Add models basd on OpenImage-v5 and Object365 (#26)

* Add cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms model on oidv5 and obj365.
* Add obj365 config annotation
* Update docs.

Author: littletomatodonkey

README.md

@@ -71,6 +71,7 @@ PaddleDetection的目的是为工业界和学术界提供丰富、易用的目
 - [行人检测和车辆检测预训练模型](contrib/README_cn.md) 针对不同场景的检测模型
 - [YOLOv3增强模型](docs/YOLOv3_ENHANCEMENT.md) 改进原始YOLOv3，精度达到41.4%，原论文精度为33.0%，同时预测速度也得到提升
 - [Objects365 2019 Challenge夺冠模型](docs/CACascadeRCNN.md) Objects365 Full Track任务中最好的单模型之一,精度达到31.7%
+- [Open Images V5和Objects365数据集模型](docs/OIDV5_BASELINE_MODEL.md)
 
 
 ## 模型压缩
@@ -90,8 +91,13 @@ PaddleDetection的目的是为工业界和学术界提供丰富、易用的目
 
 ## 版本更新
 
-### 10/2019
+### 21/11/2019
+- 增加CascadeClsAware RCNN模型。
+- 增加CBNet，ResNet200和Non-local模型。
+- 增加SoftNMS。
+- 增加Open Image V5数据集和Objects365数据集模型。
 
+### 10/2019
 - 增加增强版YOLOv3模型，精度高达41.4%。
 - 增加人脸检测模型BlazeFace、Faceboxes。
 - 丰富基于COCO的模型，精度高达51.9%。

README_en.md

@@ -80,6 +80,7 @@ Advanced Features:
 - [Pretrained models for pedestrian  and vehicle detection](contrib/README.md) Models for object detection in specific scenarios. 
 - [YOLOv3 enhanced model](docs/YOLOv3_ENHANCEMENT.md) Compared to MAP of 33.0% in paper, enhanced YOLOv3 reaches the MAP of 41.4% and inference speed is improved as well
 - [Objects365 2019 Challenge champion model](docs/CACascadeRCNN.md) One of the best single models in Objects365 Full Track of which MAP reaches 31.7%.
+- [Open Images Dataset V5 and Objects365 Dataset models](docs/OIDV5_BASELINE_MODEL.md)
 
 ## Model compression
 
@@ -98,6 +99,12 @@ Advanced Features:
 
 ## Updates
 
+#### 21/11/2019
+- Add CascadeClsAware RCNN model.
+- Add CBNet, ResNet200 and Non-local model.
+- Add SoftNMS.
+- Add models of Open Images Dataset V5 and Objects365 Dataset.
+
 #### 10/2019
 
 - Add enhanced YOLOv3 models, box mAP up to 41.4%.

configs/obj365/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms.yml

@@ -0,0 +1,190 @@
+architecture: CascadeRCNNClsAware
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 800000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar
+weights: output/cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms/model_final
+# obj365 dataset format and its eval method are same as those for coco
+metric: COCO
+num_classes: 366
+
+CascadeRCNNClsAware:
+  backbone: ResNet
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: CascadeBBoxHead
+  bbox_assigner: CascadeBBoxAssigner
+
+ResNet:
+  norm_type: bn
+  depth: 200
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  variant: d
+  dcn_v2_stages: [3, 4, 5]
+  nonlocal_stages: [4]
+
+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: 14
+  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
+  class_aware: True
+
+CascadeBBoxHead:
+  head: CascadeTwoFCHead
+  nms: MultiClassSoftNMS
+
+CascadeTwoFCHead:
+  mlp_dim: 1024
+
+MultiClassSoftNMS:
+  score_threshold: 0.001
+  keep_top_k: 300
+  softnms_sigma: 0.15
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [520000, 740000]
+  - !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/obj365
+    annotation: train.json
+    image_dir: train
+  sample_transforms: 
+  - !DecodeImage
+    to_rgb: True
+    with_mixup: False
+  - !RandomFlipImage
+    prob: 0.5
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: True
+    mean:
+    - 0.485
+    - 0.456
+    - 0.406
+    std:
+    - 0.229
+    - 0.224
+    - 0.225 
+  - !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: 1800
+    use_cv2: true
+  - !Permute
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  drop_last: false
+  num_workers: 2
+
+FasterRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/obj365
+    annotation: val.json
+    image_dir: val
+  sample_transforms: 
+  - !DecodeImage
+    to_rgb: True
+    with_mixup: False
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: True
+    mean:
+    - 0.485
+    - 0.456
+    - 0.406
+    std:
+    - 0.229
+    - 0.224
+    - 0.225 
+  - !ResizeImage
+    interp: 1
+    target_size:
+    - 1200
+    max_size: 2000
+    use_cv2: true
+  - !Permute
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+
+FasterRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: dataset/obj365/val.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  drop_last: false
+  num_workers: 2