diff --git a/configs/cascade_rcnn_r50_fpn_1x.yml b/configs/cascade_rcnn_r50_fpn_1x.yml
index 3e257d043cd8279cbe57a740d42e0978504d2104..81f5eb09a6dd7b1a7880a04a2dac87a6264718be 100644
--- a/configs/cascade_rcnn_r50_fpn_1x.yml
+++ b/configs/cascade_rcnn_r50_fpn_1x.yml
@@ -10,6 +10,7 @@ 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
@@ -74,7 +75,6 @@ CascadeBBoxAssigner:
   bg_thresh_hi: [0.5, 0.6, 0.7]
   fg_thresh: [0.5, 0.6, 0.7]
   fg_fraction: 0.25
-  num_classes: 81
 
 CascadeBBoxHead:
   head: FC6FC7Head
@@ -82,7 +82,6 @@ CascadeBBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 FC6FC7Head:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r101_1x.yml b/configs/faster_rcnn_r101_1x.yml
index b04a9fc42eb5328eea0292c222d0e724f9a35146..27773309ac3e6ffa3abef7018f675ac00d62148c 100644
--- a/configs/faster_rcnn_r101_1x.yml
+++ b/configs/faster_rcnn_r101_1x.yml
@@ -10,6 +10,7 @@ snapshot_iter: 10000
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
 metric: COCO
 weights: output/faster_rcnn_r101_1x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -64,7 +65,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: ResNetC5
@@ -72,7 +72,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 LearningRate:
   base_lr: 0.01
diff --git a/configs/faster_rcnn_r101_fpn_1x.yml b/configs/faster_rcnn_r101_fpn_1x.yml
index c9536b46cb93c0016c2c285f9452bb45e75e013b..dbb4d6d9aa9019e111a32a5ba89642fd0b73a547 100644
--- a/configs/faster_rcnn_r101_fpn_1x.yml
+++ b/configs/faster_rcnn_r101_fpn_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
 weights: output/faster_rcnn_r101_fpn_1x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -73,7 +74,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -81,7 +81,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r101_fpn_2x.yml b/configs/faster_rcnn_r101_fpn_2x.yml
index 995c8e936379c760cfa263d88cb286c41f14fee2..a742782bcf7e0fac62ac9d2179bd46806ed97d3e 100644
--- a/configs/faster_rcnn_r101_fpn_2x.yml
+++ b/configs/faster_rcnn_r101_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
 weights: output/faster_rcnn_r101_fpn_2x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -73,7 +74,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -81,7 +81,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r101_vd_fpn_1x.yml b/configs/faster_rcnn_r101_vd_fpn_1x.yml
index 033104194b0e6f52b249e7b3dba175d7bb57cc3c..7c0fc39be9a8c1bdc295cdf8a7dc6de246e9f186 100644
--- a/configs/faster_rcnn_r101_vd_fpn_1x.yml
+++ b/configs/faster_rcnn_r101_vd_fpn_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
 weights: output/faster_rcnn_r101_vd_fpn_1x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -74,7 +75,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -82,7 +82,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r101_vd_fpn_2x.yml b/configs/faster_rcnn_r101_vd_fpn_2x.yml
index 722fcf887c1b722140914ad922c179125cbc9952..726de38a9c2049c69f2c1427e2e1ab757164b805 100644
--- a/configs/faster_rcnn_r101_vd_fpn_2x.yml
+++ b/configs/faster_rcnn_r101_vd_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
 weights: output/faster_rcnn_r101_vd_fpn_2x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -74,7 +75,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -82,7 +82,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r50_1x.yml b/configs/faster_rcnn_r50_1x.yml
index 9ec90c674d1a5608cef205aac0e2820db6a625ca..bf4a828fb0a9b8385924e05e3a1c9252ed0412c1 100644
--- a/configs/faster_rcnn_r50_1x.yml
+++ b/configs/faster_rcnn_r50_1x.yml
@@ -10,6 +10,7 @@ snapshot_iter: 10000
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/faster_rcnn_r50_1x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -64,7 +65,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: ResNetC5
@@ -72,7 +72,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 LearningRate:
   base_lr: 0.01
diff --git a/configs/faster_rcnn_r50_2x.yml b/configs/faster_rcnn_r50_2x.yml
index c28bcc25f9781cb84f03eeb782011bbb7518bb47..5257161aae01e6ff2a728f2929d13dc25d5027bb 100644
--- a/configs/faster_rcnn_r50_2x.yml
+++ b/configs/faster_rcnn_r50_2x.yml
@@ -10,6 +10,7 @@ snapshot_iter: 10000
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/faster_rcnn_r50_2x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -64,7 +65,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: ResNetC5
@@ -72,7 +72,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 LearningRate:
   base_lr: 0.01
diff --git a/configs/faster_rcnn_r50_fpn_1x.yml b/configs/faster_rcnn_r50_fpn_1x.yml
index b06ec6ffe6474a6d8860b1c3c665e11f66349d4b..d41e9e737252bc52db806010e023be754b31b613 100644
--- a/configs/faster_rcnn_r50_fpn_1x.yml
+++ b/configs/faster_rcnn_r50_fpn_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/fpn/faster_rcnn_r50_fpn_1x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -74,7 +75,6 @@ BBoxAssigner:
   bg_thresh_hi: 0.5
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -82,7 +82,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r50_fpn_2x.yml b/configs/faster_rcnn_r50_fpn_2x.yml
index b5cf9931ddb13fedd4d77380ccc06f430e2307d6..a1989db64b17967ba00d3f286c0209c27eb90013 100644
--- a/configs/faster_rcnn_r50_fpn_2x.yml
+++ b/configs/faster_rcnn_r50_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/faster_rcnn_r50_fpn_2x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -74,7 +75,6 @@ BBoxAssigner:
   bg_thresh_hi: 0.5
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -82,7 +82,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_r50_vd_1x.yml b/configs/faster_rcnn_r50_vd_1x.yml
index 5941a03777f480e203e0e046da7aa4255d06da7b..25ce550e408c7d935fd5e7f5e75a47fbbfbc2dc1 100644
--- a/configs/faster_rcnn_r50_vd_1x.yml
+++ b/configs/faster_rcnn_r50_vd_1x.yml
@@ -10,6 +10,7 @@ snapshot_iter: 10000
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
 metric: COCO
 weights: output/faster_rcnn_r50_vd_1x/model_final
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -66,7 +67,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: ResNetC5
@@ -74,7 +74,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 LearningRate:
   base_lr: 0.01
diff --git a/configs/faster_rcnn_r50_vd_fpn_2x.yml b/configs/faster_rcnn_r50_vd_fpn_2x.yml
index 3d92f6f8308c5e4e129e47c1db23345351e0198b..ef19b275fdbd491a3b18e60580cda4fb709714ea 100644
--- a/configs/faster_rcnn_r50_vd_fpn_2x.yml
+++ b/configs/faster_rcnn_r50_vd_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
 weights: output/faster_rcnn_r50_vd_fpn_2x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNet
@@ -74,7 +75,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -82,7 +82,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_se154_vd_fpn_s1x.yml b/configs/faster_rcnn_se154_vd_fpn_s1x.yml
index 26dc789bd801e75ade532f589ff340c1ead0a5c5..3e16ecc25699d199765955d2cf610cc392185c26 100644
--- a/configs/faster_rcnn_se154_vd_fpn_s1x.yml
+++ b/configs/faster_rcnn_se154_vd_fpn_s1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
 weights: output/faster_rcnn_se154_vd_fpn_s1x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: SENet
@@ -76,7 +77,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -84,7 +84,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml b/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
index 60c243b2d34df943ee4a3f777884b7ae256e469a..435f937ea4827023552c0c7ed253d14902c93498 100644
--- a/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
+++ b/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
 weights: output/faster_rcnn_x101_vd_64x4d_fpn_1x/model_final
 metric: COCO
+num_classes: 81
 
 FasterRCNN:
   backbone: ResNeXt
@@ -76,7 +77,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 BBoxHead:
   head: TwoFCHead
@@ -84,7 +84,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/mask_rcnn_r101_fpn_1x.yml b/configs/mask_rcnn_r101_fpn_1x.yml
index d7b9aa0ce6b77d5512a59c5b72c9394cb3d06bb8..d9a476b9eadaa5d9d39ea5e210497d36b2b94be1 100644
--- a/configs/mask_rcnn_r101_fpn_1x.yml
+++ b/configs/mask_rcnn_r101_fpn_1x.yml
@@ -10,6 +10,7 @@ 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
@@ -68,7 +69,6 @@ FPNRoIAlign:
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   num_convs: 4
   resolution: 28
 
@@ -79,7 +79,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
   resolution: 28
@@ -90,7 +89,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/mask_rcnn_r50_1x.yml b/configs/mask_rcnn_r50_1x.yml
index 571be5fef110f857719a8630c341d1a81f4c00e4..b652affbea5d9ae1b69a0bf9bcd9d09d4be095fb 100644
--- a/configs/mask_rcnn_r50_1x.yml
+++ b/configs/mask_rcnn_r50_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/mask_rcnn_r50_1x/model_final
+num_classes: 81
 
 MaskRCNN:
   backbone: ResNet
@@ -66,12 +67,10 @@ BBoxHead:
     nms_threshold: 0.5
     normalized: false
     score_threshold: 0.05
-  num_classes: 81
 
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   resolution: 14
 
 BBoxAssigner:
@@ -81,10 +80,8 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
-  num_classes: 81
   resolution: 14
 
 LearningRate:
diff --git a/configs/mask_rcnn_r50_2x.yml b/configs/mask_rcnn_r50_2x.yml
index 2c3b59b220f1e4aeaeee04c879c09fec8576e0f5..58f9b39f48399aa540466f121baa1e3edfc59097 100644
--- a/configs/mask_rcnn_r50_2x.yml
+++ b/configs/mask_rcnn_r50_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/mask_rcnn_r50_2x/model_final/
+num_classes: 81
 
 MaskRCNN:
   backbone: ResNet
@@ -67,12 +68,10 @@ BBoxHead:
     nms_threshold: 0.5
     normalized: false
     score_threshold: 0.05
-  num_classes: 81
 
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   resolution: 14
 
 BBoxAssigner:
@@ -82,10 +81,8 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
-  num_classes: 81
   resolution: 14
 
 LearningRate:
diff --git a/configs/mask_rcnn_r50_fpn_1x.yml b/configs/mask_rcnn_r50_fpn_1x.yml
index fd378e5a52967c0b598d24b77af08661e21d1c09..1059d7b4e907ac2ae3659b85937205c1f61d5f96 100644
--- a/configs/mask_rcnn_r50_fpn_1x.yml
+++ b/configs/mask_rcnn_r50_fpn_1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 metric: COCO
 weights: output/mask_rcnn_r50_fpn_1x/model_final/
+num_classes: 81
 
 MaskRCNN:
   backbone: ResNet
@@ -68,7 +69,6 @@ FPNRoIAlign:
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   num_convs: 4
   resolution: 28
 
@@ -79,7 +79,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
   resolution: 28
@@ -90,7 +89,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/mask_rcnn_r50_fpn_2x.yml b/configs/mask_rcnn_r50_fpn_2x.yml
index 59ad857bfa734c5ee983efa9f340c69e3c2aaeb1..9f7604982d38cd66eb34299dfc2ae8e043583de1 100644
--- a/configs/mask_rcnn_r50_fpn_2x.yml
+++ b/configs/mask_rcnn_r50_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
 weights: output/mask_rcnn_r50_fpn_2x/model_final/
 metric: COCO
+num_classes: 81
 
 MaskRCNN:
   backbone: ResNet
@@ -68,7 +69,6 @@ FPNRoIAlign:
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   num_convs: 4
   resolution: 28
 
@@ -79,7 +79,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
   resolution: 28
@@ -90,7 +89,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
@@ -116,7 +114,7 @@ OptimizerBuilder:
 MaskRCNNTrainFeed:
   batch_size: 1
   dataset:
-    dataset_dir: dataset/coco 
+    dataset_dir: dataset/coco
     annotation: annotations/instances_train2017.json
     image_dir: train2017
   batch_transforms:
@@ -127,7 +125,7 @@ MaskRCNNTrainFeed:
 MaskRCNNEvalFeed:
   batch_size: 1
   dataset:
-    dataset_dir: dataset/coco 
+    dataset_dir: dataset/coco
     annotation: annotations/instances_val2017.json
     image_dir: val2017
   batch_transforms:
diff --git a/configs/mask_rcnn_r50_vd_fpn_2x.yml b/configs/mask_rcnn_r50_vd_fpn_2x.yml
index bee5710b1f8e43d7fade2f5f0c4b07148160a889..957c53d6ded13574c4e5093e14430831b4a94794 100644
--- a/configs/mask_rcnn_r50_vd_fpn_2x.yml
+++ b/configs/mask_rcnn_r50_vd_fpn_2x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
 metric: COCO
 weights: output/mask_rcnn_r50_vd_fpn_2x/model_final/
+num_classes: 81
 
 MaskRCNN:
   backbone: ResNet
@@ -69,7 +70,6 @@ FPNRoIAlign:
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   num_convs: 4
   resolution: 28
 
@@ -80,7 +80,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
   resolution: 28
@@ -91,7 +90,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
diff --git a/configs/mask_rcnn_se154_vd_fpn_s1x.yml b/configs/mask_rcnn_se154_vd_fpn_s1x.yml
index 3346bdb1d228f7de41351133e0a738d1de95a595..76bed15ee2dc8a130e6a0a8b59461132876c6cbb 100644
--- a/configs/mask_rcnn_se154_vd_fpn_s1x.yml
+++ b/configs/mask_rcnn_se154_vd_fpn_s1x.yml
@@ -10,6 +10,7 @@ save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
 weights: output/mask_rcnn_se154_vd_fpn_s1x/model_final/
 metric: COCO
+num_classes: 81
 
 MaskRCNN:
   backbone: SENet
@@ -71,7 +72,6 @@ FPNRoIAlign:
 MaskHead:
   dilation: 1
   num_chan_reduced: 256
-  num_classes: 81
   num_convs: 4
   resolution: 28
 
@@ -82,7 +82,6 @@ BBoxAssigner:
   bg_thresh_lo: 0.0
   fg_fraction: 0.25
   fg_thresh: 0.5
-  num_classes: 81
 
 MaskAssigner:
   resolution: 28
@@ -93,7 +92,6 @@ BBoxHead:
     keep_top_k: 100
     nms_threshold: 0.5
     score_threshold: 0.05
-  num_classes: 81
 
 TwoFCHead:
   num_chan: 1024
@@ -120,7 +118,7 @@ MaskRCNNTrainFeed:
   # batch size per device
   batch_size: 1
   dataset:
-    dataset_dir: dataset/coco 
+    dataset_dir: dataset/coco
     image_dir: train2017
     annotation: annotations/instances_train2017.json
   batch_transforms:
diff --git a/docs/CONFIG.md b/docs/CONFIG.md
index 10376e055a1c6333630dcaab09cfa23d638a2285..1655e02d4e4a07ded6f7ff9a736e679c33490e64 100644
--- a/docs/CONFIG.md
+++ b/docs/CONFIG.md
@@ -188,3 +188,14 @@ A small utility (`tools/configure.py`) is included to simplify the configuration
     ```shell
     python tools/configure.py --minimal generate FasterRCNN BBoxHead
     ```
+
+
+# FAQ
+
+**Q:** There are some configuration options that are used by multiple modules (e.g., `num_classes`), how do I avoid duplication in config files?
+
+**A:** We provided a `__shared__` annotation for exactly this purpose, simply annotate like this `__shared__ = ['num_classes']`. It works as follows:
+
+1.  if `num_classes` is configured for a module in config file, it takes precedence.
+2.  if `num_classes` is not configured for a module but is present in the config file as a global key, its value will be used.
+3.  otherwise, the default value (`81`) will be used.
diff --git a/docs/CONFIG_cn.md b/docs/CONFIG_cn.md
index f27b7bdcc7e6f3d791352519ed56a9b97050b112..9008c3117e0af5d8cd8e5a78a206cee28a9cad24 100644
--- a/docs/CONFIG_cn.md
+++ b/docs/CONFIG_cn.md
@@ -180,3 +180,14 @@ pip install typeguard http://github.com/willthefrog/docstring_parser/tarball/mas
     ```shell
     python tools/configure.py --minimal generate FasterRCNN BBoxHead
     ```
+
+
+# FAQ
+
+**Q:** 某些配置项会在多个模块中用到(如 `num_classes`)，如何避免在配置文件中多次重复设置？
+
+**A:** 框架提供了 `__shared__` 标记来实现配置的共享，用户可以标记参数，如 `__shared__ = ['num_classes']` ，配置数值作用规则如下：
+
+1.  如果模块配置中提供了 `num_classes` ，会优先使用其数值。
+2.  如果模块配置中未提供 `num_classes` ，但配置文件中存在全局键值，那么会使用全局键值。
+3.  两者均为配置的情况下，将使用默认值(`81`)。
diff --git a/ppdet/core/config/schema.py b/ppdet/core/config/schema.py
index 5a73db4dc3ee43eb83746cdecdeec162bfea71f2..efba5be1dfd93243ff7a071f0f30accfa513e18f 100644
--- a/ppdet/core/config/schema.py
+++ b/ppdet/core/config/schema.py
@@ -43,13 +43,14 @@ except Exception:
         if not check_type.__warning_sent__:
             from ppdet.utils.cli import ColorTTY
             color_tty = ColorTTY()
-            message = "typeguard is not installed, type checking is not available"
+            message = "typeguard is not installed," \
+                + "type checking is not available"
             print(color_tty.yellow(message))
             check_type.__warning_sent__ = True
 
     check_type.__warning_sent__ = False
 
-__all__ = ['SchemaValue', 'SchemaDict', 'extract_schema']
+__all__ = ['SchemaValue', 'SchemaDict', 'SharedConfig', 'extract_schema']
 
 
 class SchemaValue(object):
@@ -160,6 +161,27 @@ class SchemaDict(dict):
                 self.name, ", ".join(mismatch_keys)))
 
 
+class SharedConfig(object):
+    """
+    Representation class for `__shared__` annotations, which work as follows:
+
+    - if `key` is set for the module in config file, its value will take
+      precedence
+    - if `key` is not set for the module but present in the config file, its
+      value will be used
+    - otherwise, use the provided `default_value` as fallback
+
+    Args:
+        key: config[key] will be injected
+        default_value: fallback value
+    """
+
+    def __init__(self, key, default_value=None):
+        super(SharedConfig, self).__init__()
+        self.key = key
+        self.default_value = default_value
+
+
 def extract_schema(cls):
     """
     Extract schema from a given class
@@ -216,6 +238,7 @@ def extract_schema(cls):
     schema.strict = not has_kwargs
     schema.pymodule = importlib.import_module(cls.__module__)
     schema.inject = getattr(cls, '__inject__', [])
+    schema.shared = getattr(cls, '__shared__', [])
     for idx, name in enumerate(names):
         comment = name in comments and comments[name] or name
         if name in schema.inject:
@@ -223,8 +246,13 @@ def extract_schema(cls):
         else:
             type_ = name in annotations and annotations[name] or None
         value_schema = SchemaValue(name, comment, type_)
-        if idx >= num_required:
-            value_schema.set_default(defaults[idx - num_required])
+        if name in schema.shared:
+            assert idx >= num_required, "shared config must have default value"
+            default = defaults[idx - num_required]
+            value_schema.set_default(SharedConfig(name, default))
+        elif idx >= num_required:
+            default = defaults[idx - num_required]
+            value_schema.set_default(default)
         schema.set_schema(name, value_schema)
 
     return schema
diff --git a/ppdet/core/config/yaml_helpers.py b/ppdet/core/config/yaml_helpers.py
index 099a13e55d4c2982709e6dd4ba6d9939e7fa02ec..8a7738b47f4f86acde78ab8a3bcac590d61615fa 100644
--- a/ppdet/core/config/yaml_helpers.py
+++ b/ppdet/core/config/yaml_helpers.py
@@ -16,6 +16,7 @@ import importlib
 import inspect
 
 import yaml
+from .schema import SharedConfig
 
 __all__ = ['serializable', 'Callable']
 
@@ -59,7 +60,8 @@ def _make_python_representer(cls):
 
 def serializable(cls):
     """
-    Add loader and dumper for given class, which must be "trivially serializable"
+    Add loader and dumper for given class, which must be
+    "trivially serializable"
 
     Args:
         cls: class to be serialized
@@ -72,6 +74,10 @@ def serializable(cls):
     return cls
 
 
+yaml.add_representer(SharedConfig,
+                     lambda d, o: d.represent_data(o.default_value))
+
+
 @serializable
 class Callable(object):
     """
diff --git a/ppdet/core/workspace.py b/ppdet/core/workspace.py
index 375da3e33f88e4d0159d581bf010f3e308b5228c..c922b3b3cde39e3908c41446b2e5c9f4b231762d 100644
--- a/ppdet/core/workspace.py
+++ b/ppdet/core/workspace.py
@@ -23,7 +23,7 @@ import sys
 import yaml
 import copy
 
-from .config.schema import SchemaDict, extract_schema
+from .config.schema import SchemaDict, SharedConfig, extract_schema
 from .config.yaml_helpers import serializable
 
 __all__ = [
@@ -136,7 +136,8 @@ def create(cls_or_name, **kwargs):
     assert type(cls_or_name) in [type, str
                                  ], "should be a class or name of a class"
     name = type(cls_or_name) == str and cls_or_name or cls_or_name.__name__
-    assert name in global_config and isinstance(global_config[name], SchemaDict), \
+    assert name in global_config and \
+        isinstance(global_config[name], SchemaDict), \
         "the module {} is not registered".format(name)
     config = global_config[name]
     config.update(kwargs)
@@ -145,9 +146,26 @@ def create(cls_or_name, **kwargs):
 
     kwargs = {}
     kwargs.update(global_config[name])
+
+    # parse `shared` annoation of registered modules
+    if getattr(config, 'shared', None):
+        for k in config.shared:
+            target_key = config[k]
+            shared_conf = config.schema[k].default
+            assert isinstance(shared_conf, SharedConfig)
+            if target_key is not None and not isinstance(
+                    target_key, SharedConfig):
+                continue   # value is given for the module
+            elif shared_conf.key in global_config:
+                # `key` is present in config
+                kwargs[k] = global_config[shared_conf.key]
+            else:
+                kwargs[k] = shared_conf.default_value
+
+    # parse `inject` annoation of registered modules
     if getattr(config, 'inject', None):
         for k in config.inject:
-            target_key = global_config[name][k]
+            target_key = config[k]
             # optional dependency
             if target_key is None:
                 continue
diff --git a/ppdet/data/data_feed.py b/ppdet/data/data_feed.py
index b4a89803f05db51c9594b71a943740532d85517f..b3c7222cae5a3d819b72a5d11438787f97c33ba6 100644
--- a/ppdet/data/data_feed.py
+++ b/ppdet/data/data_feed.py
@@ -181,7 +181,6 @@ class DataSet(object):
     Args:
         annotation (str): annotation file path
         image_dir (str): directory where image files are stored
-        num_classes (int): number of classes
         shuffle (bool): shuffle samples
     """
     __source__ = 'RoiDbSource'
diff --git a/ppdet/modeling/anchor_heads/retina_head.py b/ppdet/modeling/anchor_heads/retina_head.py
index 918efc8e220b9a58a8ce3db975500182340a2953..41246e8b6267881f62386653841ecfb525a254e1 100644
--- a/ppdet/modeling/anchor_heads/retina_head.py
+++ b/ppdet/modeling/anchor_heads/retina_head.py
@@ -25,7 +25,7 @@ from paddle.fluid.regularizer import L2Decay
 from ppdet.modeling.ops import (AnchorGenerator, RetinaTargetAssign,
                                 RetinaOutputDecoder)
 
-from ppdet.core.workspace import register, serializable
+from ppdet.core.workspace import register
 
 __all__ = ['RetinaHead']
 
@@ -52,6 +52,7 @@ class RetinaHead(object):
         sigma (float): The parameter in smooth l1 loss
     """
     __inject__ = ['anchor_generator', 'target_assign', 'output_decoder']
+    __shared__ = ['num_classes']
 
     def __init__(self,
                  anchor_generator=AnchorGenerator().__dict__,
@@ -333,7 +334,6 @@ class RetinaHead(object):
         cls_pred_reshape_list = output['cls_pred']
         bbox_pred_reshape_list = output['bbox_pred']
         anchor_reshape_list = output['anchor']
-        anchor_var_reshape_list = output['anchor_var']
         for i in range(self.max_level - self.min_level + 1):
             cls_pred_reshape_list[i] = fluid.layers.sigmoid(
                 cls_pred_reshape_list[i])
diff --git a/ppdet/modeling/ops.py b/ppdet/modeling/ops.py
index ae804134c5faebac92b21b7a28dea6369877d772..a6a08728d569df06395021e12ba2a85859ba6eeb 100644
--- a/ppdet/modeling/ops.py
+++ b/ppdet/modeling/ops.py
@@ -88,6 +88,7 @@ class GenerateProposals(object):
 class MaskAssigner(object):
     __op__ = fluid.layers.generate_mask_labels
     __append_doc__ = True
+    __shared__ = ['num_classes']
 
     def __init__(self, num_classes=81, resolution=14):
         super(MaskAssigner, self).__init__()
@@ -123,6 +124,7 @@ class MultiClassNMS(object):
 class BBoxAssigner(object):
     __op__ = fluid.layers.generate_proposal_labels
     __append_doc__ = True
+    __shared__ = ['num_classes']
 
     def __init__(self,
                  batch_size_per_im=512,
diff --git a/ppdet/modeling/roi_heads/bbox_head.py b/ppdet/modeling/roi_heads/bbox_head.py
index a5344cf4a550564e263f644d2a334cf22d4d1461..21f79459d4b931021b89266c00082510c6b3641d 100644
--- a/ppdet/modeling/roi_heads/bbox_head.py
+++ b/ppdet/modeling/roi_heads/bbox_head.py
@@ -92,12 +92,13 @@ class BBoxHead(object):
     RCNN bbox head
 
     Args:
-        head (object): the head module instance, e.g., `ResNetC5` or `TwoFCHead`
+        head (object): the head module instance, e.g., `ResNetC5`, `TwoFCHead`
         box_coder (object): `BoxCoder` instance
         nms (object): `MultiClassNMS` instance
         num_classes: number of output classes
     """
     __inject__ = ['head', 'box_coder', 'nms']
+    __shared__ = ['num_classes']
 
     def __init__(self,
                  head,
diff --git a/ppdet/modeling/roi_heads/cascade_head.py b/ppdet/modeling/roi_heads/cascade_head.py
index 8971b4e0376be0cbc5a5443e58fb202d09616d57..aad4b141d6043ff0ca4dc66eaac5c58fd4986053 100644
--- a/ppdet/modeling/roi_heads/cascade_head.py
+++ b/ppdet/modeling/roi_heads/cascade_head.py
@@ -37,6 +37,7 @@ class CascadeBBoxHead(object):
         num_classes: number of output classes
     """
     __inject__ = ['head', 'nms']
+    __shared__ = ['num_classes']
 
     def __init__(self, head, nms=MultiClassNMS().__dict__, num_classes=81):
         super(CascadeBBoxHead, self).__init__()
diff --git a/ppdet/modeling/roi_heads/mask_head.py b/ppdet/modeling/roi_heads/mask_head.py
index 1d2b027de0f0e8a280e10fe5c7500a5b2da650d3..ad59de00e346be98ff99aec12abb504cfa304795 100644
--- a/ppdet/modeling/roi_heads/mask_head.py
+++ b/ppdet/modeling/roi_heads/mask_head.py
@@ -38,6 +38,8 @@ class MaskHead(object):
         num_classes (int): number of output classes
     """
 
+    __shared__ = ['num_classes']
+
     def __init__(self,
                  num_convs=0,
                  num_chan_reduced=256,
diff --git a/ppdet/modeling/target_assigners.py b/ppdet/modeling/target_assigners.py
index ccdb2672e872689bac53e2791dc3c9760880352e..03755762df22c9707c0a15202561ed4cb145a0f4 100644
--- a/ppdet/modeling/target_assigners.py
+++ b/ppdet/modeling/target_assigners.py
@@ -26,6 +26,8 @@ __all__ = ['BBoxAssigner', 'MaskAssigner', 'CascadeBBoxAssigner']
 
 @register
 class CascadeBBoxAssigner(object):
+    __shared__ = ['num_classes']
+
     def __init__(self,
                  batch_size_per_im=512,
                  fg_fraction=.25,