Skip to content

F
FluidDoc

PaddlePaddle / FluidDoc

通知 10
Star 2
Fork 0
F
FluidDoc
未验证 提交 9c80f825 编写于 作者: Y yuyang18
浏览文件
操作

remove python file

上级 b2eb302f
隐藏空白更改
内联 并排
Showing with 0 addition and 1361 deletion
source/beginners_guide/basics/03.image_classification/resnet.py 已删除 100644 → 0
浏览文件 @ b2eb302f
# 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 as paddle
__all__ = ['resnet_cifar10']
def conv_bn_layer(input,
ch_out,
filter_size,
stride,
padding,
active_type=paddle.activation.Relu(),
ch_in=None):
tmp = paddle.layer.img_conv(
input=input,
filter_size=filter_size,
num_channels=ch_in,
num_filters=ch_out,
stride=stride,
padding=padding,
act=paddle.activation.Linear(),
bias_attr=False)
return paddle.layer.batch_norm(input=tmp, act=active_type)
def shortcut(ipt, ch_in, ch_out, stride):
if ch_in != ch_out:
return conv_bn_layer(ipt, ch_out, 1, stride, 0,
paddle.activation.Linear())
else:
return ipt
def basicblock(ipt, ch_in, ch_out, stride):
tmp = conv_bn_layer(ipt, ch_out, 3, stride, 1)
tmp = conv_bn_layer(tmp, ch_out, 3, 1, 1, paddle.activation.Linear())
short = shortcut(ipt, ch_in, ch_out, stride)
return paddle.layer.addto(input=[tmp, short], act=paddle.activation.Relu())
def layer_warp(block_func, ipt, ch_in, ch_out, count, stride):
tmp = block_func(ipt, ch_in, ch_out, stride)
for i in range(1, count):
tmp = block_func(tmp, ch_out, ch_out, 1)
return tmp
def resnet_cifar10(ipt, depth=32):
# depth should be one of 20, 32, 44, 56, 110, 1202
assert (depth - 2) % 6 == 0
n = (depth - 2) / 6
nStages = {16, 64, 128}
conv1 = conv_bn_layer(
ipt, ch_in=3, ch_out=16, filter_size=3, stride=1, padding=1)
res1 = layer_warp(basicblock, conv1, 16, 16, n, 1)
res2 = layer_warp(basicblock, res1, 16, 32, n, 2)
res3 = layer_warp(basicblock, res2, 32, 64, n, 2)
pool = paddle.layer.img_pool(
input=res3, pool_size=8, stride=1, pool_type=paddle.pooling.Avg())
return pool
source/beginners_guide/basics/03.image_classification/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
# 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 sys, os
import paddle.v2 as paddle
from vgg import vgg_bn_drop
from resnet import resnet_cifar10
with_gpu = os.getenv('WITH_GPU', '0') != '0'
def main():
datadim = 3 * 32 * 32
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=with_gpu, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(datadim))
# Add neural network config
# option 1. resnet
# net = resnet_cifar10(image, depth=32)
# option 2. vgg
net = vgg_bn_drop(image)
out = paddle.layer.fc(
input=net, size=classdim, act=paddle.activation.Softmax())
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(classdim))
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
momentum_optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.1 / 128.0,
learning_rate_decay_a=0.1,
learning_rate_decay_b=50000 * 100,
learning_rate_schedule='discexp')
# Create trainer
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=momentum_optimizer)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
# save parameters
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(
reader=paddle.batch(
paddle.dataset.cifar.test10(), batch_size=128),
feeding={'image': 0,
'label': 1})
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Save the inference topology to protobuf.
inference_topology = paddle.topology.Topology(layers=out)
with open("inference_topology.pkl", 'wb') as f:
inference_topology.serialize_for_inference(f)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),
num_passes=200,
event_handler=event_handler,
feeding={'image': 0,
'label': 1})
# inference
from PIL import Image
import numpy as np
import os
def load_image(file):
im = Image.open(file)
im = im.resize((32, 32), Image.ANTIALIAS)
im = np.array(im).astype(np.float32)
# The storage order of the loaded image is W(widht),
# H(height), C(channel). PaddlePaddle requires
# the CHW order, so transpose them.
im = im.transpose((2, 0, 1)) # CHW
# In the training phase, the channel order of CIFAR
# image is B(Blue), G(green), R(Red). But PIL open
# image in RGB mode. It must swap the channel order.
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
test_data = []
cur_dir = os.path.dirname(os.path.realpath(__file__))
test_data.append((load_image(cur_dir + '/image/dog.png'), ))
# users can remove the comments and change the model name
# with open('params_pass_50.tar', 'r') as f:
# parameters = paddle.parameters.Parameters.from_tar(f)
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs) # probs and lab are the results of one batch data
print "Label of image/dog.png is: %d" % lab[0][0]
if __name__ == '__main__':
main()
source/beginners_guide/basics/03.image_classification/vgg.py 已删除 100644 → 0
浏览文件 @ b2eb302f
# 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 as paddle
__all__ = ['vgg_bn_drop']
def vgg_bn_drop(input):
def conv_block(ipt, num_filter, groups, dropouts, num_channels=None):
return paddle.networks.img_conv_group(
input=ipt,
num_channels=num_channels,
pool_size=2,
pool_stride=2,
conv_num_filter=[num_filter] * groups,
conv_filter_size=3,
conv_act=paddle.activation.Relu(),
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type=paddle.pooling.Max())
conv1 = conv_block(input, 64, 2, [0.3, 0], 3)
conv2 = conv_block(conv1, 128, 2, [0.4, 0])
conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0])
conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0])
conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0])
drop = paddle.layer.dropout(input=conv5, dropout_rate=0.5)
fc1 = paddle.layer.fc(input=drop, size=512, act=paddle.activation.Linear())
bn = paddle.layer.batch_norm(
input=fc1,
act=paddle.activation.Relu(),
layer_attr=paddle.attr.Extra(drop_rate=0.5))
fc2 = paddle.layer.fc(input=bn, size=512, act=paddle.activation.Linear())
return fc2
source/beginners_guide/basics/04.word2vec/calculate_dis.py 已删除 100755 → 0
浏览文件 @ b2eb302f
# 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.
"""
Example:
python calculate_dis.py DICTIONARYTXT FEATURETXT
Required arguments:
DICTIONARYTXT the dictionary generated in dataprovider
FEATURETXT the text format word feature, one line for one word
"""
import numpy as np
from argparse import ArgumentParser
def load_dict(fdict):
words = [line.strip() for line in fdict.readlines()]
dictionary = dict(zip(words, xrange(len(words))))
return dictionary
def load_emb(femb):
feaBank = []
flag_firstline = True
for line in femb:
if flag_firstline:
flag_firstline = False
continue
fea = np.array([float(x) for x in line.strip().split(',')])
normfea = fea * 1.0 / np.linalg.norm(fea)
feaBank.append(normfea)
return feaBank
def calcos(id1, id2, Fea):
f1 = Fea[id1]
f2 = Fea[id2]
return np.dot(f1.transpose(), f2)
def get_wordidx(w, Dict):
if w not in Dict:
print 'ERROR: %s not in the dictionary' % w
return -1
return Dict[w]
if __name__ == '__main__':
parser = ArgumentParser()
parser.add_argument('dict', help='dictionary file')
parser.add_argument('fea', help='feature file')
args = parser.parse_args()
with open(args.dict) as fdict:
word_dict = load_dict(fdict)
with open(args.fea) as ffea:
word_fea = load_emb(ffea)
while True:
w1, w2 = raw_input("please input two words: ").split()
w1_id = get_wordidx(w1, word_dict)
w2_id = get_wordidx(w2, word_dict)
if w1_id == -1 or w2_id == -1:
continue
print 'similarity: %s' % (calcos(w1_id, w2_id, word_fea))
source/beginners_guide/basics/04.word2vec/format_convert.py 已删除 100755 → 0
浏览文件 @ b2eb302f
# 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.
"""
Example:
python format_convert.py --b2t -i INPUT -o OUTPUT -d DIM
python format_convert.py --t2b -i INPUT -o OUTPUT
Options:
-h, --help show this help message and exit
--b2t convert parameter file of embedding model from binary to text
--t2b convert parameter file of embedding model from text to binary
-i INPUT input parameter file name
-o OUTPUT output parameter file name
-d DIM dimension of parameter
"""
from optparse import OptionParser
import struct
def binary2text(input, output, paraDim):
"""
Convert a binary parameter file of embedding model to be a text file.
input: the name of input binary parameter file, the format is:
1) the first 16 bytes is filehead:
version(4 bytes): version of paddle, default = 0
floatSize(4 bytes): sizeof(float) = 4
paraCount(8 bytes): total number of parameter
2) the next (paraCount * 4) bytes is parameters, each has 4 bytes
output: the name of output text parameter file, for example:
0,4,32156096
-0.7845433,1.1937413,-0.1704215,...
0.0000909,0.0009465,-0.0008813,...
...
the format is:
1) the first line is filehead:
version=0, floatSize=4, paraCount=32156096
2) other lines print the paramters
a) each line prints paraDim paramters splitted by ','
b) there is paraCount/paraDim lines (embedding words)
paraDim: dimension of parameters
"""
fi = open(input, "rb")
fo = open(output, "w")
"""
"""
version, floatSize, paraCount = struct.unpack("iil", fi.read(16))
newHead = ','.join([str(version), str(floatSize), str(paraCount)])
print >> fo, newHead
bytes = 4 * int(paraDim)
format = "%df" % int(paraDim)
context = fi.read(bytes)
line = 0
while context:
numbers = struct.unpack(format, context)
lst = []
for i in numbers:
lst.append('%8.7f' % i)
print >> fo, ','.join(lst)
context = fi.read(bytes)
line += 1
fi.close()
fo.close()
print "binary2text finish, total", line, "lines"
def get_para_count(input):
"""
Compute the total number of embedding parameters in input text file.
input: the name of input text file
"""
numRows = 1
paraDim = 0
with open(input) as f:
line = f.readline()
paraDim = len(line.split(","))
for line in f:
numRows += 1
return numRows * paraDim
def text2binary(input, output, paddle_head=True):
"""
Convert a text parameter file of embedding model to be a binary file.
input: the name of input text parameter file, for example:
-0.7845433,1.1937413,-0.1704215,...
0.0000909,0.0009465,-0.0008813,...
...
the format is:
1) it doesn't have filehead
2) each line stores the same dimension of parameters,
the separator is commas ','
output: the name of output binary parameter file, the format is:
1) the first 16 bytes is filehead:
version(4 bytes), floatSize(4 bytes), paraCount(8 bytes)
2) the next (paraCount * 4) bytes is parameters, each has 4 bytes
"""
fi = open(input, "r")
fo = open(output, "wb")
newHead = struct.pack("iil", 0, 4, get_para_count(input))
fo.write(newHead)
count = 0
for line in fi:
line = line.strip().split(",")
for i in range(0, len(line)):
binary_data = struct.pack("f", float(line[i]))
fo.write(binary_data)
count += 1
fi.close()
fo.close()
print "text2binary finish, total", count, "lines"
def main():
"""
Main entry for running format_convert.py
"""
usage = "usage: \n" \
"python %prog --b2t -i INPUT -o OUTPUT -d DIM \n" \
"python %prog --t2b -i INPUT -o OUTPUT"
parser = OptionParser(usage)
parser.add_option(
"--b2t",
action="store_true",
help="convert parameter file of embedding model from binary to text")
parser.add_option(
"--t2b",
action="store_true",
help="convert parameter file of embedding model from text to binary")
parser.add_option(
"-i", action="store", dest="input", help="input parameter file name")
parser.add_option(
"-o", action="store", dest="output", help="output parameter file name")
parser.add_option(
"-d", action="store", dest="dim", help="dimension of parameter")
(options, args) = parser.parse_args()
if options.b2t:
binary2text(options.input, options.output, options.dim)
if options.t2b:
text2binary(options.input, options.output)
if __name__ == '__main__':
main()
source/beginners_guide/basics/04.word2vec/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
import math
import os
import numpy
import paddle.v2 as paddle
with_gpu = os.getenv('WITH_GPU', '0') != '0'
embsize = 32
hiddensize = 256
N = 5
def wordemb(inlayer):
wordemb = paddle.layer.table_projection(
input=inlayer,
size=embsize,
param_attr=paddle.attr.Param(
name="_proj", initial_std=0.001, learning_rate=1, l2_rate=0))
return wordemb
# save and load word dict and embedding table
def save_dict_and_embedding(word_dict, embeddings):
with open("word_dict", "w") as f:
for key in word_dict:
f.write(key + " " + str(word_dict[key]) + "\n")
with open("embedding_table", "w") as f:
numpy.savetxt(f, embeddings, delimiter=',', newline='\n')
def load_dict_and_embedding():
word_dict = dict()
with open("word_dict", "r") as f:
for line in f:
key, value = line.strip().split(" ")
word_dict[key] = int(value)
embeddings = numpy.loadtxt("embedding_table", delimiter=",")
return word_dict, embeddings
def main():
paddle.init(use_gpu=with_gpu, trainer_count=1)
word_dict = paddle.dataset.imikolov.build_dict()
dict_size = len(word_dict)
# Every layer takes integer value of range [0, dict_size)
firstword = paddle.layer.data(
name="firstw", type=paddle.data_type.integer_value(dict_size))
secondword = paddle.layer.data(
name="secondw", type=paddle.data_type.integer_value(dict_size))
thirdword = paddle.layer.data(
name="thirdw", type=paddle.data_type.integer_value(dict_size))
fourthword = paddle.layer.data(
name="fourthw", type=paddle.data_type.integer_value(dict_size))
nextword = paddle.layer.data(
name="fifthw", type=paddle.data_type.integer_value(dict_size))
Efirst = wordemb(firstword)
Esecond = wordemb(secondword)
Ethird = wordemb(thirdword)
Efourth = wordemb(fourthword)
contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
hidden1 = paddle.layer.fc(
input=contextemb,
size=hiddensize,
act=paddle.activation.Sigmoid(),
layer_attr=paddle.attr.Extra(drop_rate=0.5),
bias_attr=paddle.attr.Param(learning_rate=2),
param_attr=paddle.attr.Param(
initial_std=1. / math.sqrt(embsize * 8), learning_rate=1))
predictword = paddle.layer.fc(
input=hidden1,
size=dict_size,
bias_attr=paddle.attr.Param(learning_rate=2),
act=paddle.activation.Softmax())
cost = paddle.layer.classification_cost(input=predictword, label=nextword)
parameters = paddle.parameters.create(cost)
adagrad = paddle.optimizer.AdaGrad(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(8e-4))
trainer = paddle.trainer.SGD(cost, parameters, adagrad)
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
result = trainer.test(
paddle.batch(paddle.dataset.imikolov.test(word_dict, N), 32))
print "Pass %d, Testing metrics %s" % (event.pass_id,
result.metrics)
with open("model_%d.tar" % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
trainer.train(
paddle.batch(paddle.dataset.imikolov.train(word_dict, N), 32),
num_passes=100,
event_handler=event_handler)
# save word dict and embedding table
embeddings = parameters.get("_proj").reshape(len(word_dict), embsize)
save_dict_and_embedding(word_dict, embeddings)
if __name__ == '__main__':
main()
source/beginners_guide/basics/05.recommender_system/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
import paddle.v2 as paddle
import cPickle
import copy
import os
with_gpu = os.getenv('WITH_GPU', '0') != '0'
def get_usr_combined_features():
uid = paddle.layer.data(
name='user_id',
type=paddle.data_type.integer_value(
paddle.dataset.movielens.max_user_id() + 1))
usr_emb = paddle.layer.embedding(input=uid, size=32)
usr_fc = paddle.layer.fc(input=usr_emb, size=32)
usr_gender_id = paddle.layer.data(
name='gender_id', type=paddle.data_type.integer_value(2))
usr_gender_emb = paddle.layer.embedding(input=usr_gender_id, size=16)
usr_gender_fc = paddle.layer.fc(input=usr_gender_emb, size=16)
usr_age_id = paddle.layer.data(
name='age_id',
type=paddle.data_type.integer_value(
len(paddle.dataset.movielens.age_table)))
usr_age_emb = paddle.layer.embedding(input=usr_age_id, size=16)
usr_age_fc = paddle.layer.fc(input=usr_age_emb, size=16)
usr_job_id = paddle.layer.data(
name='job_id',
type=paddle.data_type.integer_value(
paddle.dataset.movielens.max_job_id() + 1))
usr_job_emb = paddle.layer.embedding(input=usr_job_id, size=16)
usr_job_fc = paddle.layer.fc(input=usr_job_emb, size=16)
usr_combined_features = paddle.layer.fc(
input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc],
size=200,
act=paddle.activation.Tanh())
return usr_combined_features
def get_mov_combined_features():
movie_title_dict = paddle.dataset.movielens.get_movie_title_dict()
mov_id = paddle.layer.data(
name='movie_id',
type=paddle.data_type.integer_value(
paddle.dataset.movielens.max_movie_id() + 1))
mov_emb = paddle.layer.embedding(input=mov_id, size=32)
mov_fc = paddle.layer.fc(input=mov_emb, size=32)
mov_categories = paddle.layer.data(
name='category_id',
type=paddle.data_type.sparse_binary_vector(
len(paddle.dataset.movielens.movie_categories())))
mov_categories_hidden = paddle.layer.fc(input=mov_categories, size=32)
mov_title_id = paddle.layer.data(
name='movie_title',
type=paddle.data_type.integer_value_sequence(len(movie_title_dict)))
mov_title_emb = paddle.layer.embedding(input=mov_title_id, size=32)
mov_title_conv = paddle.networks.sequence_conv_pool(
input=mov_title_emb, hidden_size=32, context_len=3)
mov_combined_features = paddle.layer.fc(
input=[mov_fc, mov_categories_hidden, mov_title_conv],
size=200,
act=paddle.activation.Tanh())
return mov_combined_features
def main():
paddle.init(use_gpu=with_gpu)
usr_combined_features = get_usr_combined_features()
mov_combined_features = get_mov_combined_features()
inference = paddle.layer.cos_sim(
a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
cost = paddle.layer.square_error_cost(
input=inference,
label=paddle.layer.data(
name='score', type=paddle.data_type.dense_vector(1)))
parameters = paddle.parameters.create(cost)
trainer = paddle.trainer.SGD(
cost=cost,
parameters=parameters,
update_equation=paddle.optimizer.Adam(learning_rate=1e-4))
feeding = {
'user_id': 0,
'gender_id': 1,
'age_id': 2,
'job_id': 3,
'movie_id': 4,
'category_id': 5,
'movie_title': 6,
'score': 7
}
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d Batch %d Cost %.2f" % (
event.pass_id, event.batch_id, event.cost)
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.movielens.train(), buf_size=8192),
batch_size=256),
event_handler=event_handler,
feeding=feeding,
num_passes=1)
user_id = 234
movie_id = 345
user = paddle.dataset.movielens.user_info()[user_id]
movie = paddle.dataset.movielens.movie_info()[movie_id]
feature = user.value() + movie.value()
infer_dict = copy.copy(feeding)
del infer_dict['score']
prediction = paddle.infer(
output_layer=inference,
parameters=parameters,
input=[feature],
feeding=infer_dict)
print(prediction + 5) / 2
if __name__ == '__main__':
main()
source/beginners_guide/basics/06.understand_sentiment/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
# 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 sys, os
import paddle.v2 as paddle
with_gpu = os.getenv('WITH_GPU', '0') != '0'
def convolution_net(input_dim, class_dim=2, emb_dim=128, hid_dim=128):
data = paddle.layer.data("word",
paddle.data_type.integer_value_sequence(input_dim))
emb = paddle.layer.embedding(input=data, size=emb_dim)
conv_3 = paddle.networks.sequence_conv_pool(
input=emb, context_len=3, hidden_size=hid_dim)
conv_4 = paddle.networks.sequence_conv_pool(
input=emb, context_len=4, hidden_size=hid_dim)
output = paddle.layer.fc(
input=[conv_3, conv_4], size=class_dim, act=paddle.activation.Softmax())
lbl = paddle.layer.data("label", paddle.data_type.integer_value(2))
cost = paddle.layer.classification_cost(input=output, label=lbl)
return cost, output
def stacked_lstm_net(input_dim,
class_dim=2,
emb_dim=128,
hid_dim=512,
stacked_num=3):
"""
A Wrapper for sentiment classification task.
This network uses bi-directional recurrent network,
consisting three LSTM layers. This configure is referred to
the paper as following url, but use fewer layrs.
http://www.aclweb.org/anthology/P15-1109
input_dim: here is word dictionary dimension.
class_dim: number of categories.
emb_dim: dimension of word embedding.
hid_dim: dimension of hidden layer.
stacked_num: number of stacked lstm-hidden layer.
"""
assert stacked_num % 2 == 1
fc_para_attr = paddle.attr.Param(learning_rate=1e-3)
lstm_para_attr = paddle.attr.Param(initial_std=0., learning_rate=1.)
para_attr = [fc_para_attr, lstm_para_attr]
bias_attr = paddle.attr.Param(initial_std=0., l2_rate=0.)
relu = paddle.activation.Relu()
linear = paddle.activation.Linear()
data = paddle.layer.data("word",
paddle.data_type.integer_value_sequence(input_dim))
emb = paddle.layer.embedding(input=data, size=emb_dim)
fc1 = paddle.layer.fc(
input=emb, size=hid_dim, act=linear, bias_attr=bias_attr)
lstm1 = paddle.layer.lstmemory(input=fc1, act=relu, bias_attr=bias_attr)
inputs = [fc1, lstm1]
for i in range(2, stacked_num + 1):
fc = paddle.layer.fc(
input=inputs,
size=hid_dim,
act=linear,
param_attr=para_attr,
bias_attr=bias_attr)
lstm = paddle.layer.lstmemory(
input=fc, reverse=(i % 2) == 0, act=relu, bias_attr=bias_attr)
inputs = [fc, lstm]
fc_last = paddle.layer.pooling(
input=inputs[0], pooling_type=paddle.pooling.Max())
lstm_last = paddle.layer.pooling(
input=inputs[1], pooling_type=paddle.pooling.Max())
output = paddle.layer.fc(
input=[fc_last, lstm_last],
size=class_dim,
act=paddle.activation.Softmax(),
bias_attr=bias_attr,
param_attr=para_attr)
lbl = paddle.layer.data("label", paddle.data_type.integer_value(2))
cost = paddle.layer.classification_cost(input=output, label=lbl)
return cost, output
if __name__ == '__main__':
# init
paddle.init(use_gpu=with_gpu)
#data
print 'load dictionary...'
word_dict = paddle.dataset.imdb.word_dict()
dict_dim = len(word_dict)
class_dim = 2
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=1000),
batch_size=100)
test_reader = paddle.batch(
paddle.dataset.imdb.test(word_dict), batch_size=100)
feeding = {'word': 0, 'label': 1}
# network config
# Please choose the way to build the network
# by uncommenting the corresponding line.
[cost, output] = convolution_net(dict_dim, class_dim=class_dim)
# [cost, output] = stacked_lstm_net(dict_dim, class_dim=class_dim, stacked_num=3)
# create parameters
parameters = paddle.parameters.create(cost)
# create optimizer
adam_optimizer = paddle.optimizer.Adam(
learning_rate=2e-3,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
model_average=paddle.optimizer.ModelAverage(average_window=0.5))
# create trainer
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=adam_optimizer)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
with open('./params_pass_%d.tar' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader, feeding=feeding)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Save the inference topology to protobuf.
inference_topology = paddle.topology.Topology(layers=output)
with open("./inference_topology.pkl", 'wb') as f:
inference_topology.serialize_for_inference(f)
trainer.train(
reader=train_reader,
event_handler=event_handler,
feeding=feeding,
num_passes=20)
source/beginners_guide/basics/07.label_semantic_roles/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
import math, os
import numpy as np
import paddle.v2 as paddle
import paddle.v2.dataset.conll05 as conll05
import paddle.v2.evaluator as evaluator
with_gpu = os.getenv('WITH_GPU', '0') != '0'
word_dict, verb_dict, label_dict = conll05.get_dict()
word_dict_len = len(word_dict)
label_dict_len = len(label_dict)
pred_len = len(verb_dict)
mark_dict_len = 2
word_dim = 32
mark_dim = 5
hidden_dim = 512
depth = 8
default_std = 1 / math.sqrt(hidden_dim) / 3.0
mix_hidden_lr = 1e-3
def d_type(size):
return paddle.data_type.integer_value_sequence(size)
def db_lstm():
#8 features
word = paddle.layer.data(name='word_data', type=d_type(word_dict_len))
predicate = paddle.layer.data(name='verb_data', type=d_type(pred_len))
ctx_n2 = paddle.layer.data(name='ctx_n2_data', type=d_type(word_dict_len))
ctx_n1 = paddle.layer.data(name='ctx_n1_data', type=d_type(word_dict_len))
ctx_0 = paddle.layer.data(name='ctx_0_data', type=d_type(word_dict_len))
ctx_p1 = paddle.layer.data(name='ctx_p1_data', type=d_type(word_dict_len))
ctx_p2 = paddle.layer.data(name='ctx_p2_data', type=d_type(word_dict_len))
mark = paddle.layer.data(name='mark_data', type=d_type(mark_dict_len))
emb_para = paddle.attr.Param(name='emb', initial_std=0., is_static=True)
std_0 = paddle.attr.Param(initial_std=0.)
std_default = paddle.attr.Param(initial_std=default_std)
predicate_embedding = paddle.layer.embedding(
size=word_dim,
input=predicate,
param_attr=paddle.attr.Param(name='vemb', initial_std=default_std))
mark_embedding = paddle.layer.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 = [
paddle.layer.embedding(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 = paddle.layer.mixed(
size=hidden_dim,
bias_attr=std_default,
input=[
paddle.layer.full_matrix_projection(
input=emb, param_attr=std_default) for emb in emb_layers
])
lstm_para_attr = paddle.attr.Param(initial_std=0.0, learning_rate=1.0)
hidden_para_attr = paddle.attr.Param(
initial_std=default_std, learning_rate=mix_hidden_lr)
lstm_0 = paddle.layer.lstmemory(
input=hidden_0,
act=paddle.activation.Relu(),
gate_act=paddle.activation.Sigmoid(),
state_act=paddle.activation.Sigmoid(),
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):
mix_hidden = paddle.layer.mixed(
size=hidden_dim,
bias_attr=std_default,
input=[
paddle.layer.full_matrix_projection(
input=input_tmp[0], param_attr=hidden_para_attr),
paddle.layer.full_matrix_projection(
input=input_tmp[1], param_attr=lstm_para_attr)
])
lstm = paddle.layer.lstmemory(
input=mix_hidden,
act=paddle.activation.Relu(),
gate_act=paddle.activation.Sigmoid(),
state_act=paddle.activation.Sigmoid(),
reverse=((i % 2) == 1),
bias_attr=std_0,
param_attr=lstm_para_attr)
input_tmp = [mix_hidden, lstm]
feature_out = paddle.layer.mixed(
size=label_dict_len,
bias_attr=std_default,
input=[
paddle.layer.full_matrix_projection(
input=input_tmp[0], param_attr=hidden_para_attr),
paddle.layer.full_matrix_projection(
input=input_tmp[1], param_attr=lstm_para_attr)
], )
return feature_out
def load_parameter(file_name, h, w):
with open(file_name, 'rb') as f:
f.read(16) # skip header.
return np.fromfile(f, dtype=np.float32).reshape(h, w)
def main():
paddle.init(use_gpu=with_gpu, trainer_count=1)
# define network topology
feature_out = db_lstm()
target = paddle.layer.data(name='target', type=d_type(label_dict_len))
crf_cost = paddle.layer.crf(
size=label_dict_len,
input=feature_out,
label=target,
param_attr=paddle.attr.Param(
name='crfw', initial_std=default_std, learning_rate=mix_hidden_lr))
crf_dec = paddle.layer.crf_decoding(
size=label_dict_len,
input=feature_out,
label=target,
param_attr=paddle.attr.Param(name='crfw'))
evaluator.sum(input=crf_dec)
# create parameters
parameters = paddle.parameters.create(crf_cost)
parameters.set('emb', load_parameter(conll05.get_embedding(), 44068, 32))
# create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0,
learning_rate=2e-2,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
model_average=paddle.optimizer.ModelAverage(
average_window=0.5, max_average_window=10000), )
trainer = paddle.trainer.SGD(
cost=crf_cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=crf_dec)
reader = paddle.batch(
paddle.reader.shuffle(conll05.test(), buf_size=8192), batch_size=10)
test_reader = paddle.batch(
paddle.reader.shuffle(conll05.test(), buf_size=8192), batch_size=10)
feeding = {
'word_data': 0,
'ctx_n2_data': 1,
'ctx_n1_data': 2,
'ctx_0_data': 3,
'ctx_p1_data': 4,
'ctx_p2_data': 5,
'verb_data': 6,
'mark_data': 7,
'target': 8
}
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if event.batch_id % 1000 == 0:
result = trainer.test(reader=test_reader, feeding=feeding)
print "\nTest with Pass %d, Batch %d, %s" % (
event.pass_id, event.batch_id, result.metrics)
if isinstance(event, paddle.event.EndPass):
# save parameters
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader, feeding=feeding)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(
reader=reader,
event_handler=event_handler,
num_passes=1,
feeding=feeding)
test_creator = paddle.dataset.conll05.test()
test_data = []
for item in test_creator():
test_data.append(item[0:8])
if len(test_data) == 1:
break
predict = paddle.layer.crf_decoding(
size=label_dict_len,
input=feature_out,
param_attr=paddle.attr.Param(name='crfw'))
probs = paddle.infer(
output_layer=predict,
parameters=parameters,
input=test_data,
feeding=feeding,
field='id')
assert len(probs) == len(test_data[0][0])
labels_reverse = {}
for (k, v) in label_dict.items():
labels_reverse[v] = k
pre_lab = [labels_reverse[i] for i in probs]
print pre_lab
if __name__ == '__main__':
main()
source/beginners_guide/basics/08.machine_translation/train.py 已删除 100644 → 0
浏览文件 @ b2eb302f
import sys, os
import numpy as np
import paddle.v2 as paddle
with_gpu = os.getenv('WITH_GPU', '0') != '0'
def save_model(trainer, parameters, save_path):
with open(save_path, 'w') as f:
trainer.save_parameter_to_tar(f)
def seq_to_seq_net(source_dict_dim,
target_dict_dim,
is_generating,
beam_size=3,
max_length=250):
### Network Architecture
word_vector_dim = 512 # dimension of word vector
decoder_size = 512 # dimension of hidden unit of GRU decoder
encoder_size = 512 # dimension of hidden unit of GRU encoder
#### Encoder
src_word_id = paddle.layer.data(
name='source_language_word',
type=paddle.data_type.integer_value_sequence(source_dict_dim))
src_embedding = paddle.layer.embedding(
input=src_word_id, size=word_vector_dim)
src_forward = paddle.networks.simple_gru(
input=src_embedding, size=encoder_size)
src_backward = paddle.networks.simple_gru(
input=src_embedding, size=encoder_size, reverse=True)
encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
#### Decoder
encoded_proj = paddle.layer.fc(
act=paddle.activation.Linear(),
size=decoder_size,
bias_attr=False,
input=encoded_vector)
backward_first = paddle.layer.first_seq(input=src_backward)
decoder_boot = paddle.layer.fc(
size=decoder_size,
act=paddle.activation.Tanh(),
bias_attr=False,
input=backward_first)
def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
decoder_mem = paddle.layer.memory(
name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
context = paddle.networks.simple_attention(
encoded_sequence=enc_vec,
encoded_proj=enc_proj,
decoder_state=decoder_mem)
decoder_inputs = paddle.layer.fc(
act=paddle.activation.Linear(),
size=decoder_size * 3,
bias_attr=False,
input=[context, current_word],
layer_attr=paddle.attr.ExtraLayerAttribute(
error_clipping_threshold=100.0))
gru_step = paddle.layer.gru_step(
name='gru_decoder',
input=decoder_inputs,
output_mem=decoder_mem,
size=decoder_size)
out = paddle.layer.fc(
size=target_dict_dim,
bias_attr=True,
act=paddle.activation.Softmax(),
input=gru_step)
return out
decoder_group_name = 'decoder_group'
group_input1 = paddle.layer.StaticInput(input=encoded_vector)
group_input2 = paddle.layer.StaticInput(input=encoded_proj)
group_inputs = [group_input1, group_input2]
if not is_generating:
trg_embedding = paddle.layer.embedding(
input=paddle.layer.data(
name='target_language_word',
type=paddle.data_type.integer_value_sequence(target_dict_dim)),
size=word_vector_dim,
param_attr=paddle.attr.ParamAttr(name='_target_language_embedding'))
group_inputs.append(trg_embedding)
# For decoder equipped with attention mechanism, in training,
# target embeding (the groudtruth) is the data input,
# while encoded source sequence is accessed to as an unbounded memory.
# Here, the StaticInput defines a read-only memory
# for the recurrent_group.
decoder = paddle.layer.recurrent_group(
name=decoder_group_name,
step=gru_decoder_with_attention,
input=group_inputs)
lbl = paddle.layer.data(
name='target_language_next_word',
type=paddle.data_type.integer_value_sequence(target_dict_dim))
cost = paddle.layer.classification_cost(input=decoder, label=lbl)
return cost
else:
# In generation, the decoder predicts a next target word based on
# the encoded source sequence and the previous generated target word.
# The encoded source sequence (encoder's output) must be specified by
# StaticInput, which is a read-only memory.
# Embedding of the previous generated word is automatically retrieved
# by GeneratedInputs initialized by a start mark <s>.
trg_embedding = paddle.layer.GeneratedInput(
size=target_dict_dim,
embedding_name='_target_language_embedding',
embedding_size=word_vector_dim)
group_inputs.append(trg_embedding)
beam_gen = paddle.layer.beam_search(
name=decoder_group_name,
step=gru_decoder_with_attention,
input=group_inputs,
bos_id=0,
eos_id=1,
beam_size=beam_size,
max_length=max_length)
return beam_gen
def main():
paddle.init(use_gpu=with_gpu, trainer_count=1)
is_generating = False
# source and target dict dim.
dict_size = 30000
source_dict_dim = target_dict_dim = dict_size
# train the network
if not is_generating:
# define optimize method and trainer
optimizer = paddle.optimizer.Adam(
learning_rate=5e-5,
regularization=paddle.optimizer.L2Regularization(rate=8e-4))
cost = seq_to_seq_net(source_dict_dim, target_dict_dim, is_generating)
parameters = paddle.parameters.create(cost)
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=optimizer)
# define data reader
wmt14_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.wmt14.train(dict_size), buf_size=8192),
batch_size=4)
# define event_handler callback
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 10 == 0:
print("\nPass %d, Batch %d, Cost %f, %s" %
(event.pass_id, event.batch_id, event.cost,
event.metrics))
else:
sys.stdout.write('.')
sys.stdout.flush()
if not event.batch_id % 10:
save_path = 'params_pass_%05d_batch_%05d.tar' % (
event.pass_id, event.batch_id)
save_model(trainer, parameters, save_path)
if isinstance(event, paddle.event.EndPass):
# save parameters
save_path = 'params_pass_%05d.tar' % (event.pass_id)
save_model(trainer, parameters, save_path)
# start to train
trainer.train(
reader=wmt14_reader, event_handler=event_handler, num_passes=2)
# generate a english sequence to french
else:
# use the first 3 samples for generation
gen_data = []
gen_num = 3
for item in paddle.dataset.wmt14.gen(dict_size)():
gen_data.append([item[0]])
if len(gen_data) == gen_num:
break
beam_size = 3
beam_gen = seq_to_seq_net(source_dict_dim, target_dict_dim,
is_generating, beam_size)
# get the trained model, whose bleu = 26.92
parameters = paddle.dataset.wmt14.model()
# prob is the prediction probabilities, and id is the prediction word.
beam_result = paddle.infer(
output_layer=beam_gen,
parameters=parameters,
input=gen_data,
field=['prob', 'id'])
# load the dictionary
src_dict, trg_dict = paddle.dataset.wmt14.get_dict(dict_size)
gen_sen_idx = np.where(beam_result[1] == -1)[0]
assert len(gen_sen_idx) == len(gen_data) * beam_size
# -1 is the delimiter of generated sequences.
# the first element of each generated sequence its length.
start_pos, end_pos = 1, 0
for i, sample in enumerate(gen_data):
print(
" ".join([src_dict[w] for w in sample[0][1:-1]])
) # skip the start and ending mark when printing the source sentence
for j in xrange(beam_size):
end_pos = gen_sen_idx[i * beam_size + j]
print("%.4f\t%s" % (beam_result[0][i][j], " ".join(
trg_dict[w] for w in beam_result[1][start_pos:end_pos])))
start_pos = end_pos + 2
print("\n")
if __name__ == '__main__':
main()
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或