architecture: MaskRCNN
use_gpu: true
max_iters: 180000
snapshot_iter: 10000
log_iter: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
metric: COCO
weights: output/mask_rcnn_r101_fpn_1x/model_final
num_classes: 81

MaskRCNN:
  backbone: ResNet
  fpn: FPN
  rpn_head: FPNRPNHead
  roi_extractor: FPNRoIAlign
  bbox_head: BBoxHead
  bbox_assigner: BBoxAssigner

ResNet:
  depth: 101
  feature_maps: [2, 3, 4, 5]
  freeze_at: 2
  norm_type: affine_channel

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

FPNRPNHead:
  anchor_generator:
    aspect_ratios: [0.5, 1.0, 2.0]
    variance: [1.0, 1.0, 1.0, 1.0]
  anchor_start_size: 32
  max_level: 6
  min_level: 2
  num_chan: 256
  rpn_target_assign:
    rpn_batch_size_per_im: 256
    rpn_fg_fraction: 0.5
    rpn_negative_overlap: 0.3
    rpn_positive_overlap: 0.7
    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
  max_level: 5
  min_level: 2
  sampling_ratio: 2
  box_resolution: 7
  mask_resolution: 14

MaskHead:
  dilation: 1
  conv_dim: 256
  num_convs: 4
  resolution: 28

BBoxAssigner:
  batch_size_per_im: 512
  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
  bg_thresh_hi: 0.5
  bg_thresh_lo: 0.0
  fg_fraction: 0.25
  fg_thresh: 0.5

MaskAssigner:
  resolution: 28

BBoxHead:
  head: TwoFCHead
  nms:
    keep_top_k: 100
    nms_threshold: 0.5
    score_threshold: 0.05

TwoFCHead:
  mlp_dim: 1024

LearningRate:
  base_lr: 0.01
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones: [120000, 160000]
  - !LinearWarmup
    start_factor: 0.3333333333333333
    steps: 500

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

_READER_: 'mask_fpn_reader.yml'