Update CE

fluid/image_classification/.run_ce.sh

 #!/bin/bash
 
 # This file is only used for continuous evaluation.
+export FLAGS_cudnn_deterministic=True
 cudaid=${object_detection_cudaid:=0}
 export CUDA_VISIBLE_DEVICES=$cudaid
-python train.py --batch_size=64 --num_epochs=10 --total_images=6149 --enable_ce=True | python _ce.py
+python train.py --batch_size=64 --num_epochs=5 --enable_ce=True | python _ce.py
 
 cudaid=${object_detection_cudaid_m:=0, 1, 2, 3}
 export CUDA_VISIBLE_DEVICES=$cudaid
-python train.py --batch_size=64 --num_epochs=10 --total_images=6149 --enable_ce=True | python _ce.py
+python train.py --batch_size=128 --num_epochs=5 --enable_ce=True | python _ce.py

fluid/image_classification/_ce.py

@@ -11,11 +11,11 @@ from kpi import CostKpi, DurationKpi, AccKpi
 
 train_acc_top1_kpi = AccKpi('train_acc_top1', 0.05, 0, desc='TOP1 ACC')
 train_acc_top5_kpi = AccKpi(
-    'train_acc_top5', 0.05, 0, actived=True, desc='TOP5 ACC')
+    'train_acc_top5', 0.05, 0, actived=False, 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_top5_kpi = AccKpi(
-    'test_acc_top5', 0.05, 0, actived=True, desc='TOP5 ACC')
+    'test_acc_top5', 0.05, 0, actived=False, desc='TOP5 ACC')
 test_cost_kpi = CostKpi('test_cost', 0.05, 0, actived=True, desc='train cost')
 train_speed_kpi = AccKpi(
     'train_speed',
@@ -27,13 +27,13 @@ train_speed_kpi = AccKpi(
 train_acc_top1_card4_kpi = AccKpi(
     'train_acc_top1_card4', 0.05, 0, desc='TOP1 ACC')
 train_acc_top5_card4_kpi = AccKpi(
-    'train_acc_top5_card4', 0.05, 0, actived=True, desc='TOP5 ACC')
+    'train_acc_top5_card4', 0.05, 0, actived=False, desc='TOP5 ACC')
 train_cost_card4_kpi = CostKpi(
     'train_cost_kpi', 0.05, 0, actived=True, desc='train cost')
 test_acc_top1_card4_kpi = AccKpi(
     'test_acc_top1_card4', 0.05, 0, desc='TOP1 ACC')
 test_acc_top5_card4_kpi = AccKpi(
-    'test_acc_top5_card4', 0.05, 0, actived=True, desc='TOP5 ACC')
+    'test_acc_top5_card4', 0.05, 0, actived=False, desc='TOP5 ACC')
 test_cost_card4_kpi = CostKpi(
     'test_cost_card4', 0.05, 0, actived=True, desc='train cost')
 train_speed_card4_kpi = AccKpi(

fluid/image_classification/models/se_resnext.py

@@ -14,7 +14,7 @@ train_parameters = {
     "input_size": [3, 224, 224],
     "input_mean": [0.485, 0.456, 0.406],
     "input_std": [0.229, 0.224, 0.225],
-    "dropout_seed": None,
+    "enable_ce": False,
     "learning_strategy": {
         "name": "piecewise_decay",
         "batch_size": 256,
@@ -105,9 +105,11 @@ class SE_ResNeXt():
 
         pool = fluid.layers.pool2d(
             input=conv, pool_size=7, pool_type='avg', global_pooling=True)
-        # do not set seed when traning, it is only used for debug
-        drop = fluid.layers.dropout(
-            x=pool, dropout_prob=0.5, seed=self.params["dropout_seed"])
+        # enable_ce is used for continuous evaluation to remove the randomness
+        if self.params["enable_ce"]:
+            drop = pool
+        else:
+            drop = fluid.layers.dropout(x=pool, dropout_prob=0.5)
         stdv = 1.0 / math.sqrt(drop.shape[1] * 1.0)
         out = fluid.layers.fc(input=drop,
                               size=class_dim,

fluid/image_classification/train.py

@@ -108,7 +108,7 @@ 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
+        model.params["enable_ce"] = True
         class_dim = 102
 
     if model_name == "GoogleNet":
@@ -258,7 +258,7 @@ def train(args):
         # This is for continuous evaluation only
         if args.enable_ce and pass_id == args.num_epochs - 1:
             if gpu_nums == 1:
-                # Use the last cost/acc for training
+                # Use the mean cost/acc for training
                 print("kpis	train_cost	%s" % train_loss)
                 print("kpis	train_acc_top1	%s" % train_acc1)
                 print("kpis	train_acc_top5	%s" % train_acc5)
@@ -268,21 +268,21 @@ def train(args):
                 print("kpis	test_acc_top5	%s" % test_acc5)
                 print("kpis	train_speed	%s" % train_speed)
             else:
-                # Use the last cost/acc for training
-                print("kpis    train_cost_card%s       %s" %
+                # Use the mean cost/acc for training
+                print("kpis	train_cost_card%s	%s" %
                       (gpu_nums, train_loss))
-                print("kpis    train_acc_top1_card%s   %s" %
+                print("kpis	train_acc_top1_card%s	%s" %
                       (gpu_nums, train_acc1))
-                print("kpis    train_acc_top5_card%s   %s" %
+                print("kpis	train_acc_top5_card%s	%s" %
                       (gpu_nums, train_acc5))
                 # Use the mean cost/acc for testing
-                print("kpis    test_cost_card%s        %s" %
+                print("kpis	test_cost_card%s	%s" %
                       (gpu_nums, test_loss))
-                print("kpis    test_acc_top1_card%s    %s" %
+                print("kpis	test_acc_top1_card%s	%s" %
                       (gpu_nums, test_acc1))
-                print("kpis    test_acc_top5_card%s    %s" %
+                print("kpis	test_acc_top5_card%s	%s" %
                       (gpu_nums, test_acc5))
-                print("kpis    train_speed_card%s      %s" %
+                print("kpis	train_speed_card%s	%s" %
                       (gpu_nums, train_speed))