[PaddleDetection] add cascade deformable mdoels (#3082)

* Add cascade deformable mdoels
* Fix MODLE_ZOO.md

configs/dcn/cascade_rcnn_dcn_r101_vd_fpn_1x.yml

+architecture: CascadeRCNN
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 90000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+log_iter: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
+weights: output/cascade_rcnn_dcn_r101_vd_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: bn
+  depth: 101
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  variant: d
+  dcn_stages: [3, 4, 5]
+
+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: FC6FC7Head
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+FC6FC7Head:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [60000, 80000]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+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
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+
+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

configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml

+architecture: CascadeRCNN
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 90000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+log_iter: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
+weights: output/cascade_rcnn_dcn_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: bn
+  depth: 50
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  variant: b
+  dcn_stages: [3, 4, 5]
+
+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: FC6FC7Head
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+FC6FC7Head:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [60000, 80000]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+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
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+
+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

configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml

+architecture: CascadeRCNN
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 90000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+log_iter: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
+weights: output/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x/model_final
+metric: COCO
+num_classes: 81
+
+CascadeRCNN:
+  backbone: ResNeXt
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: CascadeBBoxHead
+  bbox_assigner: CascadeBBoxAssigner
+
+ResNeXt:
+  norm_type: bn
+  depth: 101
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  group_width: 4                                                                                                                                          
+  groups: 64
+  variant: d
+  dcn_stages: [3, 4, 5]
+
+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: FC6FC7Head
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+FC6FC7Head:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [60000, 80000]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+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
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+
+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

configs/retinanet_x101_vd_64x4d_fpn_1x.yml

+architecture: RetinaNet
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 180000
+use_gpu: true
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
+weights: output/retinanet_x101_vd_64x4d_fpn_1x/model_final
+log_smooth_window: 20
+log_iter: 20
+snapshot_iter: 30000
+metric: COCO
+save_dir: output
+num_classes: 81
+
+RetinaNet:
+  backbone: ResNeXt
+  fpn: FPN
+  retina_head: RetinaHead
+
+ResNeXt:
+  depth: 101
+  feature_maps: [3, 4, 5]
+  freeze_at: 2
+  group_width: 4
+  groups: 64
+  norm_type: bn
+  variant: d
+
+FPN:
+  max_level: 7
+  min_level: 3
+  num_chan: 256
+  spatial_scale: [0.03125, 0.0625, 0.125]
+  has_extra_convs: true
+
+RetinaHead:
+  num_convs_per_octave: 4
+  num_chan: 256
+  max_level: 7
+  min_level: 3
+  prior_prob: 0.01
+  base_scale: 4
+  num_scales_per_octave: 3
+  anchor_generator:
+    aspect_ratios: [1.0, 2.0, 0.5]
+    variance: [1.0, 1.0, 1.0, 1.0]
+  target_assign:
+    positive_overlap: 0.5
+    negative_overlap: 0.4
+  gamma: 2.0
+  alpha: 0.25
+  sigma: 3.0151134457776365
+  output_decoder:
+    score_thresh: 0.05
+    nms_thresh: 0.5
+    pre_nms_top_n: 1000
+    detections_per_im: 100
+    nms_eta: 1.0
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [120000, 160000]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+FasterRCNNTrainFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_train2017.json
+    image_dir: train2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+  num_workers: 2
+
+FasterRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+  num_workers: 2
+
+FasterRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: dataset/coco/annotations/instances_val2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+  num_workers: 2

docs/MODEL_ZOO.md

@@ -9,7 +9,7 @@
 
 ## Common settings
 
-- All models below except SSD were trained on `coco_2017_train`, and tested on `coco_2017_val`.
+- All models below were trained on `coco_2017_train`, and tested on `coco_2017_val`.
 - Batch Normalization layers in backbones are replaced by Affine Channel layers.
 - Unless otherwise noted, all ResNet backbones adopt the [ResNet-B](https://arxiv.org/pdf/1812.01187) variant..
 - For RCNN and RetinaNet models, only horizontal flipping data augmentation was used in the training phase and no augmentations were used in the testing phase.
@@ -70,6 +70,9 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
 | ResNet50-vd-FPN      | Mask           | c3-c5   |    1      |   2x    |  42.9  |  38.0   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) |
 | ResNet101-vd-FPN     | Mask           | c3-c5   |    1      |   1x    |  44.6  |  39.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) |
 | ResNeXt101-vd-FPN    | Mask           | c3-c5   |    1      |   1x    |  46.2  |  40.4   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |
+| 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) |
 
 #### Notes:
 - Deformable ConvNets v2(dcn_v2) reference from [Deformable ConvNets v2](https://arxiv.org/abs/1811.11168).
@@ -112,15 +115,17 @@ results of image size 608/416/320 above.
 ### RetinaNet
 
 | Backbone          | Image/gpu | Lr schd | Box AP | Download  |
-| :-----------  | :-----: | :-----: | :----: | :-------: |
+| :---------------: | :-----: | :-----: | :----: | :-------: |
 | ResNet50-FPN      |    2    |   1x    |  36.0  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar)  |
 | ResNet101-FPN     |    2    |   1x    |  37.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) |
+| ResNeXt101-vd-FPN |    1    |   1x    |  40.5  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) |
 
 **Notes:** In RetinaNet, the base LR is changed to 0.01 for minibatch size 16.
 
 ### SSD
 
 | Backbone     | Size | Image/gpu | Lr schd | Box AP | Download  |
+| :----------: | :--: | :-------: | :-----: | :----: | :-------: |
 | VGG16        | 300  |     8   |   40w  |  25.1  | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) |
 | VGG16        | 512  |     8   |   40w  |  29.1  | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) |
 

docs/MODEL_ZOO_cn.md

@@ -10,7 +10,7 @@
 
 ## 通用设置
 
-- SSD模型在VOC数据集中训练和测试，其余所有模型均在COCO17数据集中训练和测试。
+- 所有模型均在COCO17数据集中训练和测试。
 - 除非特殊说明，所有ResNet骨干网络采用[ResNet-B](https://arxiv.org/pdf/1812.01187)结构。
 - 对于RCNN和RetinaNet系列模型，训练阶段仅使用水平翻转作为数据增强，测试阶段不使用数据增强。
 
@@ -70,6 +70,9 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
 | ResNet50-vd-FPN      | Mask           | c3-c5   |    1      |   2x    |  42.9  |  38.0   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r50_vd_fpn_2x.tar) |
 | ResNet101-vd-FPN     | Mask           | c3-c5   |    1      |   1x    |  44.6  |  39.2   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_r101_vd_fpn_1x.tar) |
 | ResNeXt101-vd-FPN    | Mask           | c3-c5   |    1      |   1x    |  46.2  |  40.4   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.tar) |
+| 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) |
 
 #### 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).
@@ -109,15 +112,17 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
 ### RetinaNet
 
 |   骨架网络        | 每张GPU图片个数 | 学习率策略 | Box AP | 下载  |
-| :-----------  | :-----: | :-----: | :----: | :-------: |
+| :---------------: | :-----: | :-----: | :----: | :-------: |
 | ResNet50-FPN      |    2    |   1x    |  36.0  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar)  |
 | ResNet101-FPN     |    2    |   1x    |  37.3  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) |
+| ResNeXt101-vd-FPN |    1    |   1x    |  40.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_x101_vd_64x4d_fpn_1x.tar) |
 
 **注意事项:** RetinaNet系列模型中，在总batch size为16下情况下，初始学习率改为0.01。
 
 ### SSD
 
 |  骨架网络     | 输入尺寸 | 每张GPU图片个数 | 学习率策略 | Box AP | 下载 |
+| :----------: | :--: | :-------: | :-----: | :----: | :-------: |
 | VGG16        | 300  |     8   |   40万  |  25.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_300.tar) |
 | VGG16        | 512  |     8   |   40万  |  29.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/ssd_vgg16_512.tar) |