Merge pull request #1153 from qingqing01/ce_image_classification2

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

 ####this file is only used for continuous evaluation test!
-
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import os
 import sys
 sys.path.append(os.environ['ceroot'])
@@ -14,7 +16,7 @@ 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=False, desc='TOP5 ACC')
-test_cost_kpi = CostKpi('test_cost', 1.0, 0, actived=True, desc='train cost')
+test_cost_kpi = CostKpi('test_cost', 0.05, 0, actived=True, desc='train cost')
 train_speed_kpi = AccKpi(
     'train_speed',
     0.5,
@@ -27,13 +29,13 @@ train_acc_top1_card4_kpi = AccKpi(
 train_acc_top5_card4_kpi = AccKpi(
     'train_acc_top5_card4', 0.05, 0, actived=False, desc='TOP5 ACC')
 train_cost_card4_kpi = CostKpi(
-    'train_cost_kpi', 0.3, 0, actived=True, desc='train cost')
+    '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=False, desc='TOP5 ACC')
 test_cost_card4_kpi = CostKpi(
-    'test_cost_card4', 1.0, 0, actived=True, desc='train cost')
+    'test_cost_card4', 0.05, 0, actived=True, desc='train cost')
 train_speed_card4_kpi = AccKpi(
     'train_speed_card4',
     0.5,

fluid/image_classification/eval.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import os
 import numpy as np
 import time

fluid/image_classification/infer.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import os
 import numpy as np
 import time
@@ -15,7 +18,6 @@ import math
 parser = argparse.ArgumentParser(description=__doc__)
 # yapf: disable
 add_arg = functools.partial(add_arguments, argparser=parser)
-add_arg('batch_size',       int,  256,                  "Minibatch size.")
 add_arg('use_gpu',          bool, True,                 "Whether to use GPU or not.")
 add_arg('class_dim',        int,  1000,                 "Class number.")
 add_arg('image_shape',      str,  "3,224,224",          "Input image size")

fluid/image_classification/models/alexnet.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 import math

fluid/image_classification/models/dpn.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import os
 import numpy as np
 import time
 import sys
-import paddle
-import paddle.fluid as fluid
-import paddle.fluid.layers.control_flow as control_flow
-import paddle.fluid.layers.nn as nn
-import paddle.fluid.layers.tensor as tensor
 import math
+import paddle.fluid as fluid
 
 __all__ = ["DPN", "DPN68", "DPN92", "DPN98", "DPN107", "DPN131"]
 
@@ -67,7 +66,7 @@ class DPN(object):
         for gc in range(4):
             bw = bws[gc]
             inc = inc_sec[gc]
-            R = (k_r * bw) / rs[gc]
+            R = (k_r * bw) // rs[gc]
             if gc == 0:
                 _type1 = 'proj'
                 _type2 = 'normal'
@@ -178,8 +177,8 @@ class DPN(object):
                           _type='normal'):
         kw = 3
         kh = 3
-        pw = (kw - 1) / 2
-        ph = (kh - 1) / 2
+        pw = (kw - 1) // 2
+        ph = (kh - 1) // 2
 
         # type
         if _type is 'proj':

fluid/image_classification/models/googlenet.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 
@@ -36,7 +39,7 @@ class GoogleNet():
             num_filters=num_filters,
             filter_size=filter_size,
             stride=stride,
-            padding=(filter_size - 1) / 2,
+            padding=(filter_size - 1) // 2,
             groups=groups,
             act=act,
             param_attr=param_attr,

fluid/image_classification/models/inception_v4.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 import math

fluid/image_classification/models/learning_rate.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 import paddle.fluid.layers.ops as ops

fluid/image_classification/models/mobilenet.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle.fluid as fluid
 from paddle.fluid.initializer import MSRA
 from paddle.fluid.param_attr import ParamAttr

fluid/image_classification/models/resnet.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 import math
@@ -75,7 +78,7 @@ class ResNet():
             num_filters=num_filters,
             filter_size=filter_size,
             stride=stride,
-            padding=(filter_size - 1) / 2,
+            padding=(filter_size - 1) // 2,
             groups=groups,
             act=None,
             bias_attr=False)

fluid/image_classification/models/se_resnext.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 import math
@@ -11,7 +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,
@@ -102,9 +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,
@@ -156,7 +161,7 @@ class SE_ResNeXt():
             num_filters=num_filters,
             filter_size=filter_size,
             stride=stride,
-            padding=(filter_size - 1) / 2,
+            padding=(filter_size - 1) // 2,
             groups=groups,
             act=None,
             bias_attr=False)
@@ -167,7 +172,7 @@ class SE_ResNeXt():
             input=input, pool_size=0, pool_type='avg', global_pooling=True)
         stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0)
         squeeze = fluid.layers.fc(input=pool,
-                                  size=num_channels / reduction_ratio,
+                                  size=num_channels // reduction_ratio,
                                   act='relu',
                                   param_attr=fluid.param_attr.ParamAttr(
                                       initializer=fluid.initializer.Uniform(

fluid/image_classification/models/vgg.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
 

fluid/image_classification/train.py

+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
 import os
 import numpy as np
 import time
 import sys
+import functools
+import math
 import paddle
 import paddle.fluid as fluid
 import paddle.dataset.flowers as flowers
 import models
 import reader
 import argparse
-import functools
 from models.learning_rate import cosine_decay
 from utility import add_arguments, print_arguments
-import math
 
 parser = argparse.ArgumentParser(description=__doc__)
 add_arg = functools.partial(add_arguments, argparser=parser)
@@ -104,8 +107,11 @@ def train(args):
 
     if args.enable_ce:
         assert model_name == "SE_ResNeXt50_32x4d"
+        fluid.default_startup_program().random_seed = 1000
+        model.params["enable_ce"] = True
+        class_dim = 102
 
-    if model_name is "GoogleNet":
+    if model_name == "GoogleNet":
         out0, out1, out2 = model.net(input=image, class_dim=class_dim)
         cost0 = fluid.layers.cross_entropy(input=out0, label=label)
         cost1 = fluid.layers.cross_entropy(input=out1, label=label)
@@ -134,8 +140,6 @@ 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 +148,6 @@ 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 +173,7 @@ 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(
@@ -256,7 +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)
@@ -266,21 +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))
 
 

fluid/image_classification/utility.py

@@ -18,6 +18,7 @@ from __future__ import division
 from __future__ import print_function
 import distutils.util
 import numpy as np
+import six
 from paddle.fluid import core
 
 
@@ -37,7 +38,7 @@ def print_arguments(args):
     :type args: argparse.Namespace
     """
     print("-----------  Configuration Arguments -----------")
-    for arg, value in sorted(vars(args).iteritems()):
+    for arg, value in sorted(six.iteritems(vars(args))):
         print("%s: %s" % (arg, value))
     print("------------------------------------------------")