release 51.9 model (#3691)

configs/dcn/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.yml

+architecture: CascadeMaskRCNN
+train_feed: MaskRCNNTrainFeed
+eval_feed: MaskRCNNEvalFeed
+test_feed: MaskRCNNTestFeed
+max_iters: 300000
+snapshot_iter: 10
+use_gpu: true
+log_iter: 20
+log_smooth_window: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_caffe_pretrained.tar 
+weights: output/cascade_mask_rcnn_dcn_se154_vd_fpn_gn_s1x/model_final/
+metric: COCO
+num_classes: 81
+
+CascadeMaskRCNN:
+  backbone: SENet
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: CascadeBBoxHead
+  bbox_assigner: CascadeBBoxAssigner
+  mask_assigner: MaskAssigner
+  mask_head: MaskHead
+
+SENet:
+  depth: 152
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  group_width: 4
+  groups: 64
+  norm_type: bn
+  freeze_norm: True
+  variant: d
+  dcn_v2_stages: [3, 4, 5]
+  std_senet: True
+
+FPN:
+  max_level: 6
+  min_level: 2
+  num_chan: 256
+  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
+  freeze_norm: False
+  norm_type: gn
+
+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
+  box_resolution: 7
+  sampling_ratio: 2
+  mask_resolution: 14
+
+MaskHead:
+  dilation: 1
+  conv_dim: 256
+  num_convs: 4
+  resolution: 28
+  norm_type: gn
+
+CascadeBBoxAssigner:
+  batch_size_per_im: 512
+  bbox_reg_weights: [10, 20, 30]
+  bg_thresh_hi: [0.5, 0.6, 0.7]
+  bg_thresh_lo: [0.0, 0.0, 0.0]
+  fg_fraction: 0.25
+  fg_thresh: [0.5, 0.6, 0.7]
+
+MaskAssigner:
+  resolution: 28
+
+CascadeBBoxHead:
+  head: CascadeXConvNormHead 
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+CascadeXConvNormHead:
+  norm_type: gn
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [240000, 280000]
+  - !LinearWarmup
+    start_factor: 0.01
+    steps: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+MaskRCNNTrainFeed:
+  # batch size per device
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    image_dir: train2017
+    annotation: annotations/instances_train2017.json
+  sample_transforms: 
+  - !DecodeImage
+    to_rgb: False
+    with_mixup: False
+  - !RandomFlipImage
+    is_mask_flip: true
+    is_normalized: false
+    prob: 0.5
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: False
+    mean:
+    - 102.9801 
+    - 115.9465
+    - 122.7717
+    std:
+    - 1.0 
+    - 1.0 
+    - 1.0 
+  - !ResizeImage
+    interp: 1
+    target_size:
+    - 416
+    - 448
+    - 480
+    - 512
+    - 544
+    - 576
+    - 608
+    - 640
+    - 672
+    - 704 
+    - 736
+    - 768
+    - 800
+    - 832
+    - 864
+    - 896
+    - 928
+    - 960
+    - 992
+    - 1024
+    - 1056
+    - 1088
+    - 1120
+    - 1152
+    - 1184
+    - 1216
+    - 1248
+    - 1280
+    - 1312
+    - 1344
+    - 1376
+    - 1408
+    max_size: 1600
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 8
+
+MaskRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+  sample_transforms: 
+  - !DecodeImage
+    to_rgb: False
+    with_mixup: False
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: False
+    mean:
+    - 102.9801 
+    - 115.9465
+    - 122.7717
+    std:
+    - 1.0 
+    - 1.0 
+    - 1.0 
+  - !ResizeImage
+    interp: 1
+    target_size:
+    - 800
+    max_size: 1333
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+
+MaskRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: dataset/coco/annotations/instances_val2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2

docs/MODEL_ZOO.md

@@ -76,6 +76,7 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
 | ResNet50-FPN            | Cascade Faster | c3-c5 |     2     |   1x    |       -        |  44.2  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) |
 | ResNet101-vd-FPN        | Cascade Faster | c3-c5 |     2     |   1x    |       -        |  46.4  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) |
 | ResNeXt101-vd-FPN       | Cascade Faster | c3-c5 |     2     |   1x    |       -        |  47.3  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |
+| SENet154-vd-FPN         | Cascade Mask   | c3-c5 |    1      |  1.44x  |       -        |  51.9  |  43.9   | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) |
 
 #### Notes:
 - Deformable ConvNets v2(dcn_v2) reference from [Deformable ConvNets v2](https://arxiv.org/abs/1811.11168).

docs/MODEL_ZOO_cn.md

@@ -75,6 +75,7 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
 | ResNet50-FPN         | Cascade Faster | c3-c5   |    2      |   1x    |      -        |  44.2  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar) |
 | ResNet101-vd-FPN     | Cascade Faster | c3-c5   |    2      |   1x    |      -        |  46.4  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r101_vd_fpn_1x.tar) |
 | ResNeXt101-vd-FPN    | Cascade Faster | c3-c5   |    2      |   1x    |      -        |  47.3  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |
+| SENet154-vd-FPN      | Cascade Mask   | c3-c5   |    1      |  1.44x  |      -        |  51.9  |  43.9   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_mask_rcnn_dcnv2_se154_vd_fpn_gn_s1x.tar) |
 
 #### 注意事项:
 - Deformable卷积网络v2(dcn_v2)参考自论文[Deformable ConvNets v2](https://arxiv.org/abs/1811.11168).