ppyolov2_r50vd_dcn_365e_lvjian1_640.yml 3.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
architecture: YOLOv3
pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams
norm_type: sync_bn
use_ema: true
ema_decay: 0.9998
use_gpu: true
use_xpu: false
log_iter: 100
save_dir: output

metric: COCO
num_classes: 5

TrainDataset:
  !COCODataSet
    image_dir: images
    anno_path: train.json
    dataset_dir: dataset/slice_lvjian1_data/train
    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']

EvalDataset:
  !COCODataSet
    image_dir: images
    anno_path: val.json
    dataset_dir: dataset/slice_lvjian1_data/eval

TestDataset:
  !ImageFolder
    anno_path: val.json
    dataset_dir: dataset/slice_lvjian1_data/eval


epoch: 20
LearningRate:
  base_lr: 0.0002
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 80
  - !LinearWarmup
    start_factor: 0.
    steps: 1000


snapshot_epoch: 3
worker_num: 2
TrainReader:
  inputs_def:
    num_max_boxes: 100
  sample_transforms:
    - Decode: {}
    - RandomDistort: {}
    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
    - RandomCrop: {}
    - RandomFlip: {}
  batch_transforms:
    - BatchRandomResize: {target_size: [576, 608, 640, 672, 704], random_size: True, random_interp: True, keep_ratio: False}
    - NormalizeBox: {}
    - PadBox: {num_max_boxes: 100}
    - BboxXYXY2XYWH: {}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[8, 7], [24, 12], [14, 25], [37, 35], [30, 140], [89, 52], [93, 189], [226, 99], [264, 352]], downsample_ratios: [32, 16, 8]}
  batch_size: 2
  shuffle: true
  drop_last: true
  use_shared_memory: true

EvalReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [640, 640], keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 8

TestReader:
  inputs_def:
    image_shape: [3, 640, 640]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [640, 640], keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 1

OptimizerBuilder:
  clip_grad_by_norm: 35.
  optimizer:
    momentum: 0.9
    type: Momentum
  regularizer:
    factor: 0.0005
    type: L2

YOLOv3:
  backbone: ResNet
  neck: PPYOLOPAN
  yolo_head: YOLOv3Head
  post_process: BBoxPostProcess

ResNet:
  depth: 50
  variant: d
  return_idx: [1, 2, 3]
  dcn_v2_stages: [3]
  freeze_at: -1
  freeze_norm: false
  norm_decay: 0.

PPYOLOPAN:
  drop_block: true
  block_size: 3
  keep_prob: 0.9
  spp: true

YOLOv3Head:
  anchors: [[8, 7], [24, 12], [14, 25],
            [37, 35], [30, 140], [89, 52],
            [93, 189], [226, 99], [264, 352]]
  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
  loss: YOLOv3Loss
  iou_aware: true
  iou_aware_factor: 0.5

YOLOv3Loss:
  ignore_thresh: 0.7
  downsample: [32, 16, 8]
  label_smooth: false
  scale_x_y: 1.05
  iou_loss: IouLoss
  iou_aware_loss: IouAwareLoss

IouLoss:
  loss_weight: 2.5
  loss_square: true

IouAwareLoss:
  loss_weight: 1.0

BBoxPostProcess:
  decode:
    name: YOLOBox
    conf_thresh: 0.01
    downsample_ratio: 32
    clip_bbox: true
    scale_x_y: 1.05
  nms:
    name: MatrixNMS
    keep_top_k: 100
    score_threshold: 0.01
    post_threshold: 0.01
    nms_top_k: -1
    background_label: -1