Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into srl_api_v2

python/paddle/trainer_config_helpers/default_decorators.py

@@ -52,6 +52,10 @@ def wrap_param_default(param_names=None,
                     kwargs[name] = default_factory(func)
             return func(*args, **kwargs)
 
+        if hasattr(func, 'argspec'):
+            __wrapper__.argspec = func.argspec
+        else:
+            __wrapper__.argspec = inspect.getargspec(func)
         return __wrapper__
 
     return __impl__

python/paddle/trainer_config_helpers/layers.py

@@ -14,6 +14,7 @@
 
 import functools
 import collections
+import inspect
 
 from paddle.trainer.config_parser import *
 from .activations import LinearActivation, SigmoidActivation, TanhActivation, \
@@ -316,6 +317,11 @@ def layer_support(*attrs):
                     val.check(method.__name__)
             return method(*args, **kwargs)
 
+        if hasattr(method, 'argspec'):
+            wrapper.argspec = method.argspec
+        else:
+            wrapper.argspec = inspect.getargspec(method)
+
         return wrapper
 
     return decorator

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 config 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

+import requests
+import hashlib
+import os
+import shutil
+
+__all__ = ['DATA_HOME', 'download', 'md5file']
+
+DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset')
+
+if not os.path.exists(DATA_HOME):
+    os.makedirs(DATA_HOME)
+
+
+def md5file(fname):
+    hash_md5 = hashlib.md5()
+    f = open(fname, "rb")
+    for chunk in iter(lambda: f.read(4096), b""):
+        hash_md5.update(chunk)
+    f.close()
+    return hash_md5.hexdigest()
+
+
+def download(url, module_name, md5sum):
+    dirname = os.path.join(DATA_HOME, module_name)
+    if not os.path.exists(dirname):
+        os.makedirs(dirname)
+
+    filename = os.path.join(dirname, url.split('/')[-1])
+    if not (os.path.exists(filename) and md5file(filename) == md5sum):
+        r = requests.get(url, stream=True)
+        with open(filename, 'w') as f:
+            shutil.copyfileobj(r.raw, f)
+
+    return filename

python/paddle/v2/dataset/config.py

-import hashlib
-import os
-import shutil
-import urllib2
-
-__all__ = ['DATA_HOME', 'download']
-
-DATA_HOME = os.path.expanduser('~/.cache/paddle_data_set')
-
-if not os.path.exists(DATA_HOME):
-    os.makedirs(DATA_HOME)
-
-
-def download(url, md5):
-    filename = os.path.split(url)[-1]
-    assert DATA_HOME is not None
-    filepath = os.path.join(DATA_HOME, md5)
-    if not os.path.exists(filepath):
-        os.makedirs(filepath)
-    __full_file__ = os.path.join(filepath, filename)
-
-    def __file_ok__():
-        if not os.path.exists(__full_file__):
-            return False
-        md5_hash = hashlib.md5()
-        with open(__full_file__, 'rb') as f:
-            for chunk in iter(lambda: f.read(4096), b""):
-                md5_hash.update(chunk)
-
-        return md5_hash.hexdigest() == md5
-
-    while not __file_ok__():
-        response = urllib2.urlopen(url)
-        with open(__full_file__, mode='wb') as of:
-            shutil.copyfileobj(fsrc=response, fdst=of)
-    return __full_file__

python/paddle/v2/dataset/mnist.py

-import sklearn.datasets.mldata
-import sklearn.model_selection
+"""
+MNIST dataset.
+"""
 import numpy
-from config import DATA_HOME
+import paddle.v2.dataset.common
+import subprocess
 
-__all__ = ['train_creator', 'test_creator']
+__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_LABEL_URL = URL_PREFIX + 't10k-labels-idx1-ubyte.gz'
+TEST_LABEL_MD5 = '4e9511fe019b2189026bd0421ba7b688'
+TRAIN_IMAGE_URL = URL_PREFIX + 'train-images-idx3-ubyte.gz'
+TRAIN_IMAGE_MD5 = 'f68b3c2dcbeaaa9fbdd348bbdeb94873'
+TRAIN_LABEL_URL = URL_PREFIX + 'train-labels-idx1-ubyte.gz'
+TRAIN_LABEL_MD5 = 'd53e105ee54ea40749a09fcbcd1e9432'
 
-def __mnist_reader_creator__(data, target):
+
+def reader_creator(image_filename, label_filename, buffer_size):
     def reader():
-        n_samples = data.shape[0]
-        for i in xrange(n_samples):
-            yield (data[i] / 255.0).astype(numpy.float32), int(target[i])
+        # 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.stdout.read(16)  # skip some magic bytes
 
-    return reader
+        l = subprocess.Popen(["zcat", label_filename], stdout=subprocess.PIPE)
+        l.stdout.read(8)  # skip some magic bytes
 
+        while True:
+            labels = numpy.fromfile(
+                l.stdout, 'ubyte', count=buffer_size).astype("int")
 
-TEST_SIZE = 10000
+            if labels.size != buffer_size:
+                break  # numpy.fromfile returns empty slice after EOF.
 
-data = sklearn.datasets.mldata.fetch_mldata(
-    "MNIST original", data_home=DATA_HOME)
-X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
-    data.data, data.target, test_size=TEST_SIZE, random_state=0)
+            images = numpy.fromfile(
+                m.stdout, 'ubyte', count=buffer_size * 28 * 28).reshape(
+                    (buffer_size, 28 * 28)).astype('float32')
 
+            images = images / 255.0 * 2.0 - 1.0
 
-def train_creator():
-    return __mnist_reader_creator__(X_train, y_train)
+            for i in xrange(buffer_size):
+                yield images[i, :], int(labels[i])
 
+        m.terminate()
+        l.terminate()
 
-def test_creator():
-    return __mnist_reader_creator__(X_test, y_test)
+    return reader
 
 
-def unittest():
-    assert len(list(test_creator()())) == TEST_SIZE
+def train():
+    return reader_creator(
+        paddle.v2.dataset.common.download(TRAIN_IMAGE_URL, 'mnist',
+                                          TRAIN_IMAGE_MD5),
+        paddle.v2.dataset.common.download(TRAIN_LABEL_URL, 'mnist',
+                                          TRAIN_LABEL_MD5), 100)
 
 
-if __name__ == '__main__':
-    unittest()
+def test():
+    return reader_creator(
+        paddle.v2.dataset.common.download(TEST_IMAGE_URL, 'mnist',
+                                          TEST_IMAGE_MD5),
+        paddle.v2.dataset.common.download(TEST_LABEL_URL, 'mnist',
+                                          TEST_LABEL_MD5), 100)

python/paddle/v2/dataset/movielens.py

 import zipfile
-from config import download
+from common import download
 import re
 import random
 import functools

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/common_test.py

+import paddle.v2.dataset.common
+import unittest
+import tempfile
+
+
+class TestCommon(unittest.TestCase):
+    def test_md5file(self):
+        _, temp_path = tempfile.mkstemp()
+        with open(temp_path, 'w') as f:
+            f.write("Hello\n")
+        self.assertEqual('09f7e02f1290be211da707a266f153b3',
+                         paddle.v2.dataset.common.md5file(temp_path))
+
+    def test_download(self):
+        yi_avatar = 'https://avatars0.githubusercontent.com/u/1548775?v=3&s=460'
+        self.assertEqual(
+            paddle.v2.dataset.common.DATA_HOME + '/test/1548775?v=3&s=460',
+            paddle.v2.dataset.common.download(
+                yi_avatar, 'test', 'f75287202d6622414c706c36c16f8e0d'))
+
+
+if __name__ == '__main__':
+    unittest.main()

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

+import paddle.v2.dataset.mnist
+import unittest
+
+
+class TestMNIST(unittest.TestCase):
+    def check_reader(self, reader):
+        sum = 0
+        label = 0
+        for l in reader():
+            self.assertEqual(l[0].size, 784)
+            if l[1] > label:
+                label = l[1]
+            sum += 1
+        return sum, label
+
+    def test_train(self):
+        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):
+        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__':
+    unittest.main()

python/paddle/v2/layer.py

@@ -67,6 +67,7 @@ paddle.v2.parameters.create, no longer exposed to users.
 """
 
 import collections
+import inspect
 
 import paddle.trainer_config_helpers as conf_helps
 from paddle.trainer_config_helpers.config_parser_utils import \
@@ -74,26 +75,14 @@ from paddle.trainer_config_helpers.config_parser_utils import \
 
 from paddle.trainer_config_helpers.default_decorators import wrap_name_default
 from paddle.trainer_config_helpers.default_decorators import wrap_act_default
-from paddle.trainer_config_helpers.default_decorators import wrap_bias_attr_default
+from paddle.trainer_config_helpers.default_decorators import \
+    wrap_bias_attr_default
 from paddle.trainer_config_helpers.layers import layer_support
 
 import data_type
 import activation
-import attr
-
-__all__ = [
-    'parse_network', 'data', 'fc', 'conv_shift', 'img_conv', 'img_pool', 'spp',
-    'maxout', 'img_cmrnorm', 'batch_norm', 'sum_to_one_norm', 'recurrent',
-    'lstmemory', 'grumemory', 'pool', 'last_seq', 'first_seq', 'concat',
-    'seq_concat', 'block_expand', 'expand', 'repeat', 'seq_reshape', 'addto',
-    'linear_comb', 'interpolation', 'bilinear_interp', 'power', 'scaling',
-    'slope_intercept', 'tensor', 'cos_sim', 'trans', 'max_id', 'sampling_id',
-    'pad', 'classification_cost', 'cross_entropy_cost',
-    'cross_entropy_with_selfnorm_cost', 'regression_cost',
-    'multi_binary_label_cross_entropy_cost', 'rank_cost', 'lambda_cost',
-    'sum_cost', 'huber_cost', 'crf', 'crf_decoding', 'ctc', 'warp_ctc', 'nce',
-    'hsigmoid', 'eos'
-]
+
+__all__ = ['parse_network', 'data']
 
 __projection_names__ = filter(lambda x: x.endswith('_projection'),
                               dir(conf_helps))
@@ -289,83 +278,51 @@ data = DataLayerV2
 AggregateLevel = conf_helps.layers.AggregateLevel
 ExpandLevel = conf_helps.layers.ExpandLevel
 
-layer_list = [
-    # [V2LayerImpl, V1_method_name, parent_names]
-    # fully connected layers
-    ['fc', 'fc_layer', ['input']],
-    # conv layers
-    ['conv_shift', 'conv_shift_layer', ['a', 'b']],
-    ['img_conv', 'img_conv_layer', ['input']],
-    # image pooling layers
-    ['img_pool', 'img_pool_layer', ['input']],
-    ['spp', 'spp_layer', ['input']],
-    ['maxout', 'maxout_layer', ['input']],
-    # norm layers
-    ['img_cmrnorm', 'img_cmrnorm_layer', ['input']],
-    ['batch_norm', 'batch_norm_layer', ['input']],
-    ['sum_to_one_norm', 'sum_to_one_norm_layer', ['input']],
-    # recurrent layers
-    ['recurrent', 'recurrent_layer', ['input']],
-    ['lstmemory', 'lstmemory', ['input']],
-    ['grumemory', 'grumemory', ['input']],
-    # aggregate layers
-    ['pool', 'pooling_layer', ['input']],
-    ['last_seq', 'last_seq', ['input']],
-    ['first_seq', 'first_seq', ['input']],
-    ['concat', 'concat_layer', ['input']],
-    ['seq_concat', 'seq_concat_layer', ['a', 'b']],
-    # reshaping layers
-    ['block_expand', 'block_expand_layer', ['input']],
-    ['expand', 'expand_layer', ['input', 'expand_as']],
-    ['repeat', 'repeat_layer', ['input']],
-    ['rotate', 'rotate_layer', ['input']],
-    ['seq_reshape', 'seq_reshape_layer', ['input']],
-    # math layers
-    ['addto', 'addto_layer', ['input']],
-    ['linear_comb', 'linear_comb_layer', ['weights', 'vectors']],
-    ['interpolation', 'interpolation_layer', ['input', 'weight']],
-    ['bilinear_interp', 'bilinear_interp_layer', ['input']],
-    ['power', 'power_layer', ['input', 'weight']],
-    ['scaling', 'scaling_layer', ['input', 'weight']],
-    ['slope_intercept', 'slope_intercept_layer', ['input']],
-    ['tensor', 'tensor_layer', ['a', 'b']],
-    ['cos_sim', 'cos_sim', ['a', 'b']],
-    ['trans', 'trans_layer', ['input']],
-    # sampling layers
-    ['max_id', 'maxid_layer', ['input']],
-    ['sampling_id', 'sampling_id_layer', ['input']],
-    # slicing and joining layers
-    ['pad', 'pad_layer', ['input']],
-    # cost layers
-    [
-        'classification_cost', 'classification_cost',
-        ['input', 'label', 'weight']
-    ],
-    ['regression_cost', 'regression_cost', ['input', 'label', 'weight']],
-    ['cross_entropy_cost', 'cross_entropy', ['input', 'label']],
-    [
-        'cross_entropy_with_selfnorm_cost', 'cross_entropy_with_selfnorm',
-        ['input', 'label']
-    ],
-    [
-        'multi_binary_label_cross_entropy_cost',
-        'multi_binary_label_cross_entropy', ['input', 'label']
-    ],
-    ['rank_cost', 'rank_cost', ['left', 'right', 'label', 'weight']],
-    ['lambda_cost', 'lambda_cost', ['input', 'score']],
-    ['sum_cost', 'sum_cost', ['input']],
-    ['huber_cost', 'huber_cost', ['input', 'label']],
-    ['crf', 'crf_layer', ['input', 'label']],
-    ['crf_decoding', 'crf_decoding_layer', ['input']],
-    ['ctc', 'ctc_layer', ['input', 'label']],
-    ['warp_ctc', 'warp_ctc_layer', ['input', 'label']],
-    ['nce', 'nce_layer', ['input', 'label']],
-    ['hsigmoid', 'hsigmoid', ['input', 'label']],
-    # check layers
-    ['eos', 'eos_layer', ['input']]
-]
-for l in layer_list:
-    globals()[l[0]] = __convert_to_v2__(l[1], l[2])
+
+def __layer_name_mapping__(inname):
+    if inname in ['data_layer', 'memory', 'mixed_layer']:
+        # Do Not handle these layers
+        return
+    elif inname == 'maxid_layer':
+        return 'max_id'
+    elif inname.endswith('memory') or inname.endswith(
+            '_seq') or inname.endswith('_sim') or inname == 'hsigmoid':
+        return inname
+    elif inname in [
+            'cross_entropy', 'multi_binary_label_cross_entropy',
+            'cross_entropy_with_selfnorm'
+    ]:
+        return inname + "_cost"
+    elif inname.endswith('_cost'):
+        return inname
+    elif inname.endswith("_layer"):
+        return inname[:-len("_layer")]
+
+
+def __layer_name_mapping_parent_names__(inname):
+    all_args = getattr(conf_helps, inname).argspec.args
+    return filter(
+        lambda x: x in ['input1', 'input2','label', 'input', 'a', 'b', 'expand_as',
+                        'weights', 'vectors', 'weight', 'score', 'left', 'right'],
+        all_args)
+
+
+def __convert_layer__(_new_name_, _old_name_, _parent_names_):
+    global __all__
+    __all__.append(_new_name_)
+    globals()[new_name] = __convert_to_v2__(_old_name_, _parent_names_)
+
+
+for each_layer_name in dir(conf_helps):
+    new_name = __layer_name_mapping__(each_layer_name)
+    if new_name is not None:
+        parent_names = __layer_name_mapping_parent_names__(each_layer_name)
+        assert len(parent_names) != 0, each_layer_name
+        __convert_layer__(new_name, each_layer_name, parent_names)
+
+del parent_names
+del new_name
+del each_layer_name
 
 # convert projection
 for prj in __projection_names__:

python/paddle/v2/tests/test_layer.py

@@ -11,17 +11,13 @@
 # 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 difflib
 import unittest
 
-import paddle.trainer_config_helpers as conf_helps
 import paddle.v2.activation as activation
 import paddle.v2.attr as attr
 import paddle.v2.data_type as data_type
 import paddle.v2.layer as layer
 import paddle.v2.pooling as pooling
-from paddle.trainer_config_helpers.config_parser_utils import \
-    parse_network_config as parse_network
 
 pixel = layer.data(name='pixel', type=data_type.dense_vector(128))
 label = layer.data(name='label', type=data_type.integer_value(10))
@@ -70,7 +66,7 @@ class ImageLayerTest(unittest.TestCase):
 
 class AggregateLayerTest(unittest.TestCase):
     def test_aggregate_layer(self):
-        pool = layer.pool(
+        pool = layer.pooling(
             input=pixel,
             pooling_type=pooling.Avg(),
             agg_level=layer.AggregateLevel.EACH_SEQUENCE)