liaogang
8 years ago
commit
ec8e2108a4
File diff suppressed because it is too large
Load Diff
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 501 KiB |
@ -0,0 +1,46 @@
|
|||||||
|
# Locales
|
||||||
|
|
||||||
|
export LC_ALL=en_US.UTF-8
|
||||||
|
export LANG=en_US.UTF-8
|
||||||
|
export LANGUAGE=en_US.UTF-8
|
||||||
|
|
||||||
|
# Aliases
|
||||||
|
|
||||||
|
alias rm='rm -i'
|
||||||
|
alias cp='cp -i'
|
||||||
|
alias mv='mv -i'
|
||||||
|
|
||||||
|
alias ls='ls -hFG'
|
||||||
|
alias l='ls -lF'
|
||||||
|
alias ll='ls -alF'
|
||||||
|
alias lt='ls -ltrF'
|
||||||
|
alias ll='ls -alF'
|
||||||
|
alias lls='ls -alSrF'
|
||||||
|
alias llt='ls -altrF'
|
||||||
|
|
||||||
|
# Colorize directory listing
|
||||||
|
|
||||||
|
alias ls="ls -ph --color=auto"
|
||||||
|
|
||||||
|
# Colorize grep
|
||||||
|
|
||||||
|
if echo hello|grep --color=auto l >/dev/null 2>&1; then
|
||||||
|
export GREP_OPTIONS="--color=auto" GREP_COLOR="1;31"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Shell
|
||||||
|
|
||||||
|
export CLICOLOR="1"
|
||||||
|
|
||||||
|
YELLOW="\[\033[1;33m\]"
|
||||||
|
NO_COLOUR="\[\033[0m\]"
|
||||||
|
GREEN="\[\033[1;32m\]"
|
||||||
|
WHITE="\[\033[1;37m\]"
|
||||||
|
|
||||||
|
source ~/.scripts/git-prompt.sh
|
||||||
|
|
||||||
|
export PS1="\[\033[1;33m\]λ $WHITE\h $GREEN\w$YELLOW\$(__git_ps1 \" \[\033[35m\]{\[\033[36m\]%s\[\033[35m\]}\")$NO_COLOUR "
|
||||||
|
|
||||||
|
# Git
|
||||||
|
|
||||||
|
source ~/.scripts/git-completion.sh
|
||||||
@ -0,0 +1,43 @@
|
|||||||
|
[user]
|
||||||
|
name =
|
||||||
|
email =
|
||||||
|
|
||||||
|
[alias]
|
||||||
|
st = status --branch --short
|
||||||
|
ci = commit
|
||||||
|
br = branch
|
||||||
|
co = checkout
|
||||||
|
df = diff
|
||||||
|
l = log --pretty=format:\"%h %ad | %s%d [%an]\" --graph --date=short
|
||||||
|
ll = log --stat
|
||||||
|
|
||||||
|
[merge]
|
||||||
|
tool = vimdiff
|
||||||
|
|
||||||
|
[core]
|
||||||
|
excludesfile = ~/.gitignore
|
||||||
|
editor = vim
|
||||||
|
|
||||||
|
[color]
|
||||||
|
branch = auto
|
||||||
|
diff = auto
|
||||||
|
status = auto
|
||||||
|
|
||||||
|
[color "branch"]
|
||||||
|
current = yellow reverse
|
||||||
|
local = yellow
|
||||||
|
remote = green
|
||||||
|
|
||||||
|
[color "diff"]
|
||||||
|
meta = yellow bold
|
||||||
|
frag = magenta bold
|
||||||
|
old = red bold
|
||||||
|
new = green bold
|
||||||
|
|
||||||
|
[color "status"]
|
||||||
|
added = yellow
|
||||||
|
changed = green
|
||||||
|
untracked = cyan
|
||||||
|
|
||||||
|
[push]
|
||||||
|
default = matching
|
||||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,86 @@
|
|||||||
|
# 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.trainer_config_helpers.default_decorators import wrap_name_default
|
||||||
|
import paddle.trainer_config_helpers as conf_helps
|
||||||
|
|
||||||
|
|
||||||
|
class Layer(object):
|
||||||
|
def __init__(self, name=None, parent_layers=None):
|
||||||
|
assert isinstance(parent_layers, dict)
|
||||||
|
self.name = name
|
||||||
|
self.__parent_layers__ = parent_layers
|
||||||
|
|
||||||
|
def to_proto(self, context):
|
||||||
|
"""
|
||||||
|
function to set proto attribute
|
||||||
|
"""
|
||||||
|
kwargs = dict()
|
||||||
|
for layer_name in self.__parent_layers__:
|
||||||
|
if not isinstance(self.__parent_layers__[layer_name],
|
||||||
|
collections.Sequence):
|
||||||
|
v1_layer = self.__parent_layers__[layer_name].to_proto(
|
||||||
|
context=context)
|
||||||
|
else:
|
||||||
|
v1_layer = map(lambda x: x.to_proto(context=context),
|
||||||
|
self.__parent_layers__[layer_name])
|
||||||
|
kwargs[layer_name] = v1_layer
|
||||||
|
|
||||||
|
if self.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]
|
||||||
|
|
||||||
|
def to_proto_impl(self, **kwargs):
|
||||||
|
raise NotImplementedError()
|
||||||
|
|
||||||
|
|
||||||
|
def __convert_to_v2__(method_name, parent_names, is_default_name=True):
|
||||||
|
if is_default_name:
|
||||||
|
wrapper = wrap_name_default(name_prefix=method_name)
|
||||||
|
else:
|
||||||
|
wrapper = None
|
||||||
|
|
||||||
|
class V2LayerImpl(Layer):
|
||||||
|
def __init__(self, **kwargs):
|
||||||
|
parent_layers = dict()
|
||||||
|
other_kwargs = dict()
|
||||||
|
for pname in parent_names:
|
||||||
|
if kwargs.has_key(pname):
|
||||||
|
parent_layers[pname] = kwargs[pname]
|
||||||
|
|
||||||
|
for key in kwargs.keys():
|
||||||
|
if key not in parent_names:
|
||||||
|
other_kwargs[key] = kwargs[key]
|
||||||
|
|
||||||
|
name = kwargs.get('name', None)
|
||||||
|
super(V2LayerImpl, self).__init__(name, parent_layers)
|
||||||
|
self.__other_kwargs__ = other_kwargs
|
||||||
|
|
||||||
|
if wrapper is not None:
|
||||||
|
__init__ = wrapper(__init__)
|
||||||
|
|
||||||
|
def to_proto_impl(self, **kwargs):
|
||||||
|
args = dict()
|
||||||
|
for each in kwargs:
|
||||||
|
args[each] = kwargs[each]
|
||||||
|
for each in self.__other_kwargs__:
|
||||||
|
args[each] = self.__other_kwargs__[each]
|
||||||
|
return getattr(conf_helps, method_name)(**args)
|
||||||
|
|
||||||
|
return V2LayerImpl
|
||||||
@ -0,0 +1,120 @@
|
|||||||
|
# /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");
|
||||||
|
# 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.
|
||||||
|
"""
|
||||||
|
IMDB dataset: http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz
|
||||||
|
"""
|
||||||
|
import paddle.v2.dataset.common
|
||||||
|
import tarfile
|
||||||
|
import Queue
|
||||||
|
import re
|
||||||
|
import string
|
||||||
|
import threading
|
||||||
|
|
||||||
|
__all__ = ['build_dict', 'train', 'test']
|
||||||
|
|
||||||
|
URL = 'http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz'
|
||||||
|
MD5 = '7c2ac02c03563afcf9b574c7e56c153a'
|
||||||
|
|
||||||
|
|
||||||
|
# Read files that match pattern. Tokenize and yield each file.
|
||||||
|
def tokenize(pattern):
|
||||||
|
with tarfile.open(paddle.v2.dataset.common.download(URL, 'imdb',
|
||||||
|
MD5)) as tarf:
|
||||||
|
# Note that we should use tarfile.next(), which does
|
||||||
|
# sequential access of member files, other than
|
||||||
|
# tarfile.extractfile, which does random access and might
|
||||||
|
# destroy hard disks.
|
||||||
|
tf = tarf.next()
|
||||||
|
while tf != None:
|
||||||
|
if bool(pattern.match(tf.name)):
|
||||||
|
# newline and punctuations removal and ad-hoc tokenization.
|
||||||
|
yield tarf.extractfile(tf).read().rstrip("\n\r").translate(
|
||||||
|
None, string.punctuation).lower().split()
|
||||||
|
tf = tarf.next()
|
||||||
|
|
||||||
|
|
||||||
|
def build_dict(pattern, cutoff):
|
||||||
|
word_freq = {}
|
||||||
|
for doc in tokenize(pattern):
|
||||||
|
for word in doc:
|
||||||
|
paddle.v2.dataset.common.dict_add(word_freq, word)
|
||||||
|
|
||||||
|
# Not sure if we should prune less-frequent words here.
|
||||||
|
word_freq = filter(lambda x: x[1] > cutoff, word_freq.items())
|
||||||
|
|
||||||
|
dictionary = sorted(word_freq, key=lambda x: (-x[1], x[0]))
|
||||||
|
words, _ = list(zip(*dictionary))
|
||||||
|
word_idx = dict(zip(words, xrange(len(words))))
|
||||||
|
word_idx['<unk>'] = len(words)
|
||||||
|
return word_idx
|
||||||
|
|
||||||
|
|
||||||
|
def reader_creator(pos_pattern, neg_pattern, word_idx, buffer_size):
|
||||||
|
UNK = word_idx['<unk>']
|
||||||
|
|
||||||
|
qs = [Queue.Queue(maxsize=buffer_size), Queue.Queue(maxsize=buffer_size)]
|
||||||
|
|
||||||
|
def load(pattern, queue):
|
||||||
|
for doc in tokenize(pattern):
|
||||||
|
queue.put(doc)
|
||||||
|
queue.put(None)
|
||||||
|
|
||||||
|
def reader():
|
||||||
|
# Creates two threads that loads positive and negative samples
|
||||||
|
# into qs.
|
||||||
|
t0 = threading.Thread(
|
||||||
|
target=load, args=(
|
||||||
|
pos_pattern,
|
||||||
|
qs[0], ))
|
||||||
|
t0.daemon = True
|
||||||
|
t0.start()
|
||||||
|
|
||||||
|
t1 = threading.Thread(
|
||||||
|
target=load, args=(
|
||||||
|
neg_pattern,
|
||||||
|
qs[1], ))
|
||||||
|
t1.daemon = True
|
||||||
|
t1.start()
|
||||||
|
|
||||||
|
# Read alternatively from qs[0] and qs[1].
|
||||||
|
i = 0
|
||||||
|
doc = qs[i].get()
|
||||||
|
while doc != None:
|
||||||
|
yield [word_idx.get(w, UNK) for w in doc], i % 2
|
||||||
|
i += 1
|
||||||
|
doc = qs[i % 2].get()
|
||||||
|
|
||||||
|
# If any queue is empty, reads from the other queue.
|
||||||
|
i += 1
|
||||||
|
doc = qs[i % 2].get()
|
||||||
|
while doc != None:
|
||||||
|
yield [word_idx.get(w, UNK) for w in doc], i % 2
|
||||||
|
doc = qs[i % 2].get()
|
||||||
|
|
||||||
|
return reader()
|
||||||
|
|
||||||
|
|
||||||
|
def train(word_idx):
|
||||||
|
return reader_creator(
|
||||||
|
re.compile("aclImdb/train/pos/.*\.txt$"),
|
||||||
|
re.compile("aclImdb/train/neg/.*\.txt$"), word_idx, 1000)
|
||||||
|
|
||||||
|
|
||||||
|
def test(word_idx):
|
||||||
|
return reader_creator(
|
||||||
|
re.compile("aclImdb/test/pos/.*\.txt$"),
|
||||||
|
re.compile("aclImdb/test/neg/.*\.txt$"), word_idx, 1000)
|
||||||
@ -0,0 +1,79 @@
|
|||||||
|
"""
|
||||||
|
imikolov's simple dataset: http://www.fit.vutbr.cz/~imikolov/rnnlm/
|
||||||
|
"""
|
||||||
|
import paddle.v2.dataset.common
|
||||||
|
import tarfile
|
||||||
|
|
||||||
|
__all__ = ['train', 'test']
|
||||||
|
|
||||||
|
URL = 'http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz'
|
||||||
|
MD5 = '30177ea32e27c525793142b6bf2c8e2d'
|
||||||
|
|
||||||
|
|
||||||
|
def word_count(f, word_freq=None):
|
||||||
|
add = paddle.v2.dataset.common.dict_add
|
||||||
|
if word_freq == None:
|
||||||
|
word_freq = {}
|
||||||
|
|
||||||
|
for l in f:
|
||||||
|
for w in l.strip().split():
|
||||||
|
add(word_freq, w)
|
||||||
|
add(word_freq, '<s>')
|
||||||
|
add(word_freq, '<e>')
|
||||||
|
|
||||||
|
return word_freq
|
||||||
|
|
||||||
|
|
||||||
|
def build_dict(train_filename, test_filename):
|
||||||
|
with tarfile.open(
|
||||||
|
paddle.v2.dataset.common.download(
|
||||||
|
paddle.v2.dataset.imikolov.URL, 'imikolov',
|
||||||
|
paddle.v2.dataset.imikolov.MD5)) as tf:
|
||||||
|
trainf = tf.extractfile(train_filename)
|
||||||
|
testf = tf.extractfile(test_filename)
|
||||||
|
word_freq = word_count(testf, word_count(trainf))
|
||||||
|
|
||||||
|
TYPO_FREQ = 50
|
||||||
|
word_freq = filter(lambda x: x[1] > TYPO_FREQ, word_freq.items())
|
||||||
|
|
||||||
|
dictionary = sorted(word_freq, key=lambda x: (-x[1], x[0]))
|
||||||
|
words, _ = list(zip(*dictionary))
|
||||||
|
word_idx = dict(zip(words, xrange(len(words))))
|
||||||
|
word_idx['<unk>'] = len(words)
|
||||||
|
|
||||||
|
return word_idx
|
||||||
|
|
||||||
|
|
||||||
|
word_idx = {}
|
||||||
|
|
||||||
|
|
||||||
|
def reader_creator(filename, n):
|
||||||
|
global word_idx
|
||||||
|
if len(word_idx) == 0:
|
||||||
|
word_idx = build_dict('./simple-examples/data/ptb.train.txt',
|
||||||
|
'./simple-examples/data/ptb.valid.txt')
|
||||||
|
|
||||||
|
def reader():
|
||||||
|
with tarfile.open(
|
||||||
|
paddle.v2.dataset.common.download(
|
||||||
|
paddle.v2.dataset.imikolov.URL, 'imikolov',
|
||||||
|
paddle.v2.dataset.imikolov.MD5)) as tf:
|
||||||
|
f = tf.extractfile(filename)
|
||||||
|
|
||||||
|
UNK = word_idx['<unk>']
|
||||||
|
for l in f:
|
||||||
|
l = ['<s>'] + l.strip().split() + ['<e>']
|
||||||
|
if len(l) >= n:
|
||||||
|
l = [word_idx.get(w, UNK) for w in l]
|
||||||
|
for i in range(n, len(l) + 1):
|
||||||
|
yield tuple(l[i - n:i])
|
||||||
|
|
||||||
|
return reader
|
||||||
|
|
||||||
|
|
||||||
|
def train(n):
|
||||||
|
return reader_creator('./simple-examples/data/ptb.train.txt', n)
|
||||||
|
|
||||||
|
|
||||||
|
def test(n):
|
||||||
|
return reader_creator('./simple-examples/data/ptb.valid.txt', n)
|
||||||
@ -0,0 +1,43 @@
|
|||||||
|
import paddle.v2.dataset.imdb
|
||||||
|
import unittest
|
||||||
|
import re
|
||||||
|
|
||||||
|
TRAIN_POS_PATTERN = re.compile("aclImdb/train/pos/.*\.txt$")
|
||||||
|
TRAIN_NEG_PATTERN = re.compile("aclImdb/train/neg/.*\.txt$")
|
||||||
|
TRAIN_PATTERN = re.compile("aclImdb/train/.*\.txt$")
|
||||||
|
|
||||||
|
TEST_POS_PATTERN = re.compile("aclImdb/test/pos/.*\.txt$")
|
||||||
|
TEST_NEG_PATTERN = re.compile("aclImdb/test/neg/.*\.txt$")
|
||||||
|
TEST_PATTERN = re.compile("aclImdb/test/.*\.txt$")
|
||||||
|
|
||||||
|
|
||||||
|
class TestIMDB(unittest.TestCase):
|
||||||
|
word_idx = None
|
||||||
|
|
||||||
|
def test_build_dict(self):
|
||||||
|
if self.word_idx == None:
|
||||||
|
self.word_idx = paddle.v2.dataset.imdb.build_dict(TRAIN_PATTERN,
|
||||||
|
150)
|
||||||
|
|
||||||
|
self.assertEqual(len(self.word_idx), 7036)
|
||||||
|
|
||||||
|
def check_dataset(self, dataset, expected_size):
|
||||||
|
if self.word_idx == None:
|
||||||
|
self.word_idx = paddle.v2.dataset.imdb.build_dict(TRAIN_PATTERN,
|
||||||
|
150)
|
||||||
|
|
||||||
|
sum = 0
|
||||||
|
for l in dataset(self.word_idx):
|
||||||
|
self.assertEqual(l[1], sum % 2)
|
||||||
|
sum += 1
|
||||||
|
self.assertEqual(sum, expected_size)
|
||||||
|
|
||||||
|
def test_train(self):
|
||||||
|
self.check_dataset(paddle.v2.dataset.imdb.train, 25000)
|
||||||
|
|
||||||
|
def test_test(self):
|
||||||
|
self.check_dataset(paddle.v2.dataset.imdb.test, 25000)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
unittest.main()
|
||||||
@ -0,0 +1,20 @@
|
|||||||
|
import paddle.v2.dataset.imikolov
|
||||||
|
import unittest
|
||||||
|
|
||||||
|
|
||||||
|
class TestMikolov(unittest.TestCase):
|
||||||
|
def check_reader(self, reader, n):
|
||||||
|
for l in reader():
|
||||||
|
self.assertEqual(len(l), n)
|
||||||
|
|
||||||
|
def test_train(self):
|
||||||
|
n = 5
|
||||||
|
self.check_reader(paddle.v2.dataset.imikolov.train(n), n)
|
||||||
|
|
||||||
|
def test_test(self):
|
||||||
|
n = 5
|
||||||
|
self.check_reader(paddle.v2.dataset.imikolov.test(n), n)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
unittest.main()
|
||||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue