Update CE.

fluid/image_classification/_ce.py

@@ -7,14 +7,14 @@ from kpi import CostKpi, DurationKpi, AccKpi
 
 #### NOTE kpi.py should shared in models in some way!!!!
 
-train_acc_top1_kpi = AccKpi('train_acc_top1', 0.05, 0, desc='TOP1 ACC')
+train_acc_top1_kpi = AccKpi('train_acc_top1', 0.005, 0, desc='TOP1 ACC')
 train_acc_top5_kpi = AccKpi(
-    'train_acc_top5', 0.05, 0, actived=False, desc='TOP5 ACC')
+    'train_acc_top5', 0.005, 0, actived=True, desc='TOP5 ACC')
 train_cost_kpi = CostKpi('train_cost', 0.5, 0, actived=True, desc='train cost')
-test_acc_top1_kpi = AccKpi('test_acc_top1', 0.05, 0, desc='TOP1 ACC')
+test_acc_top1_kpi = AccKpi('test_acc_top1', 0.005, 0, desc='TOP1 ACC')
 test_acc_top5_kpi = AccKpi(
-    'test_acc_top5', 0.05, 0, actived=False, desc='TOP5 ACC')
-test_cost_kpi = CostKpi('test_cost', 1.0, 0, actived=True, desc='train cost')
+    'test_acc_top5', 0.005, 0, actived=True, desc='TOP5 ACC')
+test_cost_kpi = CostKpi('test_cost', 0.005, 0, actived=True, desc='train cost')
 train_speed_kpi = AccKpi(
     'train_speed',
     0.5,
@@ -23,17 +23,17 @@ train_speed_kpi = AccKpi(
     unit_repr='seconds/image',
     desc='train speed in one GPU card')
 train_acc_top1_card4_kpi = AccKpi(
-    'train_acc_top1_card4', 0.05, 0, desc='TOP1 ACC')
+    'train_acc_top1_card4', 0.005, 0, desc='TOP1 ACC')
 train_acc_top5_card4_kpi = AccKpi(
-    'train_acc_top5_card4', 0.05, 0, actived=False, desc='TOP5 ACC')
+    'train_acc_top5_card4', 0.005, 0, actived=True, desc='TOP5 ACC')
 train_cost_card4_kpi = CostKpi(
-    'train_cost_kpi', 0.3, 0, actived=True, desc='train cost')
+    'train_cost_kpi', 0.005, 0, actived=True, desc='train cost')
 test_acc_top1_card4_kpi = AccKpi(
-    'test_acc_top1_card4', 0.05, 0, desc='TOP1 ACC')
+    'test_acc_top1_card4', 0.005, 0, desc='TOP1 ACC')
 test_acc_top5_card4_kpi = AccKpi(
-    'test_acc_top5_card4', 0.05, 0, actived=False, desc='TOP5 ACC')
+    'test_acc_top5_card4', 0.005, 0, actived=True, desc='TOP5 ACC')
 test_cost_card4_kpi = CostKpi(
-    'test_cost_card4', 1.0, 0, actived=True, desc='train cost')
+    'test_cost_card4', 0.005, 0, actived=True, desc='train cost')
 train_speed_card4_kpi = AccKpi(
     'train_speed_card4',
     0.5,

fluid/image_classification/train.py

@@ -104,6 +104,8 @@ def train(args):
 
     if args.enable_ce:
         assert model_name == "SE_ResNeXt50_32x4d"
+        fluid.default_startup_program().random_seed = 1000
+        model.params["dropout_seed"] = 100
 
     if model_name is "GoogleNet":
         out0, out1, out2 = model.net(input=image, class_dim=class_dim)
@@ -134,8 +136,6 @@ def train(args):
     params["num_epochs"] = args.num_epochs
     params["learning_strategy"]["batch_size"] = args.batch_size
     params["learning_strategy"]["name"] = args.lr_strategy
-    if args.enable_ce:
-        params["dropout_seed"] = 10
 
     # initialize optimizer
     optimizer = optimizer_setting(params)
@@ -144,9 +144,6 @@ def train(args):
     if with_memory_optimization:
         fluid.memory_optimize(fluid.default_main_program())
 
-    if args.enable_ce:
-        fluid.default_startup_program().random_seed = 1000
-
     place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace()
     exe = fluid.Executor(place)
     exe.run(fluid.default_startup_program())
@@ -172,6 +169,7 @@ def train(args):
         # but it is time consuming. For faster speed, need another dataset.
         import random
         random.seed(0)
+        np.random.seed(0)
         train_reader = paddle.batch(
             flowers.train(use_xmap=False), batch_size=train_batch_size)
         test_reader = paddle.batch(