merge develop, fix conflict

avx_docs
Luo Tao 9 years ago
commit 96615fe329

@ -7,18 +7,14 @@
hooks:
- id: yapf
- repo: https://github.com/pre-commit/pre-commit-hooks
sha: 4ef03c4223ad322c7adaa6c6c0efb26b57df3b71
sha: 7539d8bd1a00a3c1bfd34cdb606d3a6372e83469
hooks:
- id: check-added-large-files
- id: check-merge-conflict
- id: check-symlinks
- id: detect-private-key
- id: end-of-file-fixer
# TODO(yuyang): trailing whitespace has some bugs on markdown
# files now, please not add it to pre-commit hook now
# - id: trailing-whitespace
#
# TODO(yuyang): debug-statements not fit for Paddle, because
# not all of our python code is runnable. Some are used for
# documenation
# - id: debug-statements
- repo: https://github.com/PaddlePaddle/clang-format-pre-commit-hook.git
sha: 28c0ea8a67a3e2dbbf4822ef44e85b63a0080a29
hooks:
- id: clang-formater

@ -42,7 +42,7 @@ addons:
before_install:
- |
if [ ${JOB} == "BUILD_AND_TEST" ]; then
if ! git diff --name-only $TRAVIS_COMMIT_RANGE | grep -qvE '(\.md$)'
if ! git diff --name-only $TRAVIS_COMMIT_RANGE | grep -qvE '(\.md$)|(\.rst$)|(\.jpg$)|(\.png$)'
then
echo "Only markdown docs were updated, stopping build process."
exit

@ -2,8 +2,8 @@ cmake_minimum_required(VERSION 2.8)
project(paddle CXX C)
set(PADDLE_MAJOR_VERSION 0)
set(PADDLE_MINOR_VERSION 8)
set(PADDLE_PATCH_VERSION 0b3)
set(PADDLE_MINOR_VERSION 9)
set(PADDLE_PATCH_VERSION 0a0)
set(PADDLE_VERSION ${PADDLE_MAJOR_VERSION}.${PADDLE_MINOR_VERSION}.${PADDLE_PATCH_VERSION})
set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${CMAKE_SOURCE_DIR}/cmake")
@ -36,6 +36,7 @@ option(WITH_RDMA "Compile PaddlePaddle with rdma support" OFF)
option(WITH_GLOG "Compile PaddlePaddle use glog, otherwise use a log implement internally" ${LIBGLOG_FOUND})
option(WITH_GFLAGS "Compile PaddlePaddle use gflags, otherwise use a flag implement internally" ${GFLAGS_FOUND})
option(WITH_TIMER "Compile PaddlePaddle use timer" OFF)
option(WITH_PROFILER "Compile PaddlePaddle use gpu profiler" OFF)
option(WITH_TESTING "Compile and run unittest for PaddlePaddle" ${GTEST_FOUND})
option(WITH_DOC "Compile PaddlePaddle with documentation" OFF)
option(WITH_SWIG_PY "Compile PaddlePaddle with py PaddlePaddle prediction api" ${SWIG_FOUND})
@ -115,7 +116,6 @@ else()
endif(WITH_AVX)
if(WITH_DSO)
set(CUDA_LIBRARIES "")
add_definitions(-DPADDLE_USE_DSO)
endif(WITH_DSO)
@ -135,6 +135,10 @@ if(NOT WITH_TIMER)
add_definitions(-DPADDLE_DISABLE_TIMER)
endif(NOT WITH_TIMER)
if(NOT WITH_PROFILER)
add_definitions(-DPADDLE_DISABLE_PROFILER)
endif(NOT WITH_PROFILER)
if(WITH_AVX)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${AVX_FLAG}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${AVX_FLAG}")

@ -1,10 +1,13 @@
# PaddlePaddle
[![Build Status](https://travis-ci.org/baidu/Paddle.svg?branch=master)](https://travis-ci.org/baidu/Paddle)
[![Coverage Status](https://coveralls.io/repos/github/baidu/Paddle/badge.svg?branch=develop)](https://coveralls.io/github/baidu/Paddle?branch=develop)
[![Join the chat at https://gitter.im/PaddlePaddle/Deep_Learning](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/PaddlePaddle/Deep_Learning?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
[![Build Status](https://travis-ci.org/PaddlePaddle/Paddle.svg?branch=develop)](https://travis-ci.org/PaddlePaddle/Paddle)
[![Documentation Status](https://img.shields.io/badge/docs-latest-brightgreen.svg?style=flat)](http://www.paddlepaddle.org/)
[![Documentation Status](https://img.shields.io/badge/中文文档-最新-brightgreen.svg)](http://www.paddlepaddle.org/cn/index.html)
[![Coverage Status](https://coveralls.io/repos/github/PaddlePaddle/Paddle/badge.svg?branch=develop)](https://coveralls.io/github/PaddlePaddle/Paddle?branch=develop)
[![Release](https://img.shields.io/github/release/PaddlePaddle/Paddle.svg)](https://github.com/PaddlePaddle/Paddle/releases)
[![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)
Welcome to the PaddlePaddle GitHub.
@ -14,7 +17,7 @@ developed by Baidu scientists and engineers for the purpose of applying deep
learning to many products at Baidu.
Our vision is to enable deep learning for everyone via PaddlePaddle.
Please refer to our [release announcement](https://github.com/baidu/Paddle/releases) to track the latest feature of PaddlePaddle.
Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddle/releases) to track the latest feature of PaddlePaddle.
## Features
@ -26,15 +29,15 @@ Please refer to our [release announcement](https://github.com/baidu/Paddle/relea
connection.
- **Efficiency**
In order to unleash the power of heterogeneous computing resource,
optimization occurs at different levels of PaddlePaddle, including
computing, memory, architecture and communication. The following are some
examples:
- Optimized math operations through SSE/AVX intrinsics, BLAS libraries
(e.g. MKL, ATLAS, cuBLAS) or customized CPU/GPU kernels.
- Highly optimized recurrent networks which can handle **variable-length**
(e.g. MKL, ATLAS, cuBLAS) or customized CPU/GPU kernels.
- Highly optimized recurrent networks which can handle **variable-length**
sequence without padding.
- Optimized local and distributed training for models with high dimensional
sparse data.
@ -57,41 +60,39 @@ Please refer to our [release announcement](https://github.com/baidu/Paddle/relea
## Installation
Check out the [Install Guide](http://paddlepaddle.org/doc/build/) to install from
pre-built packages (**docker image**, **deb package**) or
pre-built packages (**docker image**, **deb package**) or
directly build on **Linux** and **Mac OS X** from the source code.
## Documentation
Both [English Docs](http://paddlepaddle.org/doc/) and [Chinese Docs](http://paddlepaddle.org/doc_cn/) are provided for our users and developers.
- [Quick Start](http://paddlepaddle.org/doc/demo/quick_start/index_en) <br>
You can follow the quick start tutorial to learn how use PaddlePaddle
step-by-step.
- [Example and Demo](http://paddlepaddle.org/doc/demo/) <br>
We provide five demos, including: image classification, sentiment analysis,
sequence to sequence model, recommendation, semantic role labeling.
sequence to sequence model, recommendation, semantic role labeling.
- [Distributed Training](http://paddlepaddle.org/doc/cluster) <br>
This system supports training deep learning models on multiple machines
with data parallelism.
- [Python API](http://paddlepaddle.org/doc/ui/) <br>
PaddlePaddle supports using either Python interface or C++ to build your
system. We also use SWIG to wrap C++ source code to create a user friendly
interface for Python. You can also use SWIG to create interface for your
favorite programming language.
- [How to Contribute](http://paddlepaddle.org/doc/build/contribute_to_paddle.html) <br>
We sincerely appreciate your interest and contributions. If you would like to
contribute, please read the contribution guide.
contribute, please read the contribution guide.
- [Source Code Documents](http://paddlepaddle.org/doc/source/) <br>
## Ask Questions
Please join the [**gitter chat**](https://gitter.im/PaddlePaddle/Deep_Learning) or send email to
**paddle-dev@baidu.com** to ask questions and talk about methods and models.
Framework development discussions and
bug reports are collected on [Issues](https://github.com/baidu/paddle/issues).
You are welcome to submit questions and bug reports as [Github Issues](https://github.com/PaddlePaddle/Paddle/issues).
## Copyright and License
PaddlePaddle is provided under the [Apache-2.0 license](LICENSE).

@ -24,7 +24,7 @@ paddle train \
--test_all_data_in_one_period=1 \
--use_gpu=1 \
--trainer_count=1 \
--num_passes=200 \
--num_passes=300 \
--save_dir=$output \
2>&1 | tee $log

@ -18,7 +18,5 @@ set -x
# download the dictionary and pretrained model
for file in baidu.dict model_32.emb model_64.emb model_128.emb model_256.emb
do
# following is the google drive address
# you can also directly download from https://pan.baidu.com/s/1o8q577s
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/embedding/$file --no-check-certificate
wget http://paddlepaddle.bj.bcebos.com/model_zoo/embedding/$file
done

@ -24,9 +24,7 @@ echo "Downloading ResNet models..."
for file in resnet_50.tar.gz resnet_101.tar.gz resnet_152.tar.gz mean_meta_224.tar.gz
do
# following is the google drive address
# you can also directly download from https://pan.baidu.com/s/1o8q577s
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/imagenet/$file --no-check-certificate
wget http://paddlepaddle.bj.bcebos.com/model_zoo/imagenet/$file
tar -xvf $file
rm $file
done

@ -23,7 +23,7 @@ set -e
export LC_ALL=C
UNAME_STR=`uname`
if [[ ${UNAME_STR} == 'Linux' ]]; then
if [ ${UNAME_STR} == 'Linux' ]; then
SHUF_PROG='shuf'
else
SHUF_PROG='gshuf'

@ -17,24 +17,15 @@ import os
from optparse import OptionParser
def extract_dict_features(pair_file, feature_file, src_dict_file,
tgt_dict_file):
src_dict = set()
tgt_dict = set()
with open(pair_file) as fin, open(feature_file, 'w') as feature_out, open(
src_dict_file, 'w') as src_dict_out, open(tgt_dict_file,
'w') as tgt_dict_out:
def extract_dict_features(pair_file, feature_file):
with open(pair_file) as fin, open(feature_file, 'w') as feature_out:
for line in fin:
sentence, labels = line.strip().split('\t')
sentence, predicate, labels = line.strip().split('\t')
sentence_list = sentence.split()
labels_list = labels.split()
src_dict.update(sentence_list)
tgt_dict.update(labels_list)
verb_index = labels_list.index('B-V')
verb_feature = sentence_list[verb_index]
mark = [0] * len(labels_list)
if verb_index > 0:
@ -42,47 +33,50 @@ def extract_dict_features(pair_file, feature_file, src_dict_file,
ctx_n1 = sentence_list[verb_index - 1]
else:
ctx_n1 = 'bos'
ctx_n1_feature = ctx_n1
if verb_index > 1:
mark[verb_index - 2] = 1
ctx_n2 = sentence_list[verb_index - 2]
else:
ctx_n2 = 'bos'
mark[verb_index] = 1
ctx_0_feature = sentence_list[verb_index]
ctx_0 = sentence_list[verb_index]
if verb_index < len(labels_list) - 2:
mark[verb_index + 1] = 1
ctx_p1 = sentence_list[verb_index + 1]
else:
ctx_p1 = 'eos'
ctx_p1_feature = ctx_p1
if verb_index < len(labels_list) - 3:
mark[verb_index + 2] = 1
ctx_p2 = sentence_list[verb_index + 2]
else:
ctx_p2 = 'eos'
feature_str = sentence + '\t' \
+ verb_feature + '\t' \
+ ctx_n1_feature + '\t' \
+ ctx_0_feature + '\t' \
+ ctx_p1_feature + '\t' \
+ predicate + '\t' \
+ ctx_n2 + '\t' \
+ ctx_n1 + '\t' \
+ ctx_0 + '\t' \
+ ctx_p1 + '\t' \
+ ctx_p2 + '\t' \
+ ' '.join([str(i) for i in mark]) + '\t' \
+ labels
feature_out.write(feature_str + '\n')
src_dict_out.write('<unk>\n')
src_dict_out.write('\n'.join(list(src_dict)))
tgt_dict_out.write('\n'.join(list(tgt_dict)))
if __name__ == '__main__':
usage = '-p pair_file -f feature_file -s source dictionary -t target dictionary '
usage = '-p pair_file -f feature_file'
parser = OptionParser(usage)
parser.add_option('-p', dest='pair_file', help='the pair file')
parser.add_option(
'-f', dest='feature_file', help='the file to store feature')
parser.add_option(
'-s', dest='src_dict', help='the file to store source dictionary')
parser.add_option(
'-t', dest='tgt_dict', help='the file to store target dictionary')
parser.add_option('-f', dest='feature_file', help='the feature file')
(options, args) = parser.parse_args()
extract_dict_features(options.pair_file, options.feature_file,
options.src_dict, options.tgt_dict)
extract_dict_features(options.pair_file, options.feature_file)

@ -51,7 +51,7 @@ def read_sentences(words_file):
for line in fin:
line = line.strip()
if line == '':
sentences.append(s.lower())
sentences.append(s)
s = ''
else:
s += line + ' '
@ -64,6 +64,11 @@ def transform_labels(sentences, labels):
if len(labels[i]) == 1:
continue
else:
verb_list = []
for x in labels[i][0]:
if x !='-':
verb_list.append(x)
for j in xrange(1, len(labels[i])):
label_list = labels[i][j]
current_tag = 'O'
@ -88,8 +93,7 @@ def transform_labels(sentences, labels):
is_in_bracket = True
else:
print 'error:', ll
sen_lab_pair.append((sentences[i], label_seq))
sen_lab_pair.append((sentences[i], verb_list[j-1], label_seq))
return sen_lab_pair
@ -97,9 +101,9 @@ def write_file(sen_lab_pair, output_file):
with open(output_file, 'w') as fout:
for x in sen_lab_pair:
sentence = x[0]
label_seq = ' '.join(x[1])
assert len(sentence.split()) == len(x[1])
fout.write(sentence + '\t' + label_seq + '\n')
label_seq = ' '.join(x[2])
assert len(sentence.split()) == len(x[2])
fout.write(sentence + '\t' + x[1]+'\t' +label_seq + '\n')
if __name__ == '__main__':

@ -14,6 +14,10 @@
# limitations under the License.
set -e
wget http://www.cs.upc.edu/~srlconll/conll05st-tests.tar.gz
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/verbDict.txt --no-check-certificate
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/targetDict.txt --no-check-certificate
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/wordDict.txt --no-check-certificate
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/emb --no-check-certificate
tar -xzvf conll05st-tests.tar.gz
rm conll05st-tests.tar.gz
cp ./conll05st-release/test.wsj/words/test.wsj.words.gz .
@ -22,4 +26,4 @@ gunzip test.wsj.words.gz
gunzip test.wsj.props.gz
python extract_pairs.py -w test.wsj.words -p test.wsj.props -o test.wsj.seq_pair
python extract_dict_feature.py -p test.wsj.seq_pair -f feature -s src.dict -t tgt.dict
python extract_dict_feature.py -p test.wsj.seq_pair -f feature

@ -17,41 +17,52 @@ from paddle.trainer.PyDataProvider2 import *
UNK_IDX = 0
def hook(settings, word_dict, label_dict, **kwargs):
def hook(settings, word_dict, label_dict, predicate_dict, **kwargs):
settings.word_dict = word_dict
settings.label_dict = label_dict
settings.predicate_dict = predicate_dict
#all inputs are integral and sequential type
settings.slots = [
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(word_dict)), integer_value_sequence(2),
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(word_dict)),
integer_value_sequence(len(predicate_dict)),
integer_value_sequence(2),
integer_value_sequence(len(label_dict))
]
@provider(init_hook=hook)
def process(obj, file_name):
def get_batch_size(yeild_data):
return len(yeild_data[0])
@provider(init_hook=hook, should_shuffle=True, calc_batch_size=get_batch_size,
can_over_batch_size=False, cache=CacheType.CACHE_PASS_IN_MEM)
def process(settings, file_name):
with open(file_name, 'r') as fdata:
for line in fdata:
sentence, predicate, ctx_n1, ctx_0, ctx_p1, mark, label = \
sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark, label = \
line.strip().split('\t')
words = sentence.split()
sen_len = len(words)
word_slot = [obj.word_dict.get(w, UNK_IDX) for w in words]
word_slot = [settings.word_dict.get(w, UNK_IDX) for w in words]
predicate_slot = [obj.word_dict.get(predicate, UNK_IDX)] * sen_len
ctx_n1_slot = [obj.word_dict.get(ctx_n1, UNK_IDX)] * sen_len
ctx_0_slot = [obj.word_dict.get(ctx_0, UNK_IDX)] * sen_len
ctx_p1_slot = [obj.word_dict.get(ctx_p1, UNK_IDX)] * sen_len
predicate_slot = [settings.predicate_dict.get(predicate)] * sen_len
ctx_n2_slot = [settings.word_dict.get(ctx_n2, UNK_IDX)] * sen_len
ctx_n1_slot = [settings.word_dict.get(ctx_n1, UNK_IDX)] * sen_len
ctx_0_slot = [settings.word_dict.get(ctx_0, UNK_IDX)] * sen_len
ctx_p1_slot = [settings.word_dict.get(ctx_p1, UNK_IDX)] * sen_len
ctx_p2_slot = [settings.word_dict.get(ctx_p2, UNK_IDX)] * sen_len
marks = mark.split()
mark_slot = [int(w) for w in marks]
label_list = label.split()
label_slot = [obj.label_dict.get(w) for w in label_list]
yield word_slot, predicate_slot, ctx_n1_slot, \
ctx_0_slot, ctx_p1_slot, mark_slot, label_slot
label_slot = [settings.label_dict.get(w) for w in label_list]
yield word_slot, ctx_n2_slot, ctx_n1_slot, \
ctx_0_slot, ctx_p1_slot, ctx_p2_slot, predicate_slot, mark_slot, label_slot

@ -18,8 +18,9 @@ import sys
from paddle.trainer_config_helpers import *
#file paths
word_dict_file = './data/src.dict'
label_dict_file = './data/tgt.dict'
word_dict_file = './data/wordDict.txt'
label_dict_file = './data/targetDict.txt'
predicate_file= './data/verbDict.txt'
train_list_file = './data/train.list'
test_list_file = './data/test.list'
@ -30,8 +31,10 @@ if not is_predict:
#load dictionaries
word_dict = dict()
label_dict = dict()
predicate_dict = dict()
with open(word_dict_file, 'r') as f_word, \
open(label_dict_file, 'r') as f_label:
open(label_dict_file, 'r') as f_label, \
open(predicate_file, 'r') as f_pre:
for i, line in enumerate(f_word):
w = line.strip()
word_dict[w] = i
@ -40,6 +43,11 @@ if not is_predict:
w = line.strip()
label_dict[w] = i
for i, line in enumerate(f_pre):
w = line.strip()
predicate_dict[w] = i
if is_test:
train_list_file = None
@ -50,91 +58,157 @@ if not is_predict:
module='dataprovider',
obj='process',
args={'word_dict': word_dict,
'label_dict': label_dict})
'label_dict': label_dict,
'predicate_dict': predicate_dict })
word_dict_len = len(word_dict)
label_dict_len = len(label_dict)
pred_len = len(predicate_dict)
else:
word_dict_len = get_config_arg('dict_len', int)
label_dict_len = get_config_arg('label_len', int)
pred_len = get_config_arg('pred_len', int)
############################## Hyper-parameters ##################################
mark_dict_len = 2
word_dim = 32
mark_dim = 5
hidden_dim = 128
hidden_dim = 512
depth = 8
emb_lr = 1e-2
fc_lr = 1e-2
lstm_lr = 2e-2
########################### Optimizer #######################################
settings(
batch_size=150,
learning_method=AdamOptimizer(),
learning_rate=1e-3,
learning_method=MomentumOptimizer(momentum=0),
learning_rate=2e-2,
regularization=L2Regularization(8e-4),
gradient_clipping_threshold=25)
is_async=False,
model_average=ModelAverage(average_window=0.5,
max_average_window=10000),
)
#6 features
####################################### network ##############################
#8 features and 1 target
word = data_layer(name='word_data', size=word_dict_len)
predicate = data_layer(name='verb_data', size=word_dict_len)
predicate = data_layer(name='verb_data', size=pred_len)
ctx_n2 = data_layer(name='ctx_n2_data', size=word_dict_len)
ctx_n1 = data_layer(name='ctx_n1_data', size=word_dict_len)
ctx_0 = data_layer(name='ctx_0_data', size=word_dict_len)
ctx_p1 = data_layer(name='ctx_p1_data', size=word_dict_len)
ctx_p2 = data_layer(name='ctx_p2_data', size=word_dict_len)
mark = data_layer(name='mark_data', size=mark_dict_len)
if not is_predict:
target = data_layer(name='target', size=label_dict_len)
ptt = ParameterAttribute(name='src_emb', learning_rate=emb_lr)
layer_attr = ExtraLayerAttribute(drop_rate=0.5)
fc_para_attr = ParameterAttribute(learning_rate=fc_lr)
lstm_para_attr = ParameterAttribute(initial_std=0., learning_rate=lstm_lr)
para_attr = [fc_para_attr, lstm_para_attr]
word_embedding = embedding_layer(size=word_dim, input=word, param_attr=ptt)
predicate_embedding = embedding_layer(
size=word_dim, input=predicate, param_attr=ptt)
ctx_n1_embedding = embedding_layer(size=word_dim, input=ctx_n1, param_attr=ptt)
ctx_0_embedding = embedding_layer(size=word_dim, input=ctx_0, param_attr=ptt)
ctx_p1_embedding = embedding_layer(size=word_dim, input=ctx_p1, param_attr=ptt)
mark_embedding = embedding_layer(size=mark_dim, input=mark)
default_std=1/math.sqrt(hidden_dim)/3.0
emb_para = ParameterAttribute(name='emb', initial_std=0., learning_rate=0.)
std_0 = ParameterAttribute(initial_std=0.)
std_default = ParameterAttribute(initial_std=default_std)
predicate_embedding = embedding_layer(size=word_dim, input=predicate, param_attr=ParameterAttribute(name='vemb',initial_std=default_std))
mark_embedding = embedding_layer(name='word_ctx-in_embedding', size=mark_dim, input=mark, param_attr=std_0)
word_input=[word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2]
emb_layers = [embedding_layer(size=word_dim, input=x, param_attr=emb_para) for x in word_input]
emb_layers.append(predicate_embedding)
emb_layers.append(mark_embedding)
hidden_0 = mixed_layer(
name='hidden0',
size=hidden_dim,
input=[
full_matrix_projection(input=word_embedding),
full_matrix_projection(input=predicate_embedding),
full_matrix_projection(input=ctx_n1_embedding),
full_matrix_projection(input=ctx_0_embedding),
full_matrix_projection(input=ctx_p1_embedding),
full_matrix_projection(input=mark_embedding),
])
bias_attr=std_default,
input=[ full_matrix_projection(input=emb, param_attr=std_default ) for emb in emb_layers ])
lstm_0 = lstmemory(input=hidden_0, layer_attr=layer_attr)
mix_hidden_lr = 1e-3
lstm_para_attr = ParameterAttribute(initial_std=0.0, learning_rate=1.0)
hidden_para_attr = ParameterAttribute(initial_std=default_std, learning_rate=mix_hidden_lr)
lstm_0 = lstmemory(name='lstm0',
input=hidden_0,
act=ReluActivation(),
gate_act=SigmoidActivation(),
state_act=SigmoidActivation(),
bias_attr=std_0,
param_attr=lstm_para_attr)
#stack L-LSTM and R-LSTM with direct edges
input_tmp = [hidden_0, lstm_0]
for i in range(1, depth):
fc = fc_layer(input=input_tmp, size=hidden_dim, param_attr=para_attr)
mix_hidden = mixed_layer(name='hidden'+str(i),
size=hidden_dim,
bias_attr=std_default,
input=[full_matrix_projection(input=input_tmp[0], param_attr=hidden_para_attr),
full_matrix_projection(input=input_tmp[1], param_attr=lstm_para_attr)
]
)
lstm = lstmemory(name='lstm'+str(i),
input=mix_hidden,
act=ReluActivation(),
gate_act=SigmoidActivation(),
state_act=SigmoidActivation(),
reverse=((i % 2)==1),
bias_attr=std_0,
param_attr=lstm_para_attr)
input_tmp = [mix_hidden, lstm]
feature_out = mixed_layer(name='output',
size=label_dict_len,
bias_attr=std_default,
input=[full_matrix_projection(input=input_tmp[0], param_attr=hidden_para_attr),
full_matrix_projection(input=input_tmp[1], param_attr=lstm_para_attr)
],
)
lstm = lstmemory(
input=fc,
act=ReluActivation(),
reverse=(i % 2) == 1,
layer_attr=layer_attr)
input_tmp = [fc, lstm]
prob = fc_layer(
input=input_tmp,
size=label_dict_len,
act=SoftmaxActivation(),
param_attr=para_attr)
if not is_predict:
cls = classification_cost(input=prob, label=target)
outputs(cls)
crf_l = crf_layer( name = 'crf',
size = label_dict_len,
input = feature_out,
label = target,
param_attr=ParameterAttribute(name='crfw',initial_std=default_std, learning_rate=mix_hidden_lr)
)
crf_dec_l = crf_decoding_layer(name = 'crf_dec_l',
size = label_dict_len,
input = feature_out,
label = target,
param_attr=ParameterAttribute(name='crfw')
)
eval = sum_evaluator(input=crf_dec_l)
outputs(crf_l)
else:
outputs(prob)
crf_dec_l = crf_decoding_layer(name = 'crf_dec_l',
size = label_dict_len,
input = feature_out,
param_attr=ParameterAttribute(name='crfw')
)
outputs(crf_dec_l)

@ -26,7 +26,7 @@ UNK_IDX = 0
class Prediction():
def __init__(self, train_conf, dict_file, model_dir, label_file):
def __init__(self, train_conf, dict_file, model_dir, label_file, predicate_dict_file):
"""
train_conf: trainer configure.
dict_file: word dictionary file name.
@ -35,26 +35,37 @@ class Prediction():
self.dict = {}
self.labels = {}
self.predicate_dict={}
self.labels_reverse = {}
self.load_dict_label(dict_file, label_file)
self.load_dict_label(dict_file, label_file, predicate_dict_file)
len_dict = len(self.dict)
len_label = len(self.labels)
conf = parse_config(train_conf, 'dict_len=' + str(len_dict) +
',label_len=' + str(len_label) + ',is_predict=True')
len_pred = len(self.predicate_dict)
conf = parse_config(
train_conf,
'dict_len=' + str(len_dict) +
',label_len=' + str(len_label) +
',pred_len=' + str(len_pred) +
',is_predict=True')
self.network = swig_paddle.GradientMachine.createFromConfigProto(
conf.model_config)
self.network.loadParameters(model_dir)
slots = [
integer_value_sequence(len_dict), integer_value_sequence(len_dict),
integer_value_sequence(len_dict), integer_value_sequence(len_dict),
integer_value_sequence(len_dict), integer_value_sequence(2)
]
integer_value_sequence(len_dict),
integer_value_sequence(len_dict),
integer_value_sequence(len_dict),
integer_value_sequence(len_dict),
integer_value_sequence(len_dict),
integer_value_sequence(len_dict),
integer_value_sequence(len_pred),
integer_value_sequence(2)
]
self.converter = DataProviderConverter(slots)
def load_dict_label(self, dict_file, label_file):
def load_dict_label(self, dict_file, label_file, predicate_dict_file):
"""
Load dictionary from self.dict_file.
"""
@ -65,39 +76,42 @@ class Prediction():
self.labels[line.strip()] = line_count
self.labels_reverse[line_count] = line.strip()
for line_count, line in enumerate(open(predicate_dict_file, 'r')):
self.predicate_dict[line.strip()] = line_count
def get_data(self, data_file):
"""
Get input data of paddle format.
"""
with open(data_file, 'r') as fdata:
for line in fdata:
sentence, predicate, ctx_n1, ctx_0, ctx_p1, mark, label = line.strip(
sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark, label = line.strip(
).split('\t')
words = sentence.split()
sen_len = len(words)
word_slot = [self.dict.get(w, UNK_IDX) for w in words]
predicate_slot = [self.dict.get(predicate, UNK_IDX)] * sen_len
predicate_slot = [self.predicate_dict.get(predicate, UNK_IDX)] * sen_len
ctx_n2_slot = [self.dict.get(ctx_n2, UNK_IDX)] * sen_len
ctx_n1_slot = [self.dict.get(ctx_n1, UNK_IDX)] * sen_len
ctx_0_slot = [self.dict.get(ctx_0, UNK_IDX)] * sen_len
ctx_p1_slot = [self.dict.get(ctx_p1, UNK_IDX)] * sen_len
ctx_p2_slot = [self.dict.get(ctx_p2, UNK_IDX)] * sen_len
marks = mark.split()
mark_slot = [int(w) for w in marks]
yield word_slot, ctx_n2_slot, ctx_n1_slot, \
ctx_0_slot, ctx_p1_slot, ctx_p2_slot, predicate_slot, mark_slot
yield word_slot, predicate_slot, ctx_n1_slot, \
ctx_0_slot, ctx_p1_slot, mark_slot
def predict(self, data_file):
def predict(self, data_file, output_file):
"""
data_file: file name of input data.
"""
input = self.converter(self.get_data(data_file))
output = self.network.forwardTest(input)
prob = output[0]["value"]
lab = list(np.argsort(-prob)[:, 0])
lab = output[0]["id"].tolist()
with open(data_file, 'r') as fin, open('predict.res', 'w') as fout:
with open(data_file, 'r') as fin, open(output_file, 'w') as fout:
index = 0
for line in fin:
sen = line.split('\t')[0]
@ -109,8 +123,8 @@ class Prediction():
def option_parser():
usage = ("python predict.py -c config -w model_dir "
"-d word dictionary -l label_file -i input_file")
usage = ("python predict.py -c config -w model_dir "
"-d word dictionary -l label_file -i input_file -p pred_dict_file")
parser = OptionParser(usage="usage: %s [options]" % usage)
parser.add_option(
"-c",
@ -131,6 +145,13 @@ def option_parser():
dest="label_file",
default=None,
help="label file")
parser.add_option(
"-p",
"--predict_dict_file",
action="store",
dest="predict_dict_file",
default=None,
help="predict_dict_file")
parser.add_option(
"-i",
"--data",
@ -144,6 +165,14 @@ def option_parser():
dest="model_path",
default=None,
help="model path")
parser.add_option(
"-o",
"--output_file",
action="store",
dest="output_file",
default=None,
help="output file")
return parser.parse_args()
@ -154,10 +183,12 @@ def main():
dict_file = options.dict_file
model_path = options.model_path
label_file = options.label_file
predict_dict_file = options.predict_dict_file
output_file = options.output_file
swig_paddle.initPaddle("--use_gpu=0")
predict = Prediction(train_conf, dict_file, model_path, label_file)
predict.predict(data_file)
predict = Prediction(train_conf, dict_file, model_path, label_file, predict_dict_file)
predict.predict(data_file,output_file)
if __name__ == '__main__':

@ -18,7 +18,7 @@ set -e
function get_best_pass() {
cat $1 | grep -Pzo 'Test .*\n.*pass-.*' | \
sed -r 'N;s/Test.* cost=([0-9]+\.[0-9]+).*\n.*pass-([0-9]+)/\1 \2/g' | \
sort | head -n 1
sort -n | head -n 1
}
log=train.log
@ -26,15 +26,18 @@ LOG=`get_best_pass $log`
LOG=(${LOG})
best_model_path="output/pass-${LOG[1]}"
config_file=db_lstm.py
dict_file=./data/src.dict
label_file=./data/tgt.dict
dict_file=./data/wordDict.txt
label_file=./data/targetDict.txt
predicate_dict_file=./data/verbDict.txt
input_file=./data/feature
output_file=predict.res
python predict.py \
-c $config_file \
-w $best_model_path \
-l $label_file \
-p $predicate_dict_file \
-d $dict_file \
-i $input_file
-i $input_file \
-o $output_file

@ -18,7 +18,7 @@ set -e
function get_best_pass() {
cat $1 | grep -Pzo 'Test .*\n.*pass-.*' | \
sed -r 'N;s/Test.* cost=([0-9]+\.[0-9]+).*\n.*pass-([0-9]+)/\1 \2/g' |\
sort | head -n 1
sort -n | head -n 1
}
log=train.log
@ -36,4 +36,5 @@ paddle train \
--job=test \
--use_gpu=false \
--config_args=is_test=1 \
--test_all_data_in_one_period=1 \
2>&1 | tee 'test.log'

@ -16,11 +16,14 @@
set -e
paddle train \
--config=./db_lstm.py \
--use_gpu=0 \
--log_period=5000 \
--trainer_count=1 \
--show_parameter_stats_period=5000 \
--save_dir=./output \
--trainer_count=4 \
--log_period=10 \
--num_passes=500 \
--use_gpu=false \
--show_parameter_stats_period=10 \
--num_passes=10000 \
--average_test_period=10000000 \
--init_model_path=./data \
--load_missing_parameter_strategy=rand \
--test_all_data_in_one_period=1 \
2>&1 | tee 'train.log'
2>&1 | tee 'train.log'

@ -17,7 +17,7 @@ set -e
function get_best_pass() {
cat $1 | grep -Pzo 'Test .*\n.*pass-.*' | \
sed -r 'N;s/Test.* classification_error_evaluator=([0-9]+\.[0-9]+).*\n.*pass-([0-9]+)/\1 \2/g' |\
sort | head -n 1
sort -n | head -n 1
}
log=train.log

@ -29,6 +29,7 @@ settings(
batch_size=128,
learning_rate=2e-3,
learning_method=AdamOptimizer(),
average_window=0.5,
regularization=L2Regularization(8e-4),
gradient_clipping_threshold=25)

@ -16,9 +16,7 @@ set -e
set -x
# download the in-house paraphrase dataset
# following is the google drive address
# you can also directly download from https://pan.baidu.com/s/1o8q577s
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/embedding/paraphrase.tar.gz --no-check-certificate
wget http://paddlepaddle.bj.bcebos.com/model_zoo/embedding/paraphrase.tar.gz
# untar the dataset
tar -zxvf paraphrase.tar.gz

@ -16,9 +16,7 @@ set -e
set -x
# download the pretrained model
# following is the google drive address
# you can also directly download from https://pan.baidu.com/s/1o8q577s
wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/wmt14_model.tar.gz --no-check-certificate
wget http://paddlepaddle.bj.bcebos.com/model_zoo/wmt14_model.tar.gz
# untar the model
tar -zxvf wmt14_model.tar.gz

@ -17,7 +17,7 @@ PaddlePaddle does not need any preprocessing to sequence data, such as padding.
.. code-block:: python
settings.slots = [
settings.input_types = [
integer_value_sequence(len(settings.src_dict)),
integer_value_sequence(len(settings.trg_dict)),
integer_value_sequence(len(settings.trg_dict))]

@ -6,10 +6,10 @@ Installing from Sources
* [3. Build on Ubuntu](#ubuntu)
## <span id="download">Download and Setup</span>
You can download PaddlePaddle from the [github source](https://github.com/gangliao/Paddle).
You can download PaddlePaddle from the [github source](https://github.com/PaddlePaddle/Paddle).
```bash
git clone https://github.com/baidu/Paddle paddle
git clone https://github.com/PaddlePaddle/Paddle paddle
cd paddle
```
@ -95,7 +95,7 @@ As a simple example, consider the following:
```bash
# necessary
sudo apt-get update
sudo apt-get install -y g++ make cmake build-essential libatlas-base-dev python python-pip libpython-dev m4 libprotobuf-dev protobuf-compiler python-protobuf python-numpy git
sudo apt-get install -y g++ make cmake swig build-essential libatlas-base-dev python python-pip libpython-dev m4 libprotobuf-dev protobuf-compiler python-protobuf python-numpy git
# optional
sudo apt-get install libgoogle-glog-dev
sudo apt-get install libgflags-dev
@ -149,15 +149,15 @@ If still not found, you can manually set it based on CMake error information fro
As a simple example, consider the following:
- **Only CPU**
- **Only CPU with swig**
```bash
cmake .. -DWITH_GPU=OFF
cmake .. -DWITH_GPU=OFF -DWITH_SWIG_PY=ON
```
- **GPU**
- **GPU with swig**
```bash
cmake .. -DWITH_GPU=ON
cmake .. -DWITH_GPU=ON -DWITH_SWIG_PY=ON
```
- **GPU with doc and swig**
@ -170,15 +170,13 @@ Finally, you can build PaddlePaddle:
```bash
# you can add build option here, such as:
cmake .. -DWITH_GPU=ON -DCMAKE_INSTALL_PREFIX=<path to install>
cmake .. -DWITH_GPU=ON -DCMAKE_INSTALL_PREFIX=<path to install> -DWITH_SWIG_PY=ON
# please use sudo make install, if you want to install PaddlePaddle into the system
make -j `nproc` && make install
# set PaddlePaddle installation path in ~/.bashrc
export PATH=<path to install>/bin:$PATH
```
**Note:**
If you set `WITH_SWIG_PY=ON`, related python dependencies also need to be installed.
Otherwise, PaddlePaddle will automatically install python dependencies
at first time when user run paddle commands, such as `paddle version`, `paddle train`.

@ -477,7 +477,7 @@ The scripts of data downloading, network configurations, and training scrips are
<td class="left">Word embedding</td>
<td class="left"> 15MB </td>
<td class="left"> 8.484%</td>
<td class="left">trainer_config.bow.py</td>
<td class="left">trainer_config.emb.py</td>
</tr>
<tr>

Binary file not shown.

After

Width:  |  Height:  |  Size: 52 KiB

Some files were not shown because too many files have changed in this diff Show More

Loading…
Cancel
Save