PaddleX/paddlex/repo_apis/PaddleDetection_api/configs/YOLOv3-ResNet50_vd_DCN.yaml

# Runtime
epoch: 270
use_gpu: true
use_xpu: false
use_mlu: false
use_npu: false
log_iter: 20
save_dir: output
snapshot_epoch: 1
print_flops: false
print_params: false

# Dataset
metric: COCO
num_classes: 80

TrainDataset:
  name: COCODataSet
  image_dir: train2017
  anno_path: annotations/instances_train2017.json
  dataset_dir: dataset/coco
  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']

EvalDataset:
  name: COCODataSet
  image_dir: val2017
  anno_path: annotations/instances_val2017.json
  dataset_dir: dataset/coco
  allow_empty: true

TestDataset:
  name: ImageFolder
  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'

worker_num: 2
TrainReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}
    - Mixup: {alpha: 1.5, beta: 1.5}
    - RandomDistort: {}
    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
    - RandomCrop: {}
    - RandomFlip: {}
  batch_transforms:
    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608], random_size: True, random_interp: True, keep_ratio: False}
    - NormalizeBox: {}
    - PadBox: {num_max_boxes: 50}
    - 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: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]}
  batch_size: 8
  shuffle: true
  drop_last: true
  mixup_epoch: 250
  use_shared_memory: true

EvalReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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

TestReader:
  inputs_def:
    image_shape: [3, 608, 608]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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

# Model
architecture: YOLOv3
pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams
norm_type: sync_bn

YOLOv3:
  backbone: ResNet
  neck: YOLOv3FPN
  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.

# YOLOv3FPN:

YOLOv3Head:
  anchors: [[10, 13], [16, 30], [33, 23],
            [30, 61], [62, 45], [59, 119],
            [116, 90], [156, 198], [373, 326]]
  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
  loss: YOLOv3Loss

YOLOv3Loss:
  ignore_thresh: 0.7
  downsample: [32, 16, 8]
  label_smooth: false

BBoxPostProcess:
  decode:
    name: YOLOBox
    conf_thresh: 0.005
    downsample_ratio: 32
    clip_bbox: true
  nms:
    name: MultiClassNMS
    keep_top_k: 100
    score_threshold: 0.01
    nms_threshold: 0.45
    nms_top_k: 1000

# Optimizer
LearningRate:
  base_lr: 0.001
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones:
    - 216
    - 243
  - !LinearWarmup
    start_factor: 0.
    steps: 4000

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

# Export
export:
  post_process: True  # Whether post-processing is included in the network when export model.
  nms: True           # Whether NMS is included in the network when export model.
  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
  fuse_conv_bn: False