architecture: CascadeRCNN
train_feed: FasterRCNNTrainFeed
eval_feed: FasterRCNNEvalFeed
test_feed: FasterRCNNTestFeed
max_iters: 90000
snapshot_iter: 10000
use_gpu: true
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
weights: output/cascade_rcnn_r50_fpn_1x/model_final
metric: COCO
num_classes: 81

CascadeRCNN:
  backbone: ResNet
  fpn: FPN
  rpn_head: FPNRPNHead
  roi_extractor: FPNRoIAlign
  bbox_head: CascadeBBoxHead
  bbox_assigner: CascadeBBoxAssigner

ResNet:
  norm_type: affine_channel
  depth: 50
  feature_maps: [2, 3, 4, 5]
  freeze_at: 2
  variant: b

FPN:
  min_level: 2
  max_level: 6
  num_chan: 256
  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]

FPNRPNHead:
  anchor_generator:
    anchor_sizes: [32, 64, 128, 256, 512]
    aspect_ratios: [0.5, 1.0, 2.0]
    stride: [16.0, 16.0]
    variance: [1.0, 1.0, 1.0, 1.0]
  anchor_start_size: 32
  min_level: 2
  max_level: 6
  num_chan: 256
  rpn_target_assign:
    rpn_batch_size_per_im: 256
    rpn_fg_fraction: 0.5
    rpn_positive_overlap: 0.7
    rpn_negative_overlap: 0.3
    rpn_straddle_thresh: 0.0
  train_proposal:
    min_size: 0.0
    nms_thresh: 0.7
    pre_nms_top_n: 2000
    post_nms_top_n: 2000
  test_proposal:
    min_size: 0.0
    nms_thresh: 0.7
    pre_nms_top_n: 1000
    post_nms_top_n: 1000

FPNRoIAlign:
  canconical_level: 4
  canonical_size: 224
  min_level: 2
  max_level: 5
  box_resolution: 7
  sampling_ratio: 2

CascadeBBoxAssigner:
  batch_size_per_im: 512
  bbox_reg_weights: [10, 20, 30]
  bg_thresh_lo: [0.0, 0.0, 0.0]
  bg_thresh_hi: [0.5, 0.6, 0.7]
  fg_thresh: [0.5, 0.6, 0.7]
  fg_fraction: 0.25

CascadeBBoxHead:
  head: CascadeTwoFCHead
  nms:
    keep_top_k: 100
    nms_threshold: 0.5
    score_threshold: 0.05

CascadeTwoFCHead:
  mlp_dim: 1024

MultiScaleTEST:
  score_thresh: 0.05
  nms_thresh: 0.5
  detections_per_im: 100
  enable_voting: true
  vote_thresh: 0.9

LearningRate:
  base_lr: 0.02
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones: [60000, 80000]
  - !LinearWarmup
    start_factor: 0.3333333333333333
    steps: 500

OptimizerBuilder:
  optimizer:
    momentum: 0.9
    type: Momentum
  regularizer:
    factor: 0.0001
    type: L2

FasterRCNNTrainFeed:
  batch_size: 2
  dataset:
    dataset_dir: dataset/coco
    annotation: annotations/instances_train2017.json
    image_dir: train2017
  batch_transforms:
  - !PadBatch
    pad_to_stride: 32
  drop_last: false
  num_workers: 2

FasterRCNNEvalFeed:
  batch_size: 1
  dataset:
    dataset_dir: dataset/coco
    annotation: annotations/instances_val2017.json
    image_dir: val2017
  sample_transforms:
  - !DecodeImage
    to_rgb: true
  - !NormalizeImage
    is_channel_first: false
    is_scale: true
    mean:
    - 0.485
    - 0.456
    - 0.406
    std:
    - 0.229
    - 0.224
    - 0.225
  - !MultiscaleTestResize
    origin_target_size: 800
    origin_max_size: 1333
    target_size:
    - 400
    - 500
    - 600
    - 700
    - 900
    - 1000
    - 1100
    - 1200
    max_size: 2000
    use_flip: true
  - !Permute
    channel_first: true
    to_bgr: false
  batch_transforms:
  - !PadMSTest
    pad_to_stride: 32
  num_scale: 18
  num_workers: 2

FasterRCNNTestFeed:
  batch_size: 1
  dataset:
    annotation: dataset/coco/annotations/instances_val2017.json
  batch_transforms:
  - !PadBatch
    pad_to_stride: 32
  drop_last: false
  num_workers: 2