ppyolo_voc.yml

architecture: YOLOv3                                                                                                                               
use_gpu: true                                                                                                                                      
max_iters: 70000                                                                                                                                   
log_smooth_window: 20                                                                                                                              
log_iter: 20                                                                                                                                       
save_dir: output                                                                                                                                   
snapshot_iter: 10000                                                                                                                               
metric: VOC                                                                                                                                        
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar                                                
weights: output/ppyolo/model_final                                                                                                                 
num_classes: 20                                                                                                                                    
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: 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.
  coord_conv: true
  iou_aware: true
  iou_aware_factor: 0.4
  scale_x_y: 1.05
  spp: true
  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
  iou_aware_loss: IouAwareLoss

IouLoss:
  loss_weight: 2.5
  max_height: 608
  max_width: 608

IouAwareLoss:
  loss_weight: 1.0
  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: 0.00333
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 56000
    - 62000
  - !LinearWarmup
    start_factor: 0.
    steps: 4000

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

_READER_: 'ppyolo_reader.yml'
TrainReader:                                                                                                                                       
  dataset:                                                                                                                                         
    !VOCDataSet                                                                                                                                    
    dataset_dir: train_data/dataset/voc                                                                                                            
    anno_path: trainval.txt                                                                                                                        
    use_default_label: true                                                                                                                        
    with_background: false                                                                                                                         
  mixup_epoch: 350                                                                                                                                 
  batch_size: 12
                                                                                                                                                   
EvalReader:                                                                                                                                        
  inputs_def:                                                                                                                                      
    fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']                                                                   
    num_max_boxes: 50                                                                                                                              
  dataset:                                                                                                                                         
    !VOCDataSet                                                                                                                                    
    dataset_dir: train_data/dataset/voc                                                                                                            
    anno_path: test.txt                                                                                                                            
    use_default_label: true                                                                                                                        
    with_background: false                                                                                                                         
                                                                                                                                                   
TestReader:                                                                                                                                        
  dataset:                                                                                                                                         
    !ImageFolder                                                                                                                                   
    use_default_label: true                                                                                                                        
    with_background: false