 50
  dataset:
    !COCODataSet
      image_dir: train2017
      anno_path: annotations/instances_train2017.json
      dataset_dir: train_data/dataset/coco
      with_background: false
  sample_transforms:
    - !DecodeImage
      to_rgb: True
      with_mixup: True
    - !MixupImage
      alpha: 1.5
      beta: 1.5
    - !ColorDistort {}
    - !RandomExpand
      fill_value: [123.675, 116.28, 103.53]
    - !RandomCrop {}
    - !RandomFlipImage
      is_normalized: false
    - !NormalizeBox {}
    - !PadBox
      num_max_boxes: 50
    - !BboxXYXY2XYWH {}
  batch_transforms:
  - !RandomShape
    sizes: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
    random_inter: True
  - !NormalizeImage
    mean: [0.485, 0.456, 0.406]
    std: [0.229, 0.224, 0.225]
    is_scale: True
    is_channel_first: false
  - !Permute
    to_bgr: false
    channel_first: True
  # Gt2YoloTarget is only used when use_fine_grained_loss set as true,
  # this operator will be deleted automatically if use_fine_grained_loss
  # is set as false
  - !Gt2YoloTarget
    anchor_masks: [[3, 4, 5], [0, 1, 2]]
    anchors: [[10, 14], [23, 27], [37, 58],
              [81, 82], [135, 169], [344, 319]]
    downsample_ratios: [32, 16]
  batch_size: 32
  shuffle: true
  mixup_epoch: 500
  drop_last: true
  worker_num: 16
  bufsize: 8
  use_process: true