Merge branch 'feature/tester' into feature/recommendation_v2_api

.travis.yml

@@ -57,7 +57,7 @@ before_install:
   - if [[ "$JOB" == "PRE_COMMIT" ]]; then sudo ln -s /usr/bin/clang-format-3.8 /usr/bin/clang-format; fi
   # Paddle is using protobuf 3.1 currently. Protobuf 3.2 breaks the compatibility. So we specify the python 
   # protobuf version.
-  - pip install numpy wheel 'protobuf==3.1' sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker 'scikit-learn>=0.18.0' 'scipy>=0.18.0'
+  - pip install numpy wheel 'protobuf==3.1' sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker
 script:
   - paddle/scripts/travis/main.sh
 notifications:

demo/mnist/api_train_v2.py

-import numpy
 import paddle.v2 as paddle
 
 
@@ -21,7 +20,7 @@ def main():
 
     adam_optimizer = paddle.optimizer.Adam(learning_rate=0.01)
 
-    trainer = paddle.trainer.SGD(topology=cost,
+    trainer = paddle.trainer.SGD(cost=cost,
                                  parameters=parameters,
                                  update_equation=adam_optimizer)
 
@@ -29,7 +28,7 @@ def main():
         if isinstance(event, paddle.event.EndIteration):
             if event.batch_id % 1000 == 0:
                 result = trainer.test(reader=paddle.reader.batched(
-                    paddle.dataset.mnist.test_creator(), batch_size=256))
+                    paddle.dataset.mnist.test(), batch_size=256))
 
                 print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
                     event.pass_id, event.batch_id, event.cost, event.metrics,
@@ -41,7 +40,7 @@ def main():
     trainer.train(
         reader=paddle.reader.batched(
             paddle.reader.shuffle(
-                paddle.dataset.mnist.train_creator(), buf_size=8192),
+                paddle.dataset.mnist.train(), buf_size=8192),
             batch_size=32),
         event_handler=event_handler)
 

python/paddle/v2/__init__.py

@@ -18,6 +18,7 @@ import parameters
 import trainer
 import event
 import data_type
+import topology
 import data_feeder
 from . import dataset
 from . import reader
@@ -27,7 +28,8 @@ import py_paddle.swig_paddle as api
 
 __all__ = [
     'optimizer', 'layer', 'activation', 'parameters', 'init', 'trainer',
-    'event', 'data_type', 'attr', 'pooling', 'data_feeder', 'dataset', 'reader'
+    'event', 'data_type', 'attr', 'pooling', 'data_feeder', 'dataset', 'reader',
+    'topology'
 ]
 
 

python/paddle/v2/data_feeder.py

@@ -23,7 +23,7 @@ class DataFeeder(DataProviderConverter):
     """
     DataFeeder converts the data returned by paddle.reader into a data structure
     of Arguments which is defined in the API. The paddle.reader usually returns
-    a list of mini-batch data entries. Each data entry in the list is one sampe.
+    a list of mini-batch data entries. Each data entry in the list is one sample.
     Each sample is a list or a tuple with one feature or multiple features.
     DataFeeder converts this mini-batch data entries into Arguments in order
     to feed it to C++ interface.

python/paddle/v2/data_type.py

@@ -13,10 +13,10 @@
 # limitations under the License.
 
 from paddle.trainer.PyDataProvider2 import \
-    InputType, dense_vector, sparse_binary_vector,\
+    InputType, DataType, dense_vector, sparse_binary_vector,\
     sparse_vector, integer_value, integer_value_sequence
 
 __all__ = [
-    'InputType', 'dense_vector', 'sparse_binary_vector', 'sparse_vector',
-    'integer_value', 'integer_value_sequence'
+    'InputType', 'DataType', 'dense_vector', 'sparse_binary_vector',
+    'sparse_vector', 'integer_value', 'integer_value_sequence'
 ]

python/paddle/v2/dataset/cifar.py

 """
-CIFAR Dataset.
-
-URL: https://www.cs.toronto.edu/~kriz/cifar.html
-
-the default train_creator, test_creator used for CIFAR-10 dataset.
+CIFAR dataset: https://www.cs.toronto.edu/~kriz/cifar.html
 """
 import cPickle
 import itertools
-import tarfile
-
 import numpy
+import paddle.v2.dataset.common
+import tarfile
 
-from common import download
-
-__all__ = [
-    'cifar_100_train_creator', 'cifar_100_test_creator', 'train_creator',
-    'test_creator'
-]
+__all__ = ['train100', 'test100', 'train10', 'test10']
 
-CIFAR10_URL = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
+URL_PREFIX = 'https://www.cs.toronto.edu/~kriz/'
+CIFAR10_URL = URL_PREFIX + 'cifar-10-python.tar.gz'
 CIFAR10_MD5 = 'c58f30108f718f92721af3b95e74349a'
-CIFAR100_URL = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
+CIFAR100_URL = URL_PREFIX + 'cifar-100-python.tar.gz'
 CIFAR100_MD5 = 'eb9058c3a382ffc7106e4002c42a8d85'
 
 
-def __read_batch__(filename, sub_name):
-    def reader():
-        def __read_one_batch_impl__(batch):
-            data = batch['data']
-            labels = batch.get('labels', batch.get('fine_labels', None))
-            assert labels is not None
-            for sample, label in itertools.izip(data, labels):
-                yield (sample / 255.0).astype(numpy.float32), int(label)
+def reader_creator(filename, sub_name):
+    def read_batch(batch):
+        data = batch['data']
+        labels = batch.get('labels', batch.get('fine_labels', None))
+        assert labels is not None
+        for sample, label in itertools.izip(data, labels):
+            yield (sample / 255.0).astype(numpy.float32), int(label)
 
+    def reader():
         with tarfile.open(filename, mode='r') as f:
             names = (each_item.name for each_item in f
                      if sub_name in each_item.name)
 
             for name in names:
                 batch = cPickle.load(f.extractfile(name))
-                for item in __read_one_batch_impl__(batch):
+                for item in read_batch(batch):
                     yield item
 
     return reader
 
 
-def cifar_100_train_creator():
-    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
-    return __read_batch__(fn, 'train')
-
-
-def cifar_100_test_creator():
-    fn = download(url=CIFAR100_URL, md5=CIFAR100_MD5)
-    return __read_batch__(fn, 'test')
-
-
-def train_creator():
-    """
-    Default train reader creator. Use CIFAR-10 dataset.
-    """
-    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
-    return __read_batch__(fn, 'data_batch')
+def train100():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR100_URL, 'cifar', CIFAR100_MD5),
+        'train')
 
 
-def test_creator():
-    """
-    Default test reader creator. Use CIFAR-10 dataset.
-    """
-    fn = download(url=CIFAR10_URL, md5=CIFAR10_MD5)
-    return __read_batch__(fn, 'test_batch')
+def test100():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR100_URL, 'cifar', CIFAR100_MD5),
+        'test')
 
 
-def unittest():
-    for _ in train_creator()():
-        pass
-    for _ in test_creator()():
-        pass
+def train10():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR10_URL, 'cifar', CIFAR10_MD5),
+        'data_batch')
 
 
-if __name__ == '__main__':
-    unittest()
+def test10():
+    return reader_creator(
+        paddle.v2.dataset.common.download(CIFAR10_URL, 'cifar', CIFAR10_MD5),
+        'test_batch')

python/paddle/v2/dataset/common.py

@@ -27,7 +27,6 @@ def download(url, module_name, md5sum):
 
     filename = os.path.join(dirname, url.split('/')[-1])
     if not (os.path.exists(filename) and md5file(filename) == md5sum):
-        # If file doesn't exist or MD5 doesn't match, then download.
         r = requests.get(url, stream=True)
         with open(filename, 'w') as f:
             shutil.copyfileobj(r.raw, f)

python/paddle/v2/dataset/mnist.py

+"""
+MNIST dataset.
+"""
 import paddle.v2.dataset.common
 import subprocess
 import numpy
-
+import platform
 __all__ = ['train', 'test']
 
 URL_PREFIX = 'http://yann.lecun.com/exdb/mnist/'
-
 TEST_IMAGE_URL = URL_PREFIX + 't10k-images-idx3-ubyte.gz'
-TEST_IMAGE_MD5 = '25e3cc63507ef6e98d5dc541e8672bb6'
+TEST_IMAGE_MD5 = '9fb629c4189551a2d022fa330f9573f3'
 TEST_LABEL_URL = URL_PREFIX + 't10k-labels-idx1-ubyte.gz'
-TEST_LABEL_MD5 = '4e9511fe019b2189026bd0421ba7b688'
+TEST_LABEL_MD5 = 'ec29112dd5afa0611ce80d1b7f02629c'
 TRAIN_IMAGE_URL = URL_PREFIX + 'train-images-idx3-ubyte.gz'
 TRAIN_IMAGE_MD5 = 'f68b3c2dcbeaaa9fbdd348bbdeb94873'
 TRAIN_LABEL_URL = URL_PREFIX + 'train-labels-idx1-ubyte.gz'
@@ -18,12 +20,19 @@ TRAIN_LABEL_MD5 = 'd53e105ee54ea40749a09fcbcd1e9432'
 
 def reader_creator(image_filename, label_filename, buffer_size):
     def reader():
+        if platform.system() == 'Darwin':
+            zcat_cmd = 'gzcat'
+        elif platform.system() == 'Linux':
+            zcat_cmd = 'zcat'
+        else:
+            raise NotImplementedError()
+
         # According to http://stackoverflow.com/a/38061619/724872, we
         # cannot use standard package gzip here.
-        m = subprocess.Popen(["zcat", image_filename], stdout=subprocess.PIPE)
+        m = subprocess.Popen([zcat_cmd, image_filename], stdout=subprocess.PIPE)
         m.stdout.read(16)  # skip some magic bytes
 
-        l = subprocess.Popen(["zcat", label_filename], stdout=subprocess.PIPE)
+        l = subprocess.Popen([zcat_cmd, label_filename], stdout=subprocess.PIPE)
         l.stdout.read(8)  # skip some magic bytes
 
         while True:
@@ -40,12 +49,12 @@ def reader_creator(image_filename, label_filename, buffer_size):
             images = images / 255.0 * 2.0 - 1.0
 
             for i in xrange(buffer_size):
-                yield images[i, :], labels[i]
+                yield images[i, :], int(labels[i])
 
         m.terminate()
         l.terminate()
 
-    return reader()
+    return reader
 
 
 def train():

python/paddle/v2/dataset/tests/cifar_test.py

+import paddle.v2.dataset.cifar
+import unittest
+
+
+class TestCIFAR(unittest.TestCase):
+    def check_reader(self, reader):
+        sum = 0
+        label = 0
+        for l in reader():
+            self.assertEqual(l[0].size, 3072)
+            if l[1] > label:
+                label = l[1]
+            sum += 1
+        return sum, label
+
+    def test_test10(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.test10())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 9)
+
+    def test_train10(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.train10())
+        self.assertEqual(instances, 50000)
+        self.assertEqual(max_label_value, 9)
+
+    def test_test100(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.test100())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 99)
+
+    def test_train100(self):
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.cifar.train100())
+        self.assertEqual(instances, 50000)
+        self.assertEqual(max_label_value, 99)
+
+
+if __name__ == '__main__':
+    unittest.main()

python/paddle/v2/dataset/tests/mnist_test.py

@@ -5,21 +5,25 @@ import unittest
 class TestMNIST(unittest.TestCase):
     def check_reader(self, reader):
         sum = 0
-        for l in reader:
+        label = 0
+        for l in reader():
             self.assertEqual(l[0].size, 784)
-            self.assertEqual(l[1].size, 1)
-            self.assertLess(l[1], 10)
-            self.assertGreaterEqual(l[1], 0)
+            if l[1] > label:
+                label = l[1]
             sum += 1
-        return sum
+        return sum, label
 
     def test_train(self):
-        self.assertEqual(
-            self.check_reader(paddle.v2.dataset.mnist.train()), 60000)
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.mnist.train())
+        self.assertEqual(instances, 60000)
+        self.assertEqual(max_label_value, 9)
 
     def test_test(self):
-        self.assertEqual(
-            self.check_reader(paddle.v2.dataset.mnist.test()), 10000)
+        instances, max_label_value = self.check_reader(
+            paddle.v2.dataset.mnist.test())
+        self.assertEqual(instances, 10000)
+        self.assertEqual(max_label_value, 9)
 
 
 if __name__ == '__main__':

python/paddle/v2/layer.py

@@ -284,6 +284,7 @@ def mixed(size=0,
     return MixedLayerV2(size, input, name, act, bias_attr, layer_attr)
 
 
+LayerV2 = Layer
 data = DataLayerV2
 AggregateLevel = conf_helps.layers.AggregateLevel
 ExpandLevel = conf_helps.layers.ExpandLevel

python/paddle/v2/parameters.py

 import numpy as np
-from . import layer as v2_layer
 import py_paddle.swig_paddle as api
 from paddle.proto.ParameterConfig_pb2 import ParameterConfig
 
+from topology import Topology
+
 __all__ = ['Parameters', 'create']
 
 
-def create(*layers):
+def create(layers):
     """
-    Create parameter pool by layers. In paddle, layer can be represent a
-    model config.
-
+    Create parameter pool by topology.
     :param layers:
     :return:
     """
-    for layer in layers:
-        if not isinstance(layer, v2_layer.Layer):
-            raise ValueError(
-                'create must pass a topologies which type is paddle.layer.Layer')
-    model_config = v2_layer.parse_network(*layers)
+    topology = Topology(layers)
     pool = Parameters()
-    for param in model_config.parameters:
+    for param in topology.proto().parameters:
         pool.__append_config__(param)
     return pool
 

python/paddle/v2/reader/decorator.py

@@ -201,7 +201,7 @@ def batched(reader, batch_size):
     :return: the batched reader.
     """
 
-    def __impl__():
+    def batched_reader():
         r = reader()
         batch = []
         for instance in r:
@@ -212,4 +212,4 @@ def batched(reader, batch_size):
         if batch:
             yield batch
 
-    return __impl__
+    return batched_reader

python/paddle/v2/tests/CMakeLists.txt

@@ -2,5 +2,11 @@ add_test(NAME test_v2_layer
         COMMAND ${PROJ_ROOT}/paddle/.set_python_path.sh -d ${PROJ_ROOT}/python/
         ${PYTHON_EXECUTABLE} ${PROJ_ROOT}/python/paddle/v2/tests/test_layer.py
         WORKING_DIRECTORY ${PROJ_ROOT}/python/paddle)
+
 add_test(NAME test_v2_api
-    COMMAND bash ${PROJ_ROOT}/python/paddle/v2/tests/run_tests.sh ${PYTHON_EXECUTABLE})
+        COMMAND bash ${PROJ_ROOT}/python/paddle/v2/tests/run_tests.sh ${PYTHON_EXECUTABLE})
+
+add_test(NAME topology_test
+        COMMAND ${PROJ_ROOT}/paddle/.set_python_path.sh -d ${PROJ_ROOT}/python/
+        ${PYTHON_EXECUTABLE} ${PROJ_ROOT}/python/paddle/v2/tests/test_topology.py
+        WORKING_DIRECTORY ${PROJ_ROOT}/python/paddle)

python/paddle/v2/tests/test_topology.py

+# Copyright PaddlePaddle contributors. All Rights Reserved
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import unittest
+import paddle.v2.layer as layer
+import paddle.v2.topology as topology
+import paddle.v2.data_type as data_type
+import paddle.trainer_config_helpers as conf_helps
+
+
+class TestTopology(unittest.TestCase):
+    def test_data_type(self):
+        pixel = layer.data(name='pixel', type=data_type.dense_vector(784))
+        label = layer.data(name='label', type=data_type.integer_value(10))
+        hidden = layer.fc(input=pixel,
+                          size=100,
+                          act=conf_helps.SigmoidActivation())
+        inference = layer.fc(input=hidden,
+                             size=10,
+                             act=conf_helps.SoftmaxActivation())
+        cost = layer.classification_cost(input=inference, label=label)
+        topo = topology.Topology(cost)
+        data_types = topo.data_type()
+        self.assertEqual(len(data_types), 2)
+        pixel_data_type = filter(lambda type: type[0] == "pixel", data_types)
+        self.assertEqual(len(pixel_data_type), 1)
+        pixel_data_type = pixel_data_type[0]
+        self.assertEqual(pixel_data_type[1].type, data_type.DataType.Dense)
+        self.assertEqual(pixel_data_type[1].dim, 784)
+
+        label_data_type = filter(lambda type: type[0] == "label", data_types)
+        self.assertEqual(len(label_data_type), 1)
+        label_data_type = label_data_type[0]
+        self.assertEqual(label_data_type[1].type, data_type.DataType.Index)
+        self.assertEqual(label_data_type[1].dim, 10)
+
+    def test_get_layer(self):
+        pixel = layer.data(name='pixel', type=data_type.dense_vector(784))
+        label = layer.data(name='label', type=data_type.integer_value(10))
+        hidden = layer.fc(input=pixel,
+                          size=100,
+                          act=conf_helps.SigmoidActivation())
+        inference = layer.fc(input=hidden,
+                             size=10,
+                             act=conf_helps.SoftmaxActivation())
+        cost = layer.classification_cost(input=inference, label=label)
+        topo = topology.Topology(cost)
+        pixel_layer = topo.get_layer("pixel")
+        label_layer = topo.get_layer("label")
+        self.assertEqual(pixel_layer, pixel)
+        self.assertEqual(label_layer, label)
+
+    def test_parse(self):
+        pixel = layer.data(name='pixel', type=data_type.dense_vector(784))
+        label = layer.data(name='label', type=data_type.integer_value(10))
+        hidden = layer.fc(input=pixel,
+                          size=100,
+                          act=conf_helps.SigmoidActivation())
+        inference = layer.fc(input=hidden,
+                             size=10,
+                             act=conf_helps.SoftmaxActivation())
+        maxid = layer.max_id(input=inference)
+        cost1 = layer.classification_cost(input=inference, label=label)
+        cost2 = layer.cross_entropy_cost(input=inference, label=label)
+
+        topology.Topology(cost2).proto()
+        topology.Topology([cost1]).proto()
+        topology.Topology([cost1, cost2]).proto()
+        topology.Topology([inference, maxid]).proto()
+
+
+if __name__ == '__main__':
+    unittest.main()

python/paddle/v2/topology.py

+# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import collections
+
+from paddle.proto.ModelConfig_pb2 import ModelConfig
+
+import layer as v2_layer
+
+__all__ = ['Topology']
+
+
+def __bfs_travel__(callback, *layers):
+    for each_layer in layers:
+        __break__ = callback(each_layer)
+        if __break__:
+            return
+        __bfs_travel__(callback, *each_layer.__parent_layers__.values())
+
+
+class Topology(object):
+    """
+    Topology is used to store the information about all layers
+    and network configs.
+    """
+
+    def __init__(self, layers):
+        if not isinstance(layers, collections.Sequence):
+            __check_layer_type__(layers)
+            layers = [layers]
+        for layer in layers:
+            __check_layer_type__(layer)
+        self.layers = layers
+        self.__model_config__ = v2_layer.parse_network(*layers)
+        assert isinstance(self.__model_config__, ModelConfig)
+
+    def proto(self):
+        return self.__model_config__
+
+    def get_layer(self, name):
+        """
+        get v2.Layer Class instance by layer name
+        :param name:
+        :return:
+        """
+        result_layer = [None]
+
+        def __impl__(l):
+            if l.name == name:
+                result_layer[0] = l
+                return True  # break
+            return False
+
+        __bfs_travel__(__impl__, *self.layers)
+        if result_layer[0] is None:
+            raise ValueError("No such layer %s" % name)
+        return result_layer[0]
+
+    def data_layers(self):
+        """
+        get all data layer
+        :return:
+        """
+        data_layers = dict()
+
+        def __impl__(l):
+            if isinstance(l, v2_layer.DataLayerV2):
+                data_layers[l.name] = l
+
+        __bfs_travel__(__impl__, *self.layers)
+        return data_layers
+
+    def data_type(self):
+        """
+        get data_type from proto, such as:
+        [('image', dense_vector(768)), ('label', integer_value(10))]
+        """
+        data_layers = self.data_layers()
+        return [(nm, data_layers[nm].type)
+                for nm in self.proto().input_layer_names]
+
+
+def __check_layer_type__(layer):
+    if not isinstance(layer, v2_layer.LayerV2):
+        raise ValueError('layer should have type paddle.layer.Layer')

python/paddle/v2/trainer.py

 import collections
 
 import py_paddle.swig_paddle as api
-from paddle.proto.ModelConfig_pb2 import ModelConfig
-from data_feeder import DataFeeder
 
+from data_feeder import DataFeeder
+from topology import Topology
 from . import event as v2_event
-from . import layer as v2_layer
 from . import optimizer as v2_optimizer
 from . import parameters as v2_parameters
 
@@ -23,13 +22,6 @@ def default_event_handler(event):
     pass
 
 
-def __bfs_travel_topology__(callback, *topologies):
-    for each_layer in topologies:
-        callback(each_layer)
-        __bfs_travel_topology__(callback,
-                                *each_layer.__parent_layers__.values())
-
-
 class ITrainer(object):
     """
     The interface of Trainer. The only exposed method is `train`.
@@ -50,40 +42,26 @@ class ITrainer(object):
 
 
 class SGD(ITrainer):
-    def __init__(self, topology, parameters, update_equation):
+    def __init__(self, cost, parameters, update_equation):
         """
         Simple SGD Trainer.
 
         :param update_equation: The optimizer object.
         :type update_equation: v2_optimizer.Optimizer
         """
+
         if not isinstance(parameters, v2_parameters.Parameters):
             raise TypeError('parameters should be parameters')
 
         if not isinstance(update_equation, v2_optimizer.Optimizer):
             raise TypeError("update equation parameter must be "
                             "paddle.v2.optimizer.Optimizer")
+        topology = Topology(cost)
         self.__optimizer__ = update_equation
         self.__topology__ = topology
         self.__parameters__ = parameters
-        self.__topology_in_proto__ = v2_layer.parse_network(topology)
-        data_types = dict()
-
-        def __travel__(l):
-            if hasattr(l, 'type'):
-                data_types[l.name] = l.type
-
-        if not isinstance(topology, collections.Sequence):
-            topology = [topology]
-        __bfs_travel_topology__(__travel__, *topology)
-        self.__data_types__ = [
-            (iname, data_types[iname])
-            for iname in self.__topology_in_proto__.input_layer_names
-        ]
-
-        if not isinstance(self.__topology_in_proto__, ModelConfig):
-            raise TypeError('topology should be a model config')
-
+        self.__topology_in_proto__ = topology.proto()
+        self.__data_types__ = topology.data_type()
         gm = api.GradientMachine.createFromConfigProto(
             self.__topology_in_proto__, api.CREATE_MODE_NORMAL,
             self.__optimizer__.enable_types())
@@ -103,7 +81,6 @@ class SGD(ITrainer):
         :param event_handler: Event handler. A method will be invoked when event
                               occurred.
         :type event_handler: (BaseEvent) => None
-        :param data_types: Not important, will be removed after data refactor.
         :return:
         """
         if event_handler is None:
@@ -113,6 +90,7 @@ class SGD(ITrainer):
             reader_dict = self.default_reader_dict()
 
         __check_train_args__(**locals())
+
         updater = self.__optimizer__.create_local_updater()
         updater.init(self.__gradient_machine__)
 
@@ -192,6 +170,5 @@ def __check_train_args__(reader, event_handler, **kwargs):
     if not callable(reader) or not isinstance(reader(), collections.Iterator):
         raise TypeError('train_data_reader should be a function, '
                         'which can return a iterator')
-
     if not callable(event_handler):
         raise TypeError('event handler should be a function')

python/setup.py.in

@@ -15,9 +15,5 @@ setup(name='paddle',
       packages=packages,
       package_dir={
           '': '${CMAKE_CURRENT_SOURCE_DIR}'
-      },
-      install_requires = [
-          'scikit-learn>=0.18.0',
-          'scipy>=0.18.0',
-      ]
+      }
 )