sync bn for yolov3.

PaddleCV/yolov3/README.md

@@ -138,9 +138,9 @@ Evalutaion result is shown as below:
 
 |   input size  | mAP(IoU=0.50:0.95) | mAP(IoU=0.50) | mAP(IoU=0.75) |
 | :------: | :------: | :------: | :------: |
-| 608x608| 37.7 | 59.8 | 40.8 |
-| 416x416 | 36.5 | 58.2 | 39.1 |
-| 320x320 | 34.1 | 55.4 | 36.3 |
+| 608x608| 38.9 | 61.1 | 42.0 |
+| 416x416 | 37.5 | 59.6 | 40.2 |
+| 320x320 | 34.8 | 56.4 | 36.9 |
 
 - **NOTE:** evaluations based on `pycocotools` evaluator, predict bounding boxes with `score < 0.05` were not filtered out. Some frameworks which filtered out predict bounding boxes with `score < 0.05` will cause a drop in accuracy.
 

PaddleCV/yolov3/README_cn.md

@@ -138,9 +138,9 @@ Train Loss
 
 |   input size  | mAP(IoU=0.50:0.95) | mAP(IoU=0.50) | mAP(IoU=0.75) |
 | :------: | :------: | :------: | :------: |
-| 608x608| 37.7 | 59.8 | 40.8 |
-| 416x416 | 36.5 | 58.2 | 39.1 |
-| 320x320 | 34.1 | 55.4 | 36.3 |
+| 608x608| 38.9 | 61.1 | 42.0 |
+| 416x416 | 37.5 | 59.6 | 40.2 |
+| 320x320 | 34.8 | 56.4 | 36.9 |
 
 - **注意: **评估结果基于`pycocotools`评估器，没有滤除`score < 0.05`的预测框，其他框架有此滤除操作会导致精度下降。
 

PaddleCV/yolov3/train.py

@@ -82,6 +82,7 @@ def train():
 
     build_strategy= fluid.BuildStrategy()
     build_strategy.memory_optimize = True
+    build_strategy.sync_batch_norm = True
     compile_program = fluid.compiler.CompiledProgram(
             fluid.default_main_program()).with_data_parallel(
             loss_name=loss.name, build_strategy=build_strategy)