DocumentAIKit/configs/ppyoloe/application/ppyoloe_plus_crn_x_80e_sku110k.yml

_BASE_: [
  './_base_/sku110k.yml',
  '../../runtime.yml'
]

log_iter: 10
snapshot_epoch: 20
weights: output/ppyoloe_plus_crn_s_80e_coco/model_final

pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_x_obj365_pretrained.pdparams
depth_mult: 1.33
width_mult: 1.25


# arch
architecture: YOLOv3
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
custom_black_list: ['reduce_mean']

YOLOv3:
  backbone: CSPResNet
  neck: CustomCSPPAN
  yolo_head: PPYOLOEHead
  post_process: ~

CSPResNet:
  layers: [3, 6, 6, 3]
  channels: [64, 128, 256, 512, 1024]
  return_idx: [1, 2, 3]
  use_large_stem: True
  use_alpha: True

CustomCSPPAN:
  out_channels: [768, 384, 192]
  stage_num: 1
  block_num: 3
  act: 'swish'
  spp: true
  use_alpha: True

PPYOLOEHead:
  fpn_strides: [32, 16, 8]
  grid_cell_scale: 5.0
  grid_cell_offset: 0.5
  static_assigner_epoch: -1
  use_varifocal_loss: True
  loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
  static_assigner:
    name: ATSSAssigner
    topk: 9
  assigner:
    name: TaskAlignedAssigner
    topk: 13
    alpha: 1.0
    beta: 6.0
  nms:
    name: MultiClassNMS
    nms_top_k: 3000
    keep_top_k: 1000
    score_threshold: 0.01
    nms_threshold: 0.7


# reader
worker_num: 8
eval_height: &eval_height 960
eval_width: &eval_width 960
eval_size: &eval_size [*eval_height, *eval_width]

TrainReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [3000, 1800], keep_ratio: True, interp: 2}
    - RandomDistort: {}
    - RandomCrop: {}
    - RandomFlip: {}
  batch_transforms:
    - BatchRandomResize: {target_size: [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024, 1056, 1088, 1120, 1152], random_size: True, random_interp: True, keep_ratio: False}
    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
    - Permute: {}
    - PadGT: {}
  batch_size: 4
  shuffle: true
  drop_last: true
  use_shared_memory: true
  collate_batch: true

EvalReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
    - Permute: {}
  batch_size: 2

TestReader:
  inputs_def:
    image_shape: [3, *eval_height, *eval_width]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
    - Permute: {}
  batch_size: 1


# optimizer
epoch: 80

LearningRate:
  base_lr: 0.002
  schedulers:
    - !CosineDecay
      max_epochs: 96
    - !LinearWarmup
      start_factor: 0.
      epochs: 5

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