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

… fit_a_line

python/paddle/v2/__init__.py

@@ -20,6 +20,7 @@
 import data_type
 import topology
 import data_feeder
+import networks
 from . import dataset
 from . import reader
 import attr

python/paddle/v2/config_base.py

@@ -22,6 +22,7 @@ class Layer(object):
     def __init__(self, name=None, parent_layers=None):
         assert isinstance(parent_layers, dict)
         self.name = name
+        self.__contex__ = {}
         self.__parent_layers__ = parent_layers
 
     def to_proto(self, context):
@@ -39,16 +40,38 @@ def to_proto(self, context):
                                self.__parent_layers__[layer_name])
             kwargs[layer_name] = v1_layer
 
-        if self.name is None:
+        if self.context_name() is None:
             return self.to_proto_impl(**kwargs)
-        elif self.name not in context:
-            context[self.name] = self.to_proto_impl(**kwargs)
-
-        return context[self.name]
+        elif self.context_name() not in context:
+            context[self.context_name()] = self.to_proto_impl(**kwargs)
+        self.__contex__ = context
+        if self.use_context_name():
+            return context[self.context_name()]
+        else:
+            return context[self.name]
 
     def to_proto_impl(self, **kwargs):
         raise NotImplementedError()
 
+    def context_name(self):
+        """
+        Context name means the context which stores `to_proto_impl` result.
+        If multiple layer share same context_name, the `to_proto_impl` of them
+        will be invoked only once.
+        """
+        return self.name
+
+    def use_context_name(self):
+        return False
+
+    def calculate_size(self):
+        """
+        lazy calculate size of the layer, should be called when to_proto_impl of
+        this layer is called.
+        :return:
+        """
+        return self.__contex__[self.context_name()].size
+
 
 def __convert_to_v2__(method_name, parent_names, is_default_name=True):
     if is_default_name:

python/paddle/v2/dataset/__init__.py

@@ -1,3 +1,17 @@
+# 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 mnist
 import imikolov
 import imdb

python/paddle/v2/dataset/cifar.py

@@ -1,6 +1,20 @@
+# 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.
 """
 CIFAR dataset: https://www.cs.toronto.edu/~kriz/cifar.html
 """
+
 import cPickle
 import itertools
 import numpy

python/paddle/v2/dataset/common.py

@@ -1,3 +1,17 @@
+# 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 requests
 import hashlib
 import os

python/paddle/v2/dataset/conll05.py

@@ -0,0 +1,205 @@
+# 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 paddle.v2.dataset.common
+import tarfile
+import gzip
+import itertools
+
+__all__ = ['test, get_dict', 'get_embedding']
+"""
+Conll 2005 dataset.  Paddle semantic role labeling Book and demo use this
+dataset as an example. Because Conll 2005 is not free in public, the default
+downloaded URL is test set of Conll 2005 (which is public). Users can change
+URL and MD5 to their Conll dataset.
+"""
+
+DATA_URL = 'http://www.cs.upc.edu/~srlconll/conll05st-tests.tar.gz'
+DATA_MD5 = '387719152ae52d60422c016e92a742fc'
+WORDDICT_URL = 'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/wordDict.txt'
+WORDDICT_MD5 = 'ea7fb7d4c75cc6254716f0177a506baa'
+VERBDICT_URL = 'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/verbDict.txt'
+VERBDICT_MD5 = '0d2977293bbb6cbefab5b0f97db1e77c'
+TRGDICT_URL = 'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/targetDict.txt'
+TRGDICT_MD5 = 'd8c7f03ceb5fc2e5a0fa7503a4353751'
+EMB_URL = 'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/emb'
+EMB_MD5 = 'bf436eb0faa1f6f9103017f8be57cdb7'
+
+UNK_IDX = 0
+
+
+def load_dict(filename):
+    d = dict()
+    with open(filename, 'r') as f:
+        for i, line in enumerate(f):
+            d[line.strip()] = i
+    return d
+
+
+def corpus_reader(data_path, words_name, props_name):
+    """
+    Read one corpus. It returns an iterator. Each element of
+    this iterator is a tuple including sentence and labels. The sentence is
+    consist of a list of word IDs. The labels include a list of label IDs.
+    :return: a iterator of data.
+    :rtype: iterator
+    """
+
+    def reader():
+        tf = tarfile.open(data_path)
+        wf = tf.extractfile(words_name)
+        pf = tf.extractfile(props_name)
+        with gzip.GzipFile(fileobj=wf) as words_file, gzip.GzipFile(
+                fileobj=pf) as props_file:
+            sentences = []
+            labels = []
+            one_seg = []
+            for word, label in itertools.izip(words_file, props_file):
+                word = word.strip()
+                label = label.strip().split()
+
+                if len(label) == 0:  # end of sentence
+                    for i in xrange(len(one_seg[0])):
+                        a_kind_lable = [x[i] for x in one_seg]
+                        labels.append(a_kind_lable)
+
+                    if len(labels) >= 1:
+                        verb_list = []
+                        for x in labels[0]:
+                            if x != '-':
+                                verb_list.append(x)
+
+                        for i, lbl in enumerate(labels[1:]):
+                            cur_tag = 'O'
+                            is_in_bracket = False
+                            lbl_seq = []
+                            verb_word = ''
+                            for l in lbl:
+                                if l == '*' and is_in_bracket == False:
+                                    lbl_seq.append('O')
+                                elif l == '*' and is_in_bracket == True:
+                                    lbl_seq.append('I-' + cur_tag)
+                                elif l == '*)':
+                                    lbl_seq.append('I-' + cur_tag)
+                                    is_in_bracket = False
+                                elif l.find('(') != -1 and l.find(')') != -1:
+                                    cur_tag = l[1:l.find('*')]
+                                    lbl_seq.append('B-' + cur_tag)
+                                    is_in_bracket = False
+                                elif l.find('(') != -1 and l.find(')') == -1:
+                                    cur_tag = l[1:l.find('*')]
+                                    lbl_seq.append('B-' + cur_tag)
+                                    is_in_bracket = True
+                                else:
+                                    raise RuntimeError('Unexpected label: %s' %
+                                                       l)
+
+                            yield sentences, verb_list[i], lbl_seq
+
+                    sentences = []
+                    labels = []
+                    one_seg = []
+                else:
+                    sentences.append(word)
+                    one_seg.append(label)
+
+        pf.close()
+        wf.close()
+        tf.close()
+
+    return reader
+
+
+def reader_creator(corpus_reader,
+                   word_dict=None,
+                   predicate_dict=None,
+                   label_dict=None):
+    def reader():
+        for sentence, predicate, labels in corpus_reader():
+
+            sen_len = len(sentence)
+
+            verb_index = labels.index('B-V')
+            mark = [0] * len(labels)
+            if verb_index > 0:
+                mark[verb_index - 1] = 1
+                ctx_n1 = sentence[verb_index - 1]
+            else:
+                ctx_n1 = 'bos'
+
+            if verb_index > 1:
+                mark[verb_index - 2] = 1
+                ctx_n2 = sentence[verb_index - 2]
+            else:
+                ctx_n2 = 'bos'
+
+            mark[verb_index] = 1
+            ctx_0 = sentence[verb_index]
+
+            if verb_index < len(labels) - 1:
+                mark[verb_index + 1] = 1
+                ctx_p1 = sentence[verb_index + 1]
+            else:
+                ctx_p1 = 'eos'
+
+            if verb_index < len(labels) - 2:
+                mark[verb_index + 2] = 1
+                ctx_p2 = sentence[verb_index + 2]
+            else:
+                ctx_p2 = 'eos'
+
+            word_idx = [word_dict.get(w, UNK_IDX) for w in sentence]
+            pred_idx = [predicate_dict.get(predicate)] * sen_len
+
+            ctx_n2_idx = [word_dict.get(ctx_n2, UNK_IDX)] * sen_len
+            ctx_n1_idx = [word_dict.get(ctx_n1, UNK_IDX)] * sen_len
+            ctx_0_idx = [word_dict.get(ctx_0, UNK_IDX)] * sen_len
+            ctx_p1_idx = [word_dict.get(ctx_p1, UNK_IDX)] * sen_len
+            ctx_p2_idx = [word_dict.get(ctx_p2, UNK_IDX)] * sen_len
+
+            label_idx = [label_dict.get(w) for w in labels]
+
+            yield word_idx, pred_idx, ctx_n2_idx, ctx_n1_idx, \
+              ctx_0_idx, ctx_p1_idx, ctx_p2_idx, mark, label_idx
+
+    return reader()
+
+
+def get_dict():
+    word_dict = load_dict(
+        common.download(WORDDICT_URL, 'conll05st', WORDDICT_MD5))
+    verb_dict = load_dict(
+        common.download(VERBDICT_URL, 'conll05st', VERBDICT_MD5))
+    label_dict = load_dict(
+        common.download(TRGDICT_URL, 'conll05st', TRGDICT_MD5))
+    return word_dict, verb_dict, label_dict
+
+
+def get_embedding():
+    return common.download(EMB_URL, 'conll05st', EMB_MD5)
+
+
+def test():
+    word_dict, verb_dict, label_dict = get_dict()
+    reader = corpus_reader(
+        common.download(DATA_URL, 'conll05st', DATA_MD5),
+        words_name='conll05st-release/test.wsj/words/test.wsj.words.gz',
+        props_name='conll05st-release/test.wsj/props/test.wsj.props.gz')
+    return reader_creator(reader, word_dict, verb_dict, label_dict)
+
+
+if __name__ == '__main__':
+    print get_embedding()
+    for f in test():
+        print f

python/paddle/v2/dataset/imdb.py

@@ -1,6 +1,3 @@
-# /usr/bin/env python
-# -*- coding:utf-8 -*-
-
 # Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -17,6 +14,7 @@
 """
 IMDB dataset: http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz
 """
+
 import paddle.v2.dataset.common
 import tarfile
 import Queue

python/paddle/v2/dataset/imikolov.py

@@ -1,3 +1,16 @@
+# 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.
 """
 imikolov's simple dataset: http://www.fit.vutbr.cz/~imikolov/rnnlm/
 """

python/paddle/v2/dataset/mnist.py

@@ -1,3 +1,16 @@
+# 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.
 """
 MNIST dataset.
 """

python/paddle/v2/dataset/movielens.py

@@ -1,3 +1,17 @@
+# 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 zipfile
 from common import download
 import re