diff --git a/PaddleCV/PaddleDetection/configs/cascade_rcnn_r50_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/cascade_rcnn_r50_fpn_1x.yml
index 3e257d043cd8279cbe57a740d42e0978504d2104..81f5eb09a6dd7b1a7880a04a2dac87a6264718be 100644
--- a/PaddleCV/PaddleDetection/configs/cascade_rcnn_r50_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_1x.yml
index b04a9fc42eb5328eea0292c222d0e724f9a35146..27773309ac3e6ffa3abef7018f675ac00d62148c 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_1x.yml
index c9536b46cb93c0016c2c285f9452bb45e75e013b..dbb4d6d9aa9019e111a32a5ba89642fd0b73a547 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_2x.yml
index 995c8e936379c760cfa263d88cb286c41f14fee2..a742782bcf7e0fac62ac9d2179bd46806ed97d3e 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_fpn_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_1x.yml
index 033104194b0e6f52b249e7b3dba175d7bb57cc3c..7c0fc39be9a8c1bdc295cdf8a7dc6de246e9f186 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_2x.yml
index 722fcf887c1b722140914ad922c179125cbc9952..726de38a9c2049c69f2c1427e2e1ab757164b805 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r101_vd_fpn_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_1x.yml
index 9ec90c674d1a5608cef205aac0e2820db6a625ca..bf4a828fb0a9b8385924e05e3a1c9252ed0412c1 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_2x.yml
index c28bcc25f9781cb84f03eeb782011bbb7518bb47..5257161aae01e6ff2a728f2929d13dc25d5027bb 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_1x.yml
index b06ec6ffe6474a6d8860b1c3c665e11f66349d4b..0414a2ec8412b2e344922e2a704d570ae58cc88e 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_1x.yml
@@ -9,7 +9,8 @@ log_smooth_window: 20
 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
+weights: output/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_2x.yml
index b5cf9931ddb13fedd4d77380ccc06f430e2307d6..a1989db64b17967ba00d3f286c0209c27eb90013 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_fpn_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_1x.yml
index 5941a03777f480e203e0e046da7aa4255d06da7b..25ce550e408c7d935fd5e7f5e75a47fbbfbc2dc1 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_fpn_2x.yml
index 3d92f6f8308c5e4e129e47c1db23345351e0198b..ef19b275fdbd491a3b18e60580cda4fb709714ea 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_r50_vd_fpn_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_se154_vd_fpn_s1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_se154_vd_fpn_s1x.yml
index 26dc789bd801e75ade532f589ff340c1ead0a5c5..3e16ecc25699d199765955d2cf610cc392185c26 100644
--- a/PaddleCV/PaddleDetection/configs/faster_rcnn_se154_vd_fpn_s1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
new file mode 100644
index 0000000000000000000000000000000000000000..1d6759e6f95ea201ca046cc85986ef41eccf8a8e
--- /dev/null
+++ b/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
@@ -0,0 +1,142 @@
+architecture: FasterRCNN
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 180000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+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
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: BBoxHead
+  bbox_assigner: BBoxAssigner
+
+ResNeXt:
+  depth: 101
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  group_width: 4
+  groups: 64
+  norm_type: affine_channel
+  variant: d
+
+FPN:
+  max_level: 6
+  min_level: 2
+  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
+  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
+    post_nms_top_n: 2000
+    pre_nms_top_n: 2000
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    post_nms_top_n: 1000
+    pre_nms_top_n: 1000
+
+FPNRoIAlign:
+  canconical_level: 4
+  canonical_size: 224
+  max_level: 5
+  min_level: 2
+  box_resolution: 7
+  sampling_ratio: 2
+
+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
+
+BBoxHead:
+  head: TwoFCHead
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+TwoFCHead:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [120000, 160000]
+    values: null
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+FasterRCNNTrainFeed:
+  # batch size per device
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    image_dir: train2017
+    annotation: annotations/instances_train2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+  shuffle: true
+
+FasterRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+
+FasterRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: annotations/instances_val2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+  shuffle: false
diff --git a/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml
new file mode 100644
index 0000000000000000000000000000000000000000..df48a706a1c0708177cc183800aceb8bdd386362
--- /dev/null
+++ b/PaddleCV/PaddleDetection/configs/faster_rcnn_x101_vd_64x4d_fpn_2x.yml
@@ -0,0 +1,142 @@
+architecture: FasterRCNN
+train_feed: FasterRCNNTrainFeed
+eval_feed: FasterRCNNEvalFeed
+test_feed: FasterRCNNTestFeed
+max_iters: 360000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+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
+
+FasterRCNN:
+  backbone: ResNeXt
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: BBoxHead
+  bbox_assigner: BBoxAssigner
+
+ResNeXt:
+  depth: 101
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+  group_width: 4
+  groups: 64
+  norm_type: affine_channel
+  variant: d
+
+FPN:
+  max_level: 6
+  min_level: 2
+  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
+  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
+    post_nms_top_n: 2000
+    pre_nms_top_n: 2000
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    post_nms_top_n: 1000
+    pre_nms_top_n: 1000
+
+FPNRoIAlign:
+  canconical_level: 4
+  canonical_size: 224
+  max_level: 5
+  min_level: 2
+  box_resolution: 7
+  sampling_ratio: 2
+
+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
+  num_classes: 81
+
+BBoxHead:
+  head: TwoFCHead
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+  num_classes: 81
+
+TwoFCHead:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [240000, 320000]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+FasterRCNNTrainFeed:
+  # batch size per device
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    image_dir: train2017
+    annotation: annotations/instances_train2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+  shuffle: true
+
+FasterRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+
+FasterRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: annotations/instances_val2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+  shuffle: false
diff --git a/PaddleCV/PaddleDetection/configs/mask_rcnn_r101_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r101_fpn_1x.yml
index d7b9aa0ce6b77d5512a59c5b72c9394cb3d06bb8..d9a476b9eadaa5d9d39ea5e210497d36b2b94be1 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_r101_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_1x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_1x.yml
index 571be5fef110f857719a8630c341d1a81f4c00e4..b652affbea5d9ae1b69a0bf9bcd9d09d4be095fb 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_2x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_2x.yml
index 2c3b59b220f1e4aeaeee04c879c09fec8576e0f5..58f9b39f48399aa540466f121baa1e3edfc59097 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_1x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_1x.yml
index fd378e5a52967c0b598d24b77af08661e21d1c09..1059d7b4e907ac2ae3659b85937205c1f61d5f96 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_2x.yml
new file mode 100644
index 0000000000000000000000000000000000000000..9f7604982d38cd66eb34299dfc2ae8e043583de1
--- /dev/null
+++ b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_fpn_2x.yml
@@ -0,0 +1,143 @@
+architecture: MaskRCNN
+train_feed: MaskRCNNTrainFeed
+eval_feed: MaskRCNNEvalFeed
+test_feed: MaskRCNNTestFeed
+max_iters: 360000
+snapshot_iter: 10000
+use_gpu: true
+log_smooth_window: 20
+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
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: BBoxHead
+  bbox_assigner: BBoxAssigner
+
+ResNet:
+  depth: 50
+  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
+  num_chan_reduced: 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:
+  num_chan: 1024
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [240000, 320000]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+MaskRCNNTrainFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_train2017.json
+    image_dir: train2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+
+MaskRCNNEvalFeed:
+  batch_size: 1
+  dataset:
+    dataset_dir: dataset/coco
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
+
+MaskRCNNTestFeed:
+  batch_size: 1
+  dataset:
+    annotation: annotations/instances_val2017.json
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  num_workers: 2
diff --git a/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_vd_fpn_2x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_vd_fpn_2x.yml
index bee5710b1f8e43d7fade2f5f0c4b07148160a889..957c53d6ded13574c4e5093e14430831b4a94794 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_r50_vd_fpn_2x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/configs/mask_rcnn_se154_vd_fpn_s1x.yml b/PaddleCV/PaddleDetection/configs/mask_rcnn_se154_vd_fpn_s1x.yml
index 3346bdb1d228f7de41351133e0a738d1de95a595..76bed15ee2dc8a130e6a0a8b59461132876c6cbb 100644
--- a/PaddleCV/PaddleDetection/configs/mask_rcnn_se154_vd_fpn_s1x.yml
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/docs/CONFIG.md b/PaddleCV/PaddleDetection/docs/CONFIG.md
index 10376e055a1c6333630dcaab09cfa23d638a2285..1655e02d4e4a07ded6f7ff9a736e679c33490e64 100644
--- a/PaddleCV/PaddleDetection/docs/CONFIG.md
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/docs/CONFIG_cn.md b/PaddleCV/PaddleDetection/docs/CONFIG_cn.md
index f27b7bdcc7e6f3d791352519ed56a9b97050b112..9008c3117e0af5d8cd8e5a78a206cee28a9cad24 100644
--- a/PaddleCV/PaddleDetection/docs/CONFIG_cn.md
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/docs/MODEL_ZOO.md b/PaddleCV/PaddleDetection/docs/MODEL_ZOO.md
index 88bf49de01eabb24431194883b8b0617ddfbb624..dea03d10b28fc4698f417457056080793244c835 100644
--- a/PaddleCV/PaddleDetection/docs/MODEL_ZOO.md
+++ b/PaddleCV/PaddleDetection/docs/MODEL_ZOO.md
@@ -38,16 +38,19 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
 | ResNet50-vd          | Faster         |    1    |   1x    |  36.4  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) |
 | ResNet50-FPN         | Faster         |    2    |   1x    |  37.2  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) |
 | ResNet50-FPN         | Faster         |    2    |   2x    |  37.7  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) |
-| ResNet50-FPN         | Mask           |    2    |   1x    |  37.9  |  34.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) |
+| ResNet50-FPN         | Mask           |    1    |   1x    |  37.9  |  34.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) |
+| ResNet50-FPN         | Mask           |    1    |   2x    |  38.7  |  34.7   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar) |
 | ResNet50-FPN         | Cascade Faster |    2    |   1x    |  40.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) |
 | ResNet50-vd-FPN      | Faster         |    2    |   2x    |  38.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) |
-| ResNet50-vd-FPN      | Mask           |    2    |   2x    |  39.8  |  35.4   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) |
+| ResNet50-vd-FPN      | Mask           |    1    |   2x    |  39.8  |  35.4   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) |
 | ResNet101            | Faster         |    1    |   1x    |  38.3  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) |
 | ResNet101-FPN        | Faster         |    1    |   1x    |  38.7  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
 | ResNet101-FPN        | Faster         |    1    |   2x    |  39.1  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
 | ResNet101-FPN        | Mask           |    1    |   1x    |  39.5  |  35.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) |
-| ResNet101-vd-FPN     | Faster         |    1    |   1x    |  40.0  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
-| ResNet101-vd-FPN     | Faster         |    1    |   2x    |  40.6  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
+| ResNet101-vd-FPN     | Faster         |    1    |   1x    |  40.5  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_1x.tar) |
+| ResNet101-vd-FPN     | Faster         |    1    |   2x    |  40.8  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar) |
+| ResNeXt101-vd-FPN    | Faster         |    1    |   1x    |  42.2  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.tar) |
+| ResNeXt101-vd-FPN    | Faster         |    1    |   2x    |  41.7  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_2x.tar) |
 | SENet154-vd-FPN      | Faster         |    1    |  1.44x  |  42.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) |
 | SENet154-vd-FPN      | Mask           |    1    |  1.44x  |  44.0  |  38.7   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) |
 
diff --git a/PaddleCV/PaddleDetection/ppdet/core/config/schema.py b/PaddleCV/PaddleDetection/ppdet/core/config/schema.py
index 5a73db4dc3ee43eb83746cdecdeec162bfea71f2..efba5be1dfd93243ff7a071f0f30accfa513e18f 100644
--- a/PaddleCV/PaddleDetection/ppdet/core/config/schema.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/core/config/yaml_helpers.py b/PaddleCV/PaddleDetection/ppdet/core/config/yaml_helpers.py
index 099a13e55d4c2982709e6dd4ba6d9939e7fa02ec..8a7738b47f4f86acde78ab8a3bcac590d61615fa 100644
--- a/PaddleCV/PaddleDetection/ppdet/core/config/yaml_helpers.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/core/workspace.py b/PaddleCV/PaddleDetection/ppdet/core/workspace.py
index 8e42ff3624a369dfec08cbad3ac03fb74d88d217..eaa0c901537bc3c6255c2202b2daed6836e86e8c 100644
--- a/PaddleCV/PaddleDetection/ppdet/core/workspace.py
+++ b/PaddleCV/PaddleDetection/ppdet/core/workspace.py
@@ -21,8 +21,9 @@ import os
 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__ = [
@@ -135,7 +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)
@@ -144,9 +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
@@ -163,4 +182,7 @@ def create(cls_or_name, **kwargs):
                     kwargs[k] = target
             else:
                 raise ValueError("Unsupported injection type:", target_key)
+    # prevent modification of global config values of reference types
+    # (e.g., list, dict) from within the created module instances
+    kwargs = copy.deepcopy(kwargs)
     return cls(**kwargs)
diff --git a/PaddleCV/PaddleDetection/ppdet/data/data_feed.py b/PaddleCV/PaddleDetection/ppdet/data/data_feed.py
index b4a89803f05db51c9594b71a943740532d85517f..b3c7222cae5a3d819b72a5d11438787f97c33ba6 100644
--- a/PaddleCV/PaddleDetection/ppdet/data/data_feed.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/modeling/anchor_heads/retina_head.py b/PaddleCV/PaddleDetection/ppdet/modeling/anchor_heads/retina_head.py
index 918efc8e220b9a58a8ce3db975500182340a2953..41246e8b6267881f62386653841ecfb525a254e1 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/anchor_heads/retina_head.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py
index 58d1e7978e3fc17356e7ce67c6b0d999909f435d..641ae0708bdda9be637861bfd29e43a6bc3b5bab 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py
+++ b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py
@@ -64,7 +64,7 @@ class FasterRCNN(object):
             gt_box = feed_vars['gt_box']
             is_crowd = feed_vars['is_crowd']
         else:
-            im_shape = feed_vars['im_info']
+            im_shape = feed_vars['im_shape']
         body_feats = self.backbone(im)
         body_feat_names = list(body_feats.keys())
 
diff --git a/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py
index fc6f7442b324f0728e3ee983a90e47fb6ced048b..ce6b1a6d724955d950ade6ba423e193a07ca0178 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py
+++ b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py
@@ -149,7 +149,11 @@ class MaskRCNN(object):
             cond = fluid.layers.less_than(x=bbox_size, y=size)
 
             mask_pred = fluid.layers.create_global_var(
-                shape=[1], value=0.0, dtype='float32', persistable=False)
+                shape=[1],
+                value=0.0,
+                dtype='float32',
+                persistable=False,
+                name='mask_pred')
 
             with fluid.layers.control_flow.Switch() as switch:
                 with switch.case(cond):
diff --git a/PaddleCV/PaddleDetection/ppdet/modeling/architectures/ssd.py b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/ssd.py
index 8857f21e4ad0d08dd0c9f6e1d1d6fa2aa7825f90..12ccff52311341133c589de31e68abab60963b36 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/architectures/ssd.py
+++ b/PaddleCV/PaddleDetection/ppdet/modeling/architectures/ssd.py
@@ -56,8 +56,8 @@ class SSD(object):
             self.output_decoder = SSDOutputDecoder(**output_decoder)
         if isinstance(metric, dict):
             self.metric = SSDMetric(**metric)
-
-    def _forward(self, feed_vars, mode='train'):
+        
+    def build(self, feed_vars, mode='train'):
         im = feed_vars['image']
         if mode == 'train' or mode == 'eval':
             gt_box = feed_vars['gt_box']
@@ -88,10 +88,16 @@ class SSD(object):
                 return {'bbox': pred}
 
     def train(self, feed_vars):
-        return self._forward(feed_vars, 'train')
+        return self.build(feed_vars, 'train')
 
     def eval(self, feed_vars):
-        return self._forward(feed_vars, 'eval')
+        return self.build(feed_vars, 'eval')
 
     def test(self, feed_vars):
-        return self._forward(feed_vars, 'test')
+        return self.build(feed_vars, 'test')
+
+    def is_bbox_normalized(self):
+        # SSD use output_decoder in output layers, bbox is normalized
+        # to range [0, 1], is_bbox_normalized is used in infer.py
+        return True
+
diff --git a/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py b/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py
index 3d36bfa21c85de848a86009671945a12cca20c38..2ffbdca83b3b6ff715e629cf859148e76ded86f1 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py
+++ b/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py
@@ -119,6 +119,7 @@ class ResNet(object):
             regularizer=L2Decay(norm_decay))
 
         if self.norm_type in ['bn', 'sync_bn']:
+            global_stats = True if self.freeze_norm else False
             out = fluid.layers.batch_norm(
                 input=conv,
                 act=act,
@@ -126,7 +127,8 @@ class ResNet(object):
                 param_attr=pattr,
                 bias_attr=battr,
                 moving_mean_name=bn_name + '_mean',
-                moving_variance_name=bn_name + '_variance', )
+                moving_variance_name=bn_name + '_variance',
+                use_global_stats=global_stats)
             scale = fluid.framework._get_var(pattr.name)
             bias = fluid.framework._get_var(battr.name)
         elif self.norm_type == 'affine_channel':
@@ -330,7 +332,6 @@ class ResNetC5(ResNet):
                  norm_decay=0.,
                  variant='b',
                  feature_maps=[5]):
-        super(ResNetC5, self).__init__(
-            depth, freeze_at, norm_type, freeze_norm, norm_decay,
-            variant, feature_maps)
+        super(ResNetC5, self).__init__(depth, freeze_at, norm_type, freeze_norm,
+                                       norm_decay, variant, feature_maps)
         self.severed_head = True
diff --git a/PaddleCV/PaddleDetection/ppdet/modeling/ops.py b/PaddleCV/PaddleDetection/ppdet/modeling/ops.py
index ae804134c5faebac92b21b7a28dea6369877d772..a6a08728d569df06395021e12ba2a85859ba6eeb 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/ops.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/bbox_head.py b/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/bbox_head.py
index a5344cf4a550564e263f644d2a334cf22d4d1461..21f79459d4b931021b89266c00082510c6b3641d 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/bbox_head.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/cascade_head.py b/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/cascade_head.py
index 563279406c5bdb6445b2410976c04abd13c8bccc..3eef6e5fe1f5a7f4d1c28d49b6252692c4dd09f0 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/cascade_head.py
+++ b/PaddleCV/PaddleDetection/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__()
@@ -196,7 +197,8 @@ class CascadeBBoxHead(object):
             # only use fg box delta to decode box
             bbox_pred_new = fluid.layers.slice(
                 bbox_pred_new, axes=[1], starts=[1], ends=[2])
-            bbox_pred_new = fluid.layers.expand(bbox_pred_new, [1, self.num_classes, 1])
+            bbox_pred_new = fluid.layers.expand(bbox_pred_new,
+                                                [1, self.num_classes, 1])
         decoded_box = fluid.layers.box_coder(
             prior_box=proposals_boxes,
             prior_box_var=bbox_reg_w,
diff --git a/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/mask_head.py b/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/mask_head.py
index 1d2b027de0f0e8a280e10fe5c7500a5b2da650d3..ad59de00e346be98ff99aec12abb504cfa304795 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/roi_heads/mask_head.py
+++ b/PaddleCV/PaddleDetection/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/PaddleCV/PaddleDetection/ppdet/modeling/target_assigners.py b/PaddleCV/PaddleDetection/ppdet/modeling/target_assigners.py
index ccdb2672e872689bac53e2791dc3c9760880352e..03755762df22c9707c0a15202561ed4cb145a0f4 100644
--- a/PaddleCV/PaddleDetection/ppdet/modeling/target_assigners.py
+++ b/PaddleCV/PaddleDetection/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,
diff --git a/PaddleCV/PaddleDetection/ppdet/utils/cli.py b/PaddleCV/PaddleDetection/ppdet/utils/cli.py
index 2df1a0fa8542d7c9be02ab2b0890350262f12773..665a29254a575b477554cbfc91a9259b8d93d2fb 100644
--- a/PaddleCV/PaddleDetection/ppdet/utils/cli.py
+++ b/PaddleCV/PaddleDetection/ppdet/utils/cli.py
@@ -65,7 +65,7 @@ class ArgsParser(ArgumentParser):
             s = s.strip()
             k, v = s.split('=')
             if '.' not in k:
-                config[k] = v
+                config[k] = yaml.load(v, Loader=yaml.Loader)
             else:
                 keys = k.split('.')
                 config[keys[0]] = {}
diff --git a/PaddleCV/PaddleDetection/ppdet/utils/coco_eval.py b/PaddleCV/PaddleDetection/ppdet/utils/coco_eval.py
index e7b01d673f2a116e57e7db56097ad7dd882c429b..7a8a5974535612754246b1a19915c6e12f3b5952 100644
--- a/PaddleCV/PaddleDetection/ppdet/utils/coco_eval.py
+++ b/PaddleCV/PaddleDetection/ppdet/utils/coco_eval.py
@@ -144,13 +144,13 @@ def mask2out(results, clsid2catid, resolution, thresh_binarize=0.5):
             continue
 
         masks = t['mask'][0]
-        im_shape = t['im_shape'][0][0]
 
         s = 0
         # for each sample
         for i in range(len(lengths)):
             num = lengths[i]
             im_id = int(im_ids[i][0])
+            im_shape = t['im_shape'][0][i]
 
             bbox = bboxes[s:s + num][:, 2:]
             clsid_scores = bboxes[s:s + num][:, 0:2]
diff --git a/PaddleCV/PaddleDetection/tools/infer.py b/PaddleCV/PaddleDetection/tools/infer.py
index 91cb939324a726089f0baa94ac2d4d0b8906bcb5..4b8f8d7fac0d5f9c1bafc7085889137e852c5a64 100644
--- a/PaddleCV/PaddleDetection/tools/infer.py
+++ b/PaddleCV/PaddleDetection/tools/infer.py
@@ -82,6 +82,47 @@ def get_test_images(infer_dir, infer_img):
     return images
 
 
+def prune_feed_vars(feeded_var_names, target_vars, prog):
+    """
+    Filter out feed variables which are not in program,
+    pruned feed variables are only used in post processing
+    on model output, which are not used in program, such
+    as im_id to identify image order, im_shape to clip bbox
+    in image.
+    """
+    exist_var_names = []
+    prog = prog.clone()
+    prog = prog._prune(targets=target_vars)
+    global_block = prog.global_block()
+    for name in feeded_var_names:
+        try:
+            v = global_block.var(name)
+            exist_var_names.append(v.name)
+        except Exception:
+            logger.info('save_inference_model pruned unused feed '
+                        'variables {}'.format(name))
+            pass
+    return exist_var_names
+
+
+def save_infer_model(FLAGS, exe, feed_vars, test_fetches, infer_prog):
+    cfg_name = os.path.basename(FLAGS.config).split('.')[0]
+    save_dir = os.path.join(FLAGS.output_dir, cfg_name)
+    feeded_var_names = [var.name for var in feed_vars.values()]
+    target_vars = test_fetches.values()
+    feeded_var_names = prune_feed_vars(feeded_var_names, target_vars, infer_prog)
+    logger.info("Save inference model to {}, input: {}, output: "
+                "{}...".format(save_dir, feeded_var_names,
+                               [var.name for var in target_vars]))
+    fluid.io.save_inference_model(
+        save_dir,
+        feeded_var_names=feeded_var_names,
+        target_vars=target_vars,
+        executor=exe,
+        main_program=infer_prog,
+        params_filename="__params__")
+
+
 def main():
     cfg = load_config(FLAGS.config)
 
@@ -143,6 +184,12 @@ def main():
     clsid2catid, catid2name = get_category_info(anno_file, with_background,
                                                 use_default_label)
 
+    # whether output bbox is normalized in model output layer
+    is_bbox_normalized = False
+    if hasattr(model, 'is_bbox_normalized') and \
+            callable(model.is_bbox_normalized):
+        is_bbox_normalized = model.is_bbox_normalized()
+
     imid2path = reader.imid2path
     for iter_id, data in enumerate(reader()):
         outs = exe.run(infer_prog,
@@ -157,7 +204,6 @@ def main():
 
         bbox_results = None
         mask_results = None
-        is_bbox_normalized = True if cfg.metric == 'VOC' else False
         if 'bbox' in res:
             bbox_results = bbox2out([res], clsid2catid, is_bbox_normalized)
         if 'mask' in res:
diff --git a/PaddleCV/PaddleDetection/tools/train.py b/PaddleCV/PaddleDetection/tools/train.py
index c12906748c20f4cdf06b419685721c1a236198cb..65e8be14a4b9522e5d2aef79ca5d742e9c26d110 100644
--- a/PaddleCV/PaddleDetection/tools/train.py
+++ b/PaddleCV/PaddleDetection/tools/train.py
@@ -86,7 +86,6 @@ def main():
     place = fluid.CUDAPlace(0) if cfg.use_gpu else fluid.CPUPlace()
     exe = fluid.Executor(place)
 
-    model = create(main_arch)
     lr_builder = create('LearningRate')
     optim_builder = create('OptimizerBuilder')
 
@@ -95,6 +94,7 @@ def main():
     train_prog = fluid.Program()
     with fluid.program_guard(train_prog, startup_prog):
         with fluid.unique_name.guard():
+            model = create(main_arch)
             train_pyreader, feed_vars = create_feed(train_feed)
             train_fetches = model.train(feed_vars)
             loss = train_fetches['loss']
@@ -113,6 +113,7 @@ def main():
         eval_prog = fluid.Program()
         with fluid.program_guard(eval_prog, startup_prog):
             with fluid.unique_name.guard():
+                model = create(main_arch)
                 eval_pyreader, feed_vars = create_feed(eval_feed)
                 fetches = model.eval(feed_vars)
         eval_prog = eval_prog.clone(True)
@@ -120,8 +121,9 @@ def main():
         eval_reader = create_reader(eval_feed)
         eval_pyreader.decorate_sample_list_generator(eval_reader, place)
 
-        # parse train fetches
-        extra_keys = ['im_info', 'im_id'] if cfg.metric == 'COCO' else []
+        # parse eval fetches
+        extra_keys = ['im_info', 'im_id',
+                      'im_shape'] if cfg.metric == 'COCO' else []
         eval_keys, eval_values, eval_cls = parse_fetches(fetches, eval_prog,
                                                          extra_keys)
 
@@ -132,7 +134,7 @@ def main():
     sync_bn = getattr(model.backbone, 'norm_type', None) == 'sync_bn'
     # only enable sync_bn in multi GPU devices
     build_strategy.sync_batch_norm = sync_bn and devices_num > 1 \
-				     and cfg.use_gpu
+         and cfg.use_gpu
     train_compile_program = fluid.compiler.CompiledProgram(
         train_prog).with_data_parallel(
             loss_name=loss.name, build_strategy=build_strategy)
@@ -141,12 +143,12 @@ def main():
 
     exe.run(startup_prog)
 
-    freeze_bn = getattr(model.backbone, 'freeze_norm', False)
+    fuse_bn = getattr(model.backbone, 'norm_type', None) == 'affine_channel'
     start_iter = 0
     if FLAGS.resume_checkpoint:
         checkpoint.load_checkpoint(exe, train_prog, FLAGS.resume_checkpoint)
         start_iter = checkpoint.global_step()
-    elif cfg.pretrain_weights and freeze_bn:
+    elif cfg.pretrain_weights and fuse_bn:
         checkpoint.load_and_fusebn(exe, train_prog, cfg.pretrain_weights)
     elif cfg.pretrain_weights:
         checkpoint.load_pretrain(exe, train_prog, cfg.pretrain_weights)
diff --git a/PaddleCV/face_detection/README_cn.md b/PaddleCV/face_detection/README_cn.md
index f63fbed02ab34520d79b2d2b000e31f5eb22e7f8..79df92893e05bf2bfa755499404215b3b0ba52fa 100644
--- a/PaddleCV/face_detection/README_cn.md
+++ b/PaddleCV/face_detection/README_cn.md
@@ -91,6 +91,7 @@ tar -xf vgg_ilsvrc_16_fc_reduced.tar.gz && rm -f vgg_ilsvrc_16_fc_reduced.tar.gz
 python -u train.py --batch_size=16 --pretrained_model=vgg_ilsvrc_16_fc_reduced
 ```
   - 可以通过设置 `export CUDA_VISIBLE_DEVICES=0,1,2,3` 指定想要使用的GPU数量，`batch_size`默认设置为12或16。
+  - **注意**: 在**Windows**机器上训练，需要设置 `--use_multiprocess=False`，因为在Windows上使用Python多进程加速训练时有错误。
   - 更多的可选参数见:
     ```bash
     python train.py --help
diff --git a/PaddleCV/face_detection/reader.py b/PaddleCV/face_detection/reader.py
index 6fdd2848b27c6e4876044a9445fcc1160f388ae1..970a88be9288ad973ab8a2e2c27ff775c8147675 100644
--- a/PaddleCV/face_detection/reader.py
+++ b/PaddleCV/face_detection/reader.py
@@ -280,14 +280,25 @@ def train_generator(settings, file_list, batch_size, shuffle=True):
     return reader
 
 
-def train(settings, file_list, batch_size, shuffle=True, num_workers=8):
+def train(settings,
+          file_list,
+          batch_size,
+          shuffle=True,
+          use_multiprocess=True,
+          num_workers=8):
     file_lists = load_file_list(file_list)
-    n = int(math.ceil(len(file_lists) // num_workers))
-    split_lists = [file_lists[i:i + n] for i in range(0, len(file_lists), n)]
-    readers = []
-    for iterm in split_lists:
-        readers.append(train_generator(settings, iterm, batch_size, shuffle))
-    return paddle.reader.multiprocess_reader(readers, False)
+    if use_multiprocess:
+        n = int(math.ceil(len(file_lists) // num_workers))
+        split_lists = [
+            file_lists[i:i + n] for i in range(0, len(file_lists), n)
+        ]
+        readers = []
+        for iterm in split_lists:
+            readers.append(
+                train_generator(settings, iterm, batch_size, shuffle))
+        return paddle.reader.multiprocess_reader(readers, False)
+    else:
+        return train_generator(settings, file_lists, batch_size, shuffle)
 
 
 def test(settings, file_list):
diff --git a/PaddleCV/face_detection/train.py b/PaddleCV/face_detection/train.py
index 2108bcc32a378bbb0803032108ddafea4161e202..425e30cfa6b2503994b7523fb0f3c13fcbcd07c3 100644
--- a/PaddleCV/face_detection/train.py
+++ b/PaddleCV/face_detection/train.py
@@ -9,6 +9,20 @@ import time
 import argparse
 import functools
 
+
+def set_paddle_flags(**kwargs):
+    for key, value in kwargs.items():
+        if os.environ.get(key, None) is None:
+            os.environ[key] = str(value)
+
+
+# NOTE(paddle-dev): All of these flags should be
+# set before `import paddle`. Otherwise, it would
+# not take any effect. 
+set_paddle_flags(
+    FLAGS_eager_delete_tensor_gb=0,  # enable GC to save memory
+)
+
 import paddle
 import paddle.fluid as fluid
 from pyramidbox import PyramidBox
@@ -32,6 +46,7 @@ add_arg('mean_BGR',         str,   '104., 117., 123.', "Mean value for B,G,R cha
 add_arg('with_mem_opt',     bool,  True,            "Whether to use memory optimization or not.")
 add_arg('pretrained_model', str,   './vgg_ilsvrc_16_fc_reduced/', "The init model path.")
 add_arg('data_dir',         str,   'data',          "The base dir of dataset")
+add_arg('use_multiprocess', bool,  True,            "Whether use multi-process for data preprocessing.")
 parser.add_argument('--enable_ce', action='store_true', help='If set, run the task with continuous evaluation logs.')
 parser.add_argument('--batch_num', type=int, help="batch num for ce")
 parser.add_argument('--num_devices', type=int, default=1, help='Number of GPU devices')
@@ -163,7 +178,8 @@ def train(args, config, train_params, train_file_list):
                                 train_file_list,
                                 batch_size_per_device,
                                 shuffle = is_shuffle,
-                                num_workers = num_workers)
+                                use_multiprocess=args.use_multiprocess,
+                                num_workers=num_workers)
     train_py_reader.decorate_paddle_reader(train_reader)
 
     if args.parallel:
diff --git a/PaddleCV/ssd/README.md b/PaddleCV/ssd/README.md
index 2466ba96577c7cb1e2bb335a0b8b5c74edbb92fd..c9b41aa4c5fa00c085f4c0013b236e81ddf5f9c1 100644
--- a/PaddleCV/ssd/README.md
+++ b/PaddleCV/ssd/README.md
@@ -23,7 +23,7 @@ SSD is readily pluggable into a wide variant standard convolutional network, suc
 
 Please download [PASCAL VOC dataset](http://host.robots.ox.ac.uk/pascal/VOC/) at first, skip this step if you already have one.
 
-```bash
+```
 cd data/pascalvoc
 ./download.sh
 ```
@@ -36,7 +36,7 @@ The command `download.sh` also will create training and testing file lists.
 
 We provide two pre-trained models. The one is MobileNet-v1 SSD trained on COCO dataset, but removed the convolutional predictors for COCO dataset. This model can be used to initialize the models when training other datasets, like PASCAL VOC. The other pre-trained model is MobileNet-v1 trained on ImageNet 2012 dataset but removed the last weights and bias in the Fully-Connected layer. Download MobileNet-v1 SSD:
 
-    ```bash
+    ```
     ./pretrained/download_coco.sh
     ```
 
@@ -46,13 +46,14 @@ Declaration: the MobileNet-v1 SSD model is converted by [TensorFlow model](https
 #### Train on PASCAL VOC
 
 `train.py` is the main caller of the training module. Examples of usage are shown below.
-  ```bash
-  python -u train.py --batch_size=64 --dataset='pascalvoc' --pretrained_model='pretrained/ssd_mobilenet_v1_coco/'
+  ```
+  python -u train.py --batch_size=64 --dataset=pascalvoc --pretrained_model=pretrained/ssd_mobilenet_v1_coco/
   ```
    - Set ```export CUDA_VISIBLE_DEVICES=0,1``` to specifiy the number of GPU you want to use.
+   - **Note**: set `--use_multiprocess=False` when training on **Windows**, since some problems need to be solved when using Python multiprocess to accelerate data processing.
    - For more help on arguments:
 
-  ```bash
+  ```
   python train.py --help
   ```
 
@@ -69,14 +70,14 @@ We used RMSProp optimizer with mini-batch size 64 to train the MobileNet-SSD. Th
 You can evaluate your trained model in different metrics like 11point, integral on both PASCAL VOC and COCO dataset. Note we set the default test list to the dataset's test/val list, you can use your own test list by setting ```--test_list``` args.
 
 `eval.py` is the main caller of the evaluating module. Examples of usage are shown below.
-```bash
-python eval.py --dataset='pascalvoc' --model_dir='train_pascal_model/best_model' --data_dir='data/pascalvoc' --test_list='test.txt' --ap_version='11point' --nms_threshold=0.45
+```
+python eval.py --dataset=pascalvoc --model_dir=model/best_model --data_dir=data/pascalvoc --test_list=test.txt
 ```
 
 ### Infer and Visualize
 `infer.py` is the main caller of the inferring module. Examples of usage are shown below.
-```bash
-python infer.py --dataset='pascalvoc' --nms_threshold=0.45 --model_dir='train_pascal_model/best_model' --image_path='./data/pascalvoc/VOCdevkit/VOC2007/JPEGImages/009963.jpg'
+```
+python infer.py --dataset=pascalvoc --nms_threshold=0.45 --model_dir=model/best_model --image_path=./data/pascalvoc/VOCdevkit/VOC2007/JPEGImages/009963.jpg
 ```
 Below are the examples of running the inference and visualizing the model result.
 <p align="center">
diff --git a/PaddleCV/ssd/README_cn.md b/PaddleCV/ssd/README_cn.md
index 8c4cecab28e49c10820e092d3a521facf4be68ea..bd1193fa4305bc6a3597b6281b8842cf45287aa5 100644
--- a/PaddleCV/ssd/README_cn.md
+++ b/PaddleCV/ssd/README_cn.md
@@ -24,7 +24,7 @@ SSD 可以方便地插入到任何一种标准卷积网络中，比如 VGG、Res
 
 请先使用下面的命令下载 [PASCAL VOC 数据集](http://host.robots.ox.ac.uk/pascal/VOC/)：
 
-```bash
+```
 cd data/pascalvoc
 ./download.sh
 ```
@@ -38,7 +38,7 @@ cd data/pascalvoc
 
 我们提供了两个预训练模型。第一个模型是在 COCO 数据集上预训练的 MobileNet-v1 SSD，我们将它的预测头移除了以便在 COCO 以外的数据集上进行训练。第二个模型是在 ImageNet 2012 数据集上预训练的 MobileNet-v1，我们也将最后的全连接层移除以便进行目标检测训练。下载 MobileNet-v1 SSD:
 
-    ```bash
+    ```
     ./pretrained/download_coco.sh
     ```
 
@@ -48,13 +48,14 @@ cd data/pascalvoc
 #### 训练
 
 `train.py` 是训练模块的主要执行程序，调用示例如下：
-  ```bash
-  python -u train.py --batch_size=64 --dataset='pascalvoc' --pretrained_model='pretrained/ssd_mobilenet_v1_coco/'
+  ```
+  python -u train.py --batch_size=64 --dataset=pascalvoc --pretrained_model=pretrained/ssd_mobilenet_v1_coco/
   ```
    - 可以通过设置 ```export CUDA_VISIBLE_DEVICES=0,1``` 指定想要使用的GPU数量。
+   - **注意**: 在**Windows**机器上训练，需要设置 `--use_multiprocess=False`，因为在Windows上使用Python多进程加速训练时有错误。
    - 更多的可选参数见:
 
-  ```bash
+  ```
   python train.py --help
   ```
 
@@ -71,15 +72,16 @@ cd data/pascalvoc
 你可以使用11point、integral等指标在PASCAL VOC 数据集上评估训练好的模型。不失一般性，我们采用相应数据集的测试列表作为样例代码的默认列表，你也可以通过设置```--test_list```来指定自己的测试样本列表。
 
 `eval.py`是评估模块的主要执行程序，调用示例如下：
-```bash
-python eval.py --dataset='pascalvoc' --model_dir='train_pascal_model/best_model' --data_dir='data/pascalvoc' --test_list='test.txt' --ap_version='11point' --nms_threshold=0.45
+
+```
+python eval.py --dataset=pascalvoc --model_dir=model/best_model --data_dir=data/pascalvoc --test_list=test.txt
 ```
 
 ### 模型预测以及可视化
 
 `infer.py`是预测及可视化模块的主要执行程序，调用示例如下：
-```bash
-python infer.py --dataset='pascalvoc' --nms_threshold=0.45 --model_dir='train_pascal_model/best_model' --image_path='./data/pascalvoc/VOCdevkit/VOC2007/JPEGImages/009963.jpg'
+```
+python infer.py --dataset=pascalvoc --nms_threshold=0.45 --model_dir=model/best_model --image_path=./data/pascalvoc/VOCdevkit/VOC2007/JPEGImages/009963.jpg
 ```
 下图可视化了模型的预测结果：
 <p align="center">
diff --git a/PaddleCV/ssd/reader.py b/PaddleCV/ssd/reader.py
index 8024bf067fcd7240fcbd9830c7df5e0afe04592c..731e943ee3074ae6afb89ddcbc61c915e20a898e 100644
--- a/PaddleCV/ssd/reader.py
+++ b/PaddleCV/ssd/reader.py
@@ -283,6 +283,7 @@ def train(settings,
           file_list,
           batch_size,
           shuffle=True,
+          use_multiprocess=True,
           num_workers=8,
           enable_ce=False):
     file_path = os.path.join(settings.data_dir, file_list)
@@ -294,14 +295,15 @@ def train(settings,
         image_ids = coco_api.getImgIds()
         images = coco_api.loadImgs(image_ids)
         np.random.shuffle(images)
-        n = int(math.ceil(len(images) // num_workers))
-        image_lists = [images[i:i + n] for i in range(0, len(images), n)]
-
         if '2014' in file_list:
             sub_dir = "train2014"
         elif '2017' in file_list:
             sub_dir = "train2017"
         data_dir = os.path.join(settings.data_dir, sub_dir)
+
+        n = int(math.ceil(len(images) // num_workers)) if use_multiprocess \
+            else len(images)
+        image_lists = [images[i:i + n] for i in range(0, len(images), n)]
         for l in image_lists:
             readers.append(
                 coco(settings, coco_api, l, 'train', batch_size, shuffle,
@@ -309,11 +311,16 @@ def train(settings,
     else:
         images = [line.strip() for line in open(file_path)]
         np.random.shuffle(images)
-        n = int(math.ceil(len(images) // num_workers))
+        n = int(math.ceil(len(images) // num_workers)) if use_multiprocess \
+            else len(images)
         image_lists = [images[i:i + n] for i in range(0, len(images), n)]
         for l in image_lists:
             readers.append(pascalvoc(settings, l, 'train', batch_size, shuffle))
-    return paddle.reader.multiprocess_reader(readers, False)
+    print("use_multiprocess ", use_multiprocess)
+    if use_multiprocess:
+        return paddle.reader.multiprocess_reader(readers, False)
+    else:
+        return readers[0]
 
 
 def test(settings, file_list, batch_size):
diff --git a/PaddleCV/ssd/train.py b/PaddleCV/ssd/train.py
index 31d69a62000391038f4628e7f77074b10c0a0c54..4f5fc26261d563e64c44b99b268c7b705a154a80 100644
--- a/PaddleCV/ssd/train.py
+++ b/PaddleCV/ssd/train.py
@@ -7,6 +7,20 @@ import shutil
 import math
 import multiprocessing
 
+
+def set_paddle_flags(**kwargs):
+    for key, value in kwargs.items():
+        if os.environ.get(key, None) is None:
+            os.environ[key] = str(value)
+
+
+# NOTE(paddle-dev): All of these flags should be
+# set before `import paddle`. Otherwise, it would
+# not take any effect. 
+set_paddle_flags(
+    FLAGS_eager_delete_tensor_gb=0,  # enable GC to save memory
+)
+
 import paddle
 import paddle.fluid as fluid
 import reader
@@ -28,6 +42,7 @@ add_arg('ap_version',       str,   '11point',           "mAP version can be inte
 add_arg('image_shape',      str,   '3,300,300',         "Input image shape.")
 add_arg('mean_BGR',         str,   '127.5,127.5,127.5', "Mean value for B,G,R channel which will be subtracted.")
 add_arg('data_dir',         str,   'data/pascalvoc', "Data directory.")
+add_arg('use_multiprocess', bool,  True,  "Whether use multi-process for data preprocessing.")
 add_arg('enable_ce',        bool,  False, "Whether use CE to evaluate the model.")
 #yapf: enable
 
@@ -185,14 +200,8 @@ def train(args,
         build_strategy.memory_optimize = True
         train_exe = fluid.ParallelExecutor(main_program=train_prog,
             use_cuda=use_gpu, loss_name=loss.name, build_strategy=build_strategy)
-    train_reader = reader.train(data_args,
-                                train_file_list,
-                                batch_size_per_device,
-                                shuffle=is_shuffle,
-                                num_workers=num_workers,
-                                enable_ce=enable_ce)
+
     test_reader = reader.test(data_args, val_file_list, batch_size)
-    train_py_reader.decorate_paddle_reader(train_reader)
     test_py_reader.decorate_paddle_reader(test_reader)
 
     def save_model(postfix, main_prog):
@@ -232,6 +241,7 @@ def train(args,
                                 train_file_list,
                                 batch_size_per_device,
                                 shuffle=is_shuffle,
+                                use_multiprocess=args.use_multiprocess,
                                 num_workers=num_workers,
                                 enable_ce=enable_ce)
         train_py_reader.decorate_paddle_reader(train_reader)