m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'develop' of github.com:baidu/Paddle into feature/serialize_deserialize_in_parameters

Browse Source
avx_docs
Yu Yang 8 years ago
parent efe53811c5 5f2cbce419
commit d34eb34d2a
41 changed files with 906 additions and 272 deletions
Show Stats Download Patch File Download Diff File

4
demo/image_classification/api_v2_train.py
Unescape View File

@ -66,7 +66,7 @@ def main():
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
result = trainer.test(
reader=paddle.reader.batched(
reader=paddle.batch(
paddle.dataset.cifar.test10(), batch_size=128),
reader_dict={'image': 0,
'label': 1})
@ -77,7 +77,7 @@ def main():
parameters=parameters,
update_equation=momentum_optimizer)
trainer.train(
reader=paddle.reader.batched(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),

4
demo/mnist/api_train_v2.py
Unescape View File

@ -111,7 +111,7 @@ def main():
result.metrics['classification_error_evaluator']))
trainer.train(
reader=paddle.reader.batched(
reader=paddle.batch(
paddle.reader.shuffle(
paddle.dataset.mnist.train(), buf_size=8192),
batch_size=128),
@ -128,7 +128,7 @@ def main():
probs = paddle.infer(
output=predict,
parameters=parameters,
reader=paddle.reader.batched(
reader=paddle.batch(
paddle.reader.firstn(
paddle.reader.map_readers(lambda item: (item[0], ),
paddle.dataset.mnist.test()),

22
demo/seqToseq/api_train_v2.py
Unescape View File

@ -72,31 +72,35 @@ def main():
# define network topology
cost = seqToseq_net_v2(source_dict_dim, target_dict_dim)
parameters = paddle.parameters.create(cost)
optimizer = paddle.optimizer.Adam(learning_rate=1e-4)
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 10 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
# define optimize method and trainer
optimizer = paddle.optimizer.Adam(learning_rate=1e-4)
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer)
# define data reader
reader_dict = {
'source_language_word': 0,
'target_language_word': 1,
'target_language_next_word': 2
}
trn_reader = paddle.reader.batched(
wmt14_reader = paddle.reader.batched(
paddle.reader.shuffle(
train_reader("data/pre-wmt14/train/train"), buf_size=8192),
batch_size=5)
# define event_handler callback
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 10 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
# start to train
trainer.train(
reader=trn_reader,
reader=wmt14_reader,
event_handler=event_handler,
num_passes=10000,
reader_dict=reader_dict)

76
demo/seqToseq/seqToseq_net_v2.py
Unescape View File

@ -1,8 +1,4 @@
import paddle.v2.activation as activation
import paddle.v2.attr as attr
import paddle.v2.data_type as data_type
import paddle.v2.layer as layer
import paddle.v2.networks as networks
import paddle.v2 as paddle
def seqToseq_net_v2(source_dict_dim, target_dict_dim):
@ -12,64 +8,70 @@ def seqToseq_net_v2(source_dict_dim, target_dict_dim):
encoder_size = 512 # dimension of hidden unit in GRU Encoder network
#### Encoder
src_word_id = layer.data(
src_word_id = paddle.layer.data(
name='source_language_word',
type=data_type.integer_value_sequence(source_dict_dim))
src_embedding = layer.embedding(
type=paddle.data_type.integer_value_sequence(source_dict_dim))
src_embedding = paddle.layer.embedding(
input=src_word_id,
size=word_vector_dim,
param_attr=attr.ParamAttr(name='_source_language_embedding'))
src_forward = networks.simple_gru(input=src_embedding, size=encoder_size)
src_backward = networks.simple_gru(
param_attr=paddle.attr.ParamAttr(name='_source_language_embedding'))
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 = layer.concat(input=[src_forward, src_backward])
encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
#### Decoder
with layer.mixed(size=decoder_size) as encoded_proj:
encoded_proj += layer.full_matrix_projection(input=encoded_vector)
with paddle.layer.mixed(size=decoder_size) as encoded_proj:
encoded_proj += paddle.layer.full_matrix_projection(
input=encoded_vector)
backward_first = layer.first_seq(input=src_backward)
backward_first = paddle.layer.first_seq(input=src_backward)
with layer.mixed(size=decoder_size, act=activation.Tanh()) as decoder_boot:
decoder_boot += layer.full_matrix_projection(input=backward_first)
with paddle.layer.mixed(
size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
decoder_boot += paddle.layer.full_matrix_projection(
input=backward_first)
def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
decoder_mem = layer.memory(
decoder_mem = paddle.layer.memory(
name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
context = networks.simple_attention(
context = paddle.networks.simple_attention(
encoded_sequence=enc_vec,
encoded_proj=enc_proj,
decoder_state=decoder_mem)
with layer.mixed(size=decoder_size * 3) as decoder_inputs:
decoder_inputs += layer.full_matrix_projection(input=context)
decoder_inputs += layer.full_matrix_projection(input=current_word)
with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
decoder_inputs += paddle.layer.full_matrix_projection(input=context)
decoder_inputs += paddle.layer.full_matrix_projection(
input=current_word)
gru_step = layer.gru_step(
gru_step = paddle.layer.gru_step(
name='gru_decoder',
input=decoder_inputs,
output_mem=decoder_mem,
size=decoder_size)
with layer.mixed(
size=target_dict_dim, bias_attr=True,
act=activation.Softmax()) as out:
out += layer.full_matrix_projection(input=gru_step)
with paddle.layer.mixed(
size=target_dict_dim,
bias_attr=True,
act=paddle.activation.Softmax()) as out:
out += paddle.layer.full_matrix_projection(input=gru_step)
return out
decoder_group_name = "decoder_group"
group_input1 = layer.StaticInputV2(input=encoded_vector, is_seq=True)
group_input2 = layer.StaticInputV2(input=encoded_proj, is_seq=True)
group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
group_input2 = paddle.layer.StaticInputV2(input=encoded_proj, is_seq=True)
group_inputs = [group_input1, group_input2]
trg_embedding = layer.embedding(
input=layer.data(
trg_embedding = paddle.layer.embedding(
input=paddle.layer.data(
name='target_language_word',
type=data_type.integer_value_sequence(target_dict_dim)),
type=paddle.data_type.integer_value_sequence(target_dict_dim)),
size=word_vector_dim,
param_attr=attr.ParamAttr(name='_target_language_embedding'))
param_attr=paddle.attr.ParamAttr(name='_target_language_embedding'))
group_inputs.append(trg_embedding)
# For decoder equipped with attention mechanism, in training,
@ -77,14 +79,14 @@ def seqToseq_net_v2(source_dict_dim, target_dict_dim):
# while encoded source sequence is accessed to as an unbounded memory.
# Here, the StaticInput defines a read-only memory
# for the recurrent_group.
decoder = layer.recurrent_group(
decoder = paddle.layer.recurrent_group(
name=decoder_group_name,
step=gru_decoder_with_attention,
input=group_inputs)
lbl = layer.data(
lbl = paddle.layer.data(
name='target_language_next_word',
type=data_type.integer_value_sequence(target_dict_dim))
cost = layer.classification_cost(input=decoder, label=lbl)
type=paddle.data_type.integer_value_sequence(target_dict_dim))
cost = paddle.layer.classification_cost(input=decoder, label=lbl)
return cost

80
demo/word2vec/train_v2.py
Unescape View File

@ -0,0 +1,80 @@
import math
import paddle.v2 as paddle
dictsize = 1953
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
def main():
paddle.init(use_gpu=False, trainer_count=1)
word_dict = paddle.dataset.imikolov.build_dict()
dict_size = len(word_dict)
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())
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
result = trainer.test(
paddle.batch(
paddle.dataset.imikolov.test(word_dict, N), 32))
print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics,
result.metrics)
cost = paddle.layer.classification_cost(input=predictword, label=nextword)
parameters = paddle.parameters.create(cost)
adam_optimizer = paddle.optimizer.Adam(
learning_rate=3e-3,
regularization=paddle.optimizer.L2Regularization(8e-4))
trainer = paddle.trainer.SGD(cost, parameters, adam_optimizer)
trainer.train(
paddle.batch(paddle.dataset.imikolov.train(word_dict, N), 32),
num_passes=30,
event_handler=event_handler)
if __name__ == '__main__':
main()

26
doc/api/index_cn.rst
Unescape View File

@ -1,2 +1,26 @@
API
===
===
模型配置 API
------------
.. toctree::
:maxdepth: 1
v2/model_configs.rst
数据 API
--------
.. toctree::
:maxdepth: 1
v2/data.rst
训练 API
--------
.. toctree::
:maxdepth: 1
v2/run_logic.rst

18
doc/api/index_en.rst
Unescape View File

@ -7,4 +7,20 @@ Model Config API
.. toctree::
:maxdepth: 1
v2/model_configs.rst
v2/model_configs.rst
Data API
--------
.. toctree::
:maxdepth: 1
v2/data.rst
Train API
---------
.. toctree::
:maxdepth: 1
v2/run_logic.rst

93
doc/api/v2/data.rst
Unescape View File

@ -0,0 +1,93 @@
================
Data Related API
================
#########
DataTypes
#########
.. automodule:: paddle.v2.data_type
:members:
##########
DataFeeder
##########
.. automodule:: paddle.v2.data_feeder
:members:
######
Reader
######
.. automodule:: paddle.v2.reader
:members:
.. automodule:: paddle.v2.reader.creator
:members:
#########
minibatch
#########
.. automodule:: paddle.v2.minibatch
:members:
#######
Dataset
#######
.. automodule:: paddle.v2.dataset
:members:
mnist
+++++
.. automodule:: paddle.v2.dataset.mnist
:members:
cifar
+++++
.. automodule:: paddle.v2.dataset.cifar
:members:
conll05
+++++++
.. automodule:: paddle.v2.dataset.conll05
:members:
imdb
++++
.. automodule:: paddle.v2.dataset.imdb
:members:
imikolov
++++++++
.. automodule:: paddle.v2.dataset.imikolov
:members:
movielens
+++++++++
.. automodule:: paddle.v2.dataset.movielens
:members:
sentiment
+++++++++
.. automodule:: paddle.v2.dataset.sentiment
:members:
uci_housing
+++++++++++
.. automodule:: paddle.v2.dataset.uci_housing
:members:

40
doc/api/v2/model_configs.rst
Unescape View File

@ -1,6 +1,46 @@
#########################
Configuration Related API
#########################
======
Layers
======
.. automodule:: paddle.v2.layer
:members:
==========
Attributes
==========
.. automodule:: paddle.v2.attr
:members:
===========
Activations
===========
.. automodule:: paddle.v2.activation
:members:
========
Poolings
========
.. automodule:: paddle.v2.pooling
:members:
========
Networks
========
.. automodule:: paddle.v2.networks
:members:
==========
Optimizers
==========
.. automodule:: paddle.v2.optimizer
:members:

26
doc/api/v2/run_logic.rst
Unescape View File

@ -0,0 +1,26 @@
###########
Trainer API
###########
==========
Parameters
==========
.. automodule:: paddle.v2.parameters
:members:
=======
Trainer
=======
.. automodule:: paddle.v2.trainer
:members:
=====
Event
=====
.. automodule:: paddle.v2.event
:members:

74
doc/design/reader/README.md
Unescape View File

@ -23,19 +23,19 @@ An example implementation for single item data reader creator:
```python
def reader_creator_random_image(width, height):
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height)
return reader
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height)
return reader
```
An example implementation for multiple item data reader creator:
```python
def reader_creator_random_imageand_label(widht, height, label):
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height), label
return reader
def reader_creator_random_image_and_label(width, height, label):
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height), label
return reader
```
## Batch Reader Interface
@ -74,11 +74,11 @@ mnist_train_batch_reader = paddle.batch(mnist_train, 128)
Also easy to create custom batch reader:
```python
def custom_batch_reader():
while True:
batch = []
for i in xrange(128):
batch.append((numpy.random.uniform(-1, 1, 28*28),)) # note that it's a tuple being appended.
yield batch
while True:
batch = []
for i in xrange(128):
batch.append((numpy.random.uniform(-1, 1, 28*28),)) # note that it's a tuple being appended.
yield batch
mnist_random_image_batch_reader = custom_batch_reader
```
@ -123,16 +123,16 @@ We can do:
```python
def reader_creator_random_image(width, height):
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height)
return reader
def reader():
while True:
yield numpy.random.uniform(-1, 1, size=width*height)
return reader
def reader_creator_bool(t):
def reader:
while True:
yield t
return reader
def reader:
while True:
yield t
return reader
true_reader = reader_creator_bool(True)
false_reader = reader_creator_bool(False)
@ -172,18 +172,18 @@ We decided to use dictionary (`{"image":0, "label":1}`) instead of list (`["imag
```python
def image_reader_creator(image_path, label_path, n):
def reader():
f = open(image_path)
l = open(label_path)
images = numpy.fromfile(
f, 'ubyte', count=n * 28 * 28).reshape((n, 28 * 28)).astype('float32')
images = images / 255.0 * 2.0 - 1.0
labels = numpy.fromfile(l, 'ubyte', count=n).astype("int")
for i in xrange(n):
yield images[i, :], labels[i] # a single entry of data is created each time
f.close()
l.close()
return reader
def reader():
f = open(image_path)
l = open(label_path)
images = numpy.fromfile(
f, 'ubyte', count=n * 28 * 28).reshape((n, 28 * 28)).astype('float32')
images = images / 255.0 * 2.0 - 1.0
labels = numpy.fromfile(l, 'ubyte', count=n).astype("int")
for i in xrange(n):
yield images[i, :], labels[i] # a single entry of data is created each time
f.close()
l.close()
return reader
# images_reader_creator creates a reader
reader = image_reader_creator("/path/to/image_file", "/path/to/label_file", 1024)
@ -196,7 +196,7 @@ An example implementation of paddle.train could be:
```python
def train(batch_reader, mapping, batch_size, total_pass):
for pass_idx in range(total_pass):
for mini_batch in batch_reader(): # this loop will never end in online learning.
do_forward_backward(mini_batch, mapping)
for pass_idx in range(total_pass):
for mini_batch in batch_reader(): # this loop will never end in online learning.
do_forward_backward(mini_batch, mapping)
```

78
doc/howto/usage/k8s/k8s_distributed_cn.md
Unescape View File

@ -43,22 +43,55 @@ docker push [YOUR_REPO]/paddle:mypaddle
注意上述命令中`[YOUR_REPO]`表示读者所使用的Docker镜像仓库地址，读者需要替换成自己使用的仓库地址。下文使用`[YOUR_REPO]/paddle:mypaddle`这个地址来表示此步骤所构建出的镜像。
### 上传训练文件
### 准备训练数据
本文使用PaddlePaddle官方的[recommendation demo](http://www.paddlepaddle.org/doc/demo/index.html#recommendation)作为这次训练的内容，我们将训练文件与数据放在一个job name命名的目录中，上传到volume所在的共享存储（使用不同分布式存储会有不同的挂载方式，需要要先挂载这个目录，然后拷贝数据）。完成后volume中的文件内容大致如下：
这里我们通过在Kubernetes集群上启动一个Job来下载并切割数据，也可以通过修改[k8s_train](./src/k8s_train/README.md)的内容来定制image.
```bash
[root@paddle-kubernetes-node0 mfs]# tree -d
在启动Job之前，需要根据不同的分布式存储来绑定一个[persistentVolumeClaim](https://kubernetes.io/docs/user-guide/persistent-volumes/),生成的数据将会存储在这个volume下.
```yaml
apiVersion: batch/v1
kind: Job
metadata:
name: paddle-data
spec:
template:
metadata:
name: pi
spec:
hostNetwork: true
containers:
- name: paddle-data
image: paddledev/paddle-tutorial:k8s_data
imagePullPolicy: Always
volumeMounts:
- mountPath: "/mnt"
name: nfs
env:
- name: OUT_DIR
value: /home/work/mfs/paddle-cluster-job
- name: SPLIT_COUNT
value: "3"
volumes:
- name: nfs
persistentVolumeClaim:
claimName: mfs
restartPolicy: Never
```
完成后volume中的文件内容大致如下：
```base
[root@paddle-kubernetes-node0 nfsdir]$ tree -d
.
└── paddle-cluster-job
├── data
│   ├── 0
│   │
│   ├── 1
│   │
│   └── 2
├── output
└── recommendation
`-- paddle-cluster-job
|-- 0
| `-- data
|-- 1
| `-- data
|-- 2
| `-- data
|-- output
|-- quick_start
```
目录中paddle-cluster-job是本次训练对应的job name，本次训练要求有3个PaddlePaddle节点，在paddle-cluster-job/data目录中存放切分好的数据，文件夹0，1，2分别代表3个节点的trainer_id。recommendation文件夹内存放训练文件，output文件夹存放训练结果与日志。
@ -118,15 +151,16 @@ spec:
`env`字段表示容器的环境变量，我们将`paddle`运行的一些参数通过这种方式传递到容器内。
`JOB_PATH`表示共享存储挂载的路径，`JOB_NAME`表示job名字，`TRAIN_CONFIG_DIR`表示本次训练文件所在目录，这三个变量组合就可以找到本次训练需要的文件路径。
`CONF_PADDLE_NIC`表示`paddle pserver`进程需要的`--nics`参数，即网卡名
`CONF_PADDLE_PORT`表示`paddle pserver`的`--port`参数，`CONF_PADDLE_PORTS_NUM`则表示稠密更新的端口数量，也就是`--ports_num`参数。
`CONF_PADDLE_PORTS_NUM_SPARSE`表示稀疏更新的端口数量，也就是`--ports_num_for_sparse`参数。
`CONF_PADDLE_GRADIENT_NUM`表示训练节点数量，即`--num_gradient_servers`参数
环境变量 | 说明
--- | ---
JOB_PATH | 共享存储挂在的路径
JOB_NAME | Job的名字
TRAIN_CONFIG_DIR | 本次训练文件所在目录，与JOB_PATH,JOB_NAME组合可以找到本次训练需要的文件路径
CONF_PADDLE_NIC | `paddle pserver`进程需要的`--nics`参数，即网卡名
CONF_PADDLE_PORT | `paddle paserver`的`--port`参数
CONF_PADDLE_PORTS_NUM | 稠密更新的端口数量，即`--ports_num`参数
CONF_PADDLE_PORTS_NUM_SPARSE | 稀疏更新的端口数量，即`--ports_num_for_sparse`参数
CONF_PADDLE_GRADIENT_NUM | 训练节点数量，即`--num_gradient_servers参数`
这些参数的具体描述，读者可以查看[这里](http://www.paddlepaddle.org/doc/ui/cmd_argument/detail_introduction.html#parameter-server-and-distributed-communication)。

93
python/paddle/trainer/PyDataProvider2.py
Unescape View File

@ -45,6 +45,23 @@ class CacheType(object):
class InputType(object):
"""
InputType is the base class for paddle input types.
.. note::
this is a base class, and should never be used by user.
:param dim: dimension of input. If the input is an integer, it means the
value range. Otherwise, it means the size of layer.
:type dim: int
:param seq_type: sequence type of input. 0 means it is not a sequence. 1
means it is a variable length sequence. 2 means it is a
nested sequence.
:type seq_type: int
:param type: data type of input.
:type type: int
"""
__slots__ = ['dim', 'seq_type', 'type']
def __init__(self, dim, seq_type, tp):
@ -54,20 +71,61 @@ class InputType(object):
def dense_slot(dim, seq_type=SequenceType.NO_SEQUENCE):
"""
Dense Vector. It means the input feature is dense float vector. For example,
if the input is an image with 28*28 pixels, the input of Paddle neural
network should be a dense vector with dimension 784.
:param dim: dimension of this vector.
:type dim: int
:param seq_type: sequence type of input.
:type seq_type: int
:return: An input type object.
:rtype: InputType
"""
return InputType(dim, seq_type, DataType.Dense)
def sparse_non_value_slot(dim, seq_type=SequenceType.NO_SEQUENCE):
"""
Sparse binary vector. It means the input feature is a sparse vector and the
every element in this vector is either zero or one.
:param dim: dimension of this vector.
:type dim: int
:param seq_type: sequence type of this input.
:type seq_type: int
:return: An input type object.
:rtype: InputType
"""
return InputType(dim, seq_type, DataType.SparseNonValue)
def sparse_value_slot(dim, seq_type=SequenceType.NO_SEQUENCE):
"""
Sparse vector. It means the input feature is a sparse vector. Most of the
elements in this vector are zero, others could be any float value.
:param dim: dimension of this vector.
:type dim: int
:param seq_type: sequence type of this input.
:type seq_type: int
:return: An input type object.
:rtype: InputType
"""
return InputType(dim, seq_type, DataType.SparseValue)
def index_slot(value_range, seq_type=SequenceType.NO_SEQUENCE):
"""Data type of integer.
"""
Data type of integer.
:param seq_type: sequence type of this input.
:type seq_type: int
:param value_range: range of this integer.
:type value_range: int
:return: An input type object
:rtype: InputType
"""
return InputType(value_range, seq_type, DataType.Index)
@ -76,10 +134,17 @@ dense_vector = dense_slot
sparse_binary_vector = sparse_non_value_slot
sparse_vector = sparse_value_slot
integer_value = index_slot
integer_value.__doc__ = index_slot.__doc__
def dense_vector_sequence(dim):
"""
Data type of a sequence of dense vector.
:param dim: dimension of dense vector.
:type dim: int
:return: An input type object
:rtype: InputType
"""
return dense_vector(dim, seq_type=SequenceType.SEQUENCE)
@ -88,6 +153,15 @@ def dense_vector_sub_sequence(dim):
def sparse_binary_vector_sequence(dim):
"""
Data type of a sequence of sparse vector, which every element is either zero
or one.
:param dim: dimension of sparse vector.
:type dim: int
:return: An input type object
:rtype: InputType
"""
return sparse_binary_vector(dim, seq_type=SequenceType.SEQUENCE)
@ -96,6 +170,15 @@ def sparse_binary_vector_sub_sequence(dim):
def sparse_vector_sequence(dim):
"""
Data type of a sequence of sparse vector, which most elements are zero,
others could be any float value.
:param dim: dimension of sparse vector.
:type dim: int
:return: An input type object
:rtype: InputType
"""
return sparse_vector(dim, seq_type=SequenceType.SEQUENCE)
@ -104,8 +187,11 @@ def sparse_vector_sub_sequence(dim):
def integer_value_sequence(value_range):
"""Data type of a sequence of integer.
"""
Data type of a sequence of integer.
:param value_range: range of each element.
:type value_range: int
"""
return integer_value(value_range, seq_type=SequenceType.SEQUENCE)
@ -115,7 +201,6 @@ def integer_value_sub_sequence(dim):
integer_sequence = integer_value_sequence
integer_sequence.__doc__ = integer_value_sequence.__doc__
class SingleSlotWrapper(object):

7
python/paddle/trainer_config_helpers/layers.py
Unescape View File

@ -795,17 +795,16 @@ def data_layer(name, size, height=None, width=None, layer_attr=None):
.. code-block:: python
data = data_layer(name="input",
size=1000)
data = data_layer(name="input", size=1000)
:param name: Name of this data layer.
:type name: basestring
:param size: Size of this data layer.
:type size: int
:param height: Height of this data layer, used for image
:type size: int|None
:type height: int|None
:param width: Width of this data layer, used for image
:type size: int|None
:type width: int|None
:param layer_attr: Extra Layer Attribute.
:type layer_attr: ExtraLayerAttribute.
:return: LayerOutput object.

2
python/paddle/v2/__init__.py
Unescape View File

@ -28,6 +28,7 @@ import pooling
import inference
import networks
import py_paddle.swig_paddle as api
import minibatch
__all__ = [
'optimizer', 'layer', 'activation', 'parameters', 'init', 'trainer',
@ -45,3 +46,4 @@ def init(**kwargs):
infer = inference.infer
batch = minibatch.batch

31
python/paddle/v2/activation.py
Unescape View File

@ -12,26 +12,15 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from paddle.trainer_config_helpers.activations import *
import paddle.trainer_config_helpers.activations
import copy
__all__ = [
"Base", "Tanh", "Sigmoid", "Softmax", "Identity", "Linear",
'SequenceSoftmax', "Exp", "Relu", "BRelu", "SoftRelu", "STanh", "Abs",
"Square", "Log"
]
__all__ = []
Base = BaseActivation
Tanh = TanhActivation
Sigmoid = SigmoidActivation
Softmax = SoftmaxActivation
SequenceSoftmax = SequenceSoftmaxActivation
Identity = IdentityActivation
Linear = Identity
Relu = ReluActivation
BRelu = BReluActivation
SoftRelu = SoftReluActivation
STanh = STanhActivation
Abs = AbsActivation
Square = SquareActivation
Exp = ExpActivation
Log = LogActivation
suffix = 'Activation'
for act in paddle.trainer_config_helpers.activations.__all__:
new_name = act[:-len(suffix)]
globals()[new_name] = copy.copy(
getattr(paddle.trainer_config_helpers.activations, act))
globals()[new_name].__name__ = new_name
__all__.append(new_name)

10
python/paddle/v2/attr.py
Unescape View File

@ -12,12 +12,16 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from paddle.trainer_config_helpers.attrs import *
import paddle.trainer_config_helpers.attrs
__all__ = [
"Param",
"Extra",
]
Param = ParameterAttribute
Extra = ExtraLayerAttribute
Param = paddle.trainer_config_helpers.attrs.ParameterAttribute
Extra = paddle.trainer_config_helpers.attrs.ExtraLayerAttribute
for each in paddle.trainer_config_helpers.attrs.__all__:
globals()[each] = getattr(paddle.trainer_config_helpers.attrs, each)
__all__.append(each)

47
python/paddle/v2/config_base.py
Unescape View File

@ -13,12 +13,55 @@
# limitations under the License.
import collections
import re
from paddle.trainer_config_helpers.default_decorators import wrap_name_default
import paddle.trainer_config_helpers as conf_helps
class LayerType(type):
def __new__(cls, name, bases, attrs):
method_name = attrs.get('METHOD_NAME', None)
if method_name is not None:
method = getattr(conf_helps, method_name)
if method.__doc__ is not None:
mapper = attrs.get("__map_docstr__", None)
if mapper is not None:
attrs['__doc__'] = LayerType.__map_docstr__(
mapper(method.__doc__),
method_name=method_name,
name=name)
else:
attrs['__doc__'] = LayerType.__map_docstr__(
method.__doc__, method_name=method_name, name=name)
return super(LayerType, cls).__new__(cls, name, bases, attrs)
@staticmethod
def __map_docstr__(doc, name, method_name):
assert isinstance(doc, basestring)
# replace LayerOutput to paddle.v2.config_base.Layer
doc = doc.replace("LayerOutput", "paddle.v2.config_base.Layer")
doc = doc.replace('ParameterAttribute',
'paddle.v2.attr.ParameterAttribute')
doc = re.sub(r'ExtraLayerAttribute[^\s]?',
'paddle.v2.attr.ExtraAttribute', doc)
# xxx_layer to xxx
doc = re.sub(r"(?P<name>[a-z]+)_layer", r"\g<name>", doc)
# XxxxActivation to paddle.v2.Activation.Xxxx
doc = re.sub(r"(?P<name>[A-Z][a-zA-Z]+)Activation",
r"paddle.v2.Activation.\g<name>", doc)
# TODO(yuyang18): Add more rules if needed.
return doc
class Layer(object):
__metaclass__ = LayerType
def __init__(self, name=None, parent_layers=None):
assert isinstance(parent_layers, dict)
self.name = name
@ -80,6 +123,8 @@ def __convert_to_v2__(method_name, parent_names, is_default_name=True):
wrapper = None
class V2LayerImpl(Layer):
METHOD_NAME = method_name
def __init__(self, **kwargs):
parent_layers = dict()
other_kwargs = dict()

49
python/paddle/v2/data_feeder.py
Unescape View File

@ -12,8 +12,8 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from py_paddle import swig_paddle
from py_paddle import DataProviderConverter
import data_type
__all__ = ['DataFeeder']
@ -29,7 +29,10 @@ class DataFeeder(DataProviderConverter):
to feed it to C++ interface.
The example usage:
.. code-block:: python
data_types = [('image', paddle.data_type.dense_vector(784)),
('label', paddle.data_type.integer_value(10))]
reader_dict = {'image':0, 'label':1}
@ -43,20 +46,24 @@ class DataFeeder(DataProviderConverter):
# [ [1.0,2.0,3.0,4.0], 5, [6,7,8] ] # second sample
# ]
arg = feeder(minibatch_data)
.. note::
This module is for internal use only. Users should use the `reader`
interface.
:param data_types: A list to specify data name and type. Each item is
a tuple of (data_name, data_type).
:type data_types: list
:param reader_dict: A dictionary to specify the position of each data
in the input data.
:type reader_dict: dict
"""
def __init__(self, data_types, reader_dict):
"""
:param data_types: A list to specify data name and type. Each item is
a tuple of (data_name, data_type). For example:
[('image', paddle.data_type.dense_vector(784)),
('label', paddle.data_type.integer_value(10))]
:type data_types: A list of tuple
:param reader_dict: A dictionary to specify the position of each data
in the input data.
:type reader_dict: dict()
"""
self.input_names = []
input_types = []
self.reader_dict = reader_dict
@ -70,22 +77,12 @@ class DataFeeder(DataProviderConverter):
"""
:param dat: A list of mini-batch data. Each sample is a list or tuple
one feature or multiple features.
for example:
[
([0.2, 0.2], ), # first sample
([0.8, 0.3], ), # second sample
]
or,
[
[[0.2, 0.2], ], # first sample
[[0.8, 0.3], ], # second sample
]
:type dat: List
:type dat: list
:param argument: An Arguments object contains this mini-batch data with
one or multiple features. The Arguments definition is
in the API.
:type argument: swig_paddle.Arguments
:type argument: py_paddle.swig_paddle.Arguments
"""
def reorder_data(data):

16
python/paddle/v2/data_type.py
Unescape View File

@ -12,11 +12,15 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from paddle.trainer.PyDataProvider2 import \
InputType, DataType, dense_vector, sparse_binary_vector,\
sparse_vector, integer_value, integer_value_sequence
import paddle.trainer.PyDataProvider2 as pydp2
__all__ = [
'InputType', 'DataType', 'dense_vector', 'sparse_binary_vector',
'sparse_vector', 'integer_value', 'integer_value_sequence'
import_list = [
nm for nm in dir(pydp2)
if '_' in nm and nm[0] != '_' and ('value' in nm or 'vector' in nm)
]
import_list.extend(['InputType'])
for nm in import_list:
globals()[nm] = getattr(pydp2, nm)
__all__ = import_list

3
python/paddle/v2/dataset/__init__.py
Unescape View File

@ -11,6 +11,9 @@
# 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.
"""
Dataset package.
"""
import mnist
import imikolov

2
python/paddle/v2/dataset/cifar.py
Unescape View File

@ -13,6 +13,8 @@
# limitations under the License.
"""
CIFAR dataset: https://www.cs.toronto.edu/~kriz/cifar.html
TODO(yuyang18): Complete the comments.
"""
import cPickle

6
python/paddle/v2/dataset/conll05.py
Unescape View File

@ -16,15 +16,17 @@ import tarfile
import gzip
import itertools
from common import download
__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.
TODO(yuyang18): Complete comments.
"""
__all__ = ['test, get_dict', 'get_embedding']
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'

2
python/paddle/v2/dataset/imdb.py
Unescape View File

@ -13,6 +13,8 @@
# limitations under the License.
"""
IMDB dataset: http://ai.stanford.edu/%7Eamaas/data/sentiment/aclImdb_v1.tar.gz
TODO(yuyang18): Complete comments.
"""
import paddle.v2.dataset.common

2
python/paddle/v2/dataset/imikolov.py
Unescape View File

@ -13,6 +13,8 @@
# limitations under the License.
"""
imikolov's simple dataset: http://www.fit.vutbr.cz/~imikolov/rnnlm/
Complete comments.
"""
import paddle.v2.dataset.common
import tarfile

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

Write Preview
Loading…
Cancel
Save