Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
OPTHREE
Paddle
提交
22956530
P
Paddle
项目概览
OPTHREE
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
22956530
编写于
12月 29, 2018
作者:
M
minqiyang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Polish PyLayers
test=develop
上级
0f6ef8ed
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
67 addition
and
124 deletion
+67
-124
python/paddle/fluid/imperative/layers.py
python/paddle/fluid/imperative/layers.py
+1
-13
python/paddle/fluid/imperative/nn.py
python/paddle/fluid/imperative/nn.py
+19
-19
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+44
-88
python/paddle/fluid/tests/unittests/test_imperative.py
python/paddle/fluid/tests/unittests/test_imperative.py
+1
-1
python/paddle/fluid/tests/unittests/test_imperative_optimizer.py
...paddle/fluid/tests/unittests/test_imperative_optimizer.py
+2
-3
未找到文件。
python/paddle/fluid/imperative/layers.py
浏览文件 @
22956530
...
...
@@ -24,19 +24,7 @@ __all__ = ['PyLayer']
class
PyLayer
(
core
.
Layer
):
def
__init__
(
self
,
dtype
=
core
.
VarDesc
.
VarType
.
FP32
,
param_attr
=
None
,
bias_attr
=
None
,
name
=
None
):
from
..layer_helper
import
LayerHelper
self
.
_helper
=
LayerHelper
(
type
(
self
).
__name__
,
param_attr
=
param_attr
,
bias_attr
=
bias_attr
,
dtype
=
dtype
,
name
=
name
)
def
__init__
(
self
,
dtype
=
core
.
VarDesc
.
VarType
.
FP32
,
name
=
None
):
self
.
_once_built
=
False
self
.
_dtype
=
dtype
...
...
python/paddle/fluid/imperative/nn.py
浏览文件 @
22956530
...
...
@@ -46,8 +46,15 @@ class Conv2D(layers.PyLayer):
name
=
None
,
dtype
=
core
.
VarDesc
.
VarType
.
FP32
):
assert
param_attr
is
not
False
,
"param_attr should not be False here."
super
(
Conv2D
,
self
).
__init__
(
param_attr
=
param_attr
,
bias_attr
=
bias_attr
,
name
=
name
,
dtype
=
dtype
)
super
(
Conv2D
,
self
).
__init__
(
name
=
name
,
dtype
=
dtype
)
from
..layer_helper
import
LayerHelper
self
.
_helper
=
LayerHelper
(
type
(
self
).
__name__
,
param_attr
=
param_attr
,
bias_attr
=
bias_attr
,
dtype
=
dtype
,
name
=
name
)
self
.
_groups
=
groups
self
.
_stride
=
utils
.
convert_to_list
(
stride
,
2
,
'stride'
)
...
...
@@ -163,6 +170,9 @@ class Pool2D(layers.PyLayer):
super
(
Pool2D
,
self
).
__init__
(
name
=
name
,
dtype
=
dtype
)
from
..layer_helper
import
LayerHelper
self
.
_helper
=
LayerHelper
(
type
(
self
).
__name__
,
dtype
=
dtype
,
name
=
name
)
self
.
_pool_type
=
pool_type
self
.
_pool_size
=
utils
.
convert_to_list
(
pool_size
,
2
,
'pool_size'
)
self
.
_pool_padding
=
utils
.
convert_to_list
(
pool_padding
,
2
,
...
...
@@ -197,32 +207,22 @@ class Pool2D(layers.PyLayer):
class
FC
(
layers
.
PyLayer
):
def
__init__
(
self
,
size_in
,
size_out
,
num_flatten_dims
=
1
,
size
,
param_attr
=
None
,
num_flatten_dims
=
1
,
dtype
=
core
.
VarDesc
.
VarType
.
FP32
):
super
(
FC
,
self
).
__init__
(
param_attr
=
param_attr
,
dtype
=
dtype
)
self
.
_size_in
=
size_in
self
.
_size_out
=
size_out
super
(
FC
,
self
).
__init__
()
self
.
_size
=
size
self
.
_num_flatten_dims
=
num_flatten_dims
self
.
_dtype
=
dtype
if
self
.
_size_in
!=
-
1
:
self
.
_w
=
self
.
_helper
.
create_parameter
(
attr
=
self
.
_helper
.
param_attr
,
shape
=
[
size_in
,
size_out
],
dtype
=
self
.
_dtype
,
is_bias
=
False
)
from
..layer_helper
import
LayerHelper
self
.
_helper
=
LayerHelper
(
'FC'
,
param_attr
=
param_attr
)
def
_build_once
(
self
,
input
):
if
self
.
_size_in
!=
-
1
:
return
input_shape
=
input
.
shape
param_shape
=
[
reduce
(
lambda
a
,
b
:
a
*
b
,
input_shape
[
self
.
_num_flatten_dims
:],
1
)
]
+
[
self
.
_size
_out
]
]
+
[
self
.
_size
]
self
.
_w
=
self
.
_helper
.
create_parameter
(
attr
=
self
.
_helper
.
param_attr
,
shape
=
param_shape
,
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
22956530
...
...
@@ -502,22 +502,22 @@ def lstm(input,
If Device is GPU, This op will use cudnn LSTM implementation
A four-gate Long Short-Term Memory network with no peephole connections.
In the forward pass the output ht and cell output ct for a given iteration can be computed from the recurrent input ht-1,
In the forward pass the output ht and cell output ct for a given iteration can be computed from the recurrent input ht-1,
the cell input ct-1 and the previous layer input xt given matrices W, R and biases bW, bR from the following equations:
.. math::
i_t &= \sigma(W_{ix}x_{t} + W_{ih}h_{t-1} + bx_i + bh_i)
f_t &= \sigma(W_{fx}x_{t} + W_{fh}h_{t-1} + bx_f + bh_f)
o_t &= \sigma(W_{ox}x_{t} + W_{oh}h_{t-1} + bx_o + bh_o)
i_t &= \sigma(W_{ix}x_{t} + W_{ih}h_{t-1} + bx_i + bh_i)
f_t &= \sigma(W_{fx}x_{t} + W_{fh}h_{t-1} + bx_f + bh_f)
o_t &= \sigma(W_{ox}x_{t} + W_{oh}h_{t-1} + bx_o + bh_o)
\\
tilde{c_t} &= tanh(W_{cx}x_t + W_{ch}h_{t-1} + bx_c + bh_c)
c_t &= f_t \odot c_{t-1} + i_t \odot
\\
tilde{c_t}
h_t &= o_t \odot tanh(c_t)
c_t &= f_t \odot c_{t-1} + i_t \odot
\\
tilde{c_t}
h_t &= o_t \odot tanh(c_t)
- $W$ terms denote weight matrices (e.g. $W_{ix}$ is the matrix
of weights from the input gate to the input)
...
...
@@ -531,19 +531,19 @@ def lstm(input,
- :math:`
\\
tilde{c_t}` is also called candidate hidden state,
which is computed based on the current input and the previous hidden state.
Where sigmoid is the sigmoid operator: :math:`sigmoid(x) = 1 / (1 + e^{-x})` , * represents a point-wise multiplication,
Where sigmoid is the sigmoid operator: :math:`sigmoid(x) = 1 / (1 + e^{-x})` , * represents a point-wise multiplication,
X represensts a matrix multiplication
Args:
input (Variable): LSTM input tensor, shape MUST be ( seq_len x batch_size x input_size )
init_h(Variable): The initial hidden state of the LSTM
init_h(Variable): The initial hidden state of the LSTM
This is a tensor with shape ( num_layers x batch_size x hidden_size)
if is_bidirec = True, shape should be ( num_layers*2 x batch_size x hidden_size)
init_c(Variable): The initial cell state of the LSTM.
This is a tensor with shape ( num_layers x batch_size x hidden_size )
if is_bidirec = True, shape should be ( num_layers*2 x batch_size x hidden_size)
max_len (int): max length of LSTM. the first dim of input tensor CAN NOT greater than max_len
max_len (int): max length of LSTM. the first dim of input tensor CAN NOT greater than max_len
hidden_size (int): hidden size of the LSTM
num_layers (int): total layers number of the LSTM
dropout_prob(float|0.0): dropout prob, dropout ONLY work between rnn layers, NOT between time steps
...
...
@@ -558,18 +558,18 @@ def lstm(input,
Returns:
rnn_out(Tensor),last_h(Tensor),last_c(Tensor):
rnn_out(Tensor),last_h(Tensor),last_c(Tensor):
Three tensors, rnn_out, last_h, last_c:
- rnn_out is result of LSTM hidden, shape is (seq_len x batch_size x hidden_size)
\
if is_bidirec set to True, shape will be ( seq_len x batch_sze x hidden_size*2)
- last_h is the hidden state of the last step of LSTM
\
shape is ( num_layers x batch_size x hidden_size )
\
if is_bidirec set to True, shape will be ( num_layers*2 x batch_size x hidden_size)
if is_bidirec set to True, shape will be ( num_layers*2 x batch_size x hidden_size)
- last_c(Tensor): the cell state of the last step of LSTM
\
shape is ( num_layers x batch_size x hidden_size )
\
if is_bidirec set to True, shape will be ( num_layers*2 x batch_size x hidden_size)
if is_bidirec set to True, shape will be ( num_layers*2 x batch_size x hidden_size)
Examples:
...
...
@@ -1255,7 +1255,7 @@ def dropout(x,
(mask is a tensor same shape with input, value is 0 or 1
ratio of 0 is dropout_prob)
Returns:
Variable: A tensor variable is the shape with `x`.
...
...
@@ -1346,10 +1346,10 @@ def cross_entropy(input, label, soft_label=False, ignore_index=kIgnoreIndex):
ValueError:
1. the 1st dimension of ``input`` and ``label`` are not equal.
2. when ``soft_label == True``, and the 2nd dimension of
``input`` and ``label`` are not equal.
3. when ``soft_label == False``, and the 2nd dimension of
``label`` is not 1.
...
...
@@ -1471,7 +1471,7 @@ def chunk_eval(input,
This function computes and outputs the precision, recall and
F1-score of chunk detection.
For some basics of chunking, please refer to
For some basics of chunking, please refer to
`Chunking with Support Vector Machines <https://aclanthology.info/pdf/N/N01/N01-1025.pdf>`_ .
ChunkEvalOp computes the precision, recall, and F1-score of chunk detection,
...
...
@@ -2306,7 +2306,7 @@ def sequence_slice(input, offset, length, name=None):
out.lod = [[2, 1]],
out.dims = (3, 2).
Note:
Note:
The first dimension size of **input**, **offset** and **length**
should be equal. The **offset** should start from 0.
...
...
@@ -4678,7 +4678,7 @@ def ctc_greedy_decoder(input, blank, name=None):
[0.5, 0.1, 0.3, 0.1]]
input.lod = [[4, 4]]
Computation:
step1: Apply argmax to first input sequence which is input.data[0:4]. Then we get:
...
...
@@ -4712,7 +4712,7 @@ def ctc_greedy_decoder(input, blank, name=None):
Variable: CTC greedy decode result which is a 2-D tensor with shape [Lp, 1].
\
'Lp' is the sum if all output sequences' length. If all the sequences
\
in result were empty, the result LoDTensor will be [-1] with
\
LoD [[]] and dims [1, 1].
LoD [[]] and dims [1, 1].
Examples:
.. code-block:: python
...
...
@@ -5065,7 +5065,7 @@ def hsigmoid(input,
"""
The hierarchical sigmoid operator is used to accelerate the training
process of language model. This operator organizes the classes into a
complete binary tree, or you can use is_custom to pass your own tree to
complete binary tree, or you can use is_custom to pass your own tree to
implement hierarchical. Each leaf node represents a class(a word) and each
internal node acts as a binary classifier. For each word there's a unique
path from root to it's leaf node, hsigmoid calculate the cost for each
...
...
@@ -5082,7 +5082,7 @@ def hsigmoid(input,
2. build a dict to store word_id -> word's leaf to root path, we call it path_table.
3. build a dict to store word_id -> code of word's leaf to root path, we call it path_code. Code
means label of each binary classification, using 1 indicate true, 0 indicate false.
4. now, each word should has its path and code along the path, you can pass a batch of path and code
4. now, each word should has its path and code along the path, you can pass a batch of path and code
related to the same batch of inputs.
Args:
...
...
@@ -5091,8 +5091,8 @@ def hsigmoid(input,
and :math:`D` is the feature size.
label (Variable): The tensor variable contains labels of training data.
It's a tensor with shape is :math:`[N
\\
times 1]`.
num_classes: (int), The number of classes, must not be less than 2. with default tree this has to be set,
it should never be None under is_custom=False, but while is_custom is true, it should be non leaf num
num_classes: (int), The number of classes, must not be less than 2. with default tree this has to be set,
it should never be None under is_custom=False, but while is_custom is true, it should be non leaf num
which indicates the num of classes using by binary classify.
param_attr (ParamAttr|None): The parameter attribute for learnable parameters/weights
of hsigmoid. If it is set to None or one attribute of ParamAttr, hsigmoid
...
...
@@ -5105,15 +5105,15 @@ def hsigmoid(input,
is not set, the bias is initialized zero. Default: None.
name (str|None): A name for this layer(optional). If set None, the layer
will be named automatically. Default: None.
path_table: (Variable|None) this variable can store each batch of samples' path to root,
path_table: (Variable|None) this variable can store each batch of samples' path to root,
it should be in leaf -> root order
path_table should have the same shape with path_code, and for each sample i path_table[i] indicates a np.array like
structure and each element in this array is indexes in parent nodes' Weight Matrix.
path_code: (Variable|None) this variable can store each batch of samples' code,
path_table should have the same shape with path_code, and for each sample i path_table[i] indicates a np.array like
structure and each element in this array is indexes in parent nodes' Weight Matrix.
path_code: (Variable|None) this variable can store each batch of samples' code,
each code consist with every code of parent nodes. it should be in leaf -> root order
is_custom: (bool|False)using user defined binary tree instead of default complete binary tree, if costum is
is_custom: (bool|False)using user defined binary tree instead of default complete binary tree, if costum is
set you need to set path_table/path_code/num_classes, otherwise num_classes should be set
is_sparse: (bool|False)using sparse update instead of dense update, if set, the gradient
is_sparse: (bool|False)using sparse update instead of dense update, if set, the gradient
of W and input will be sparse.
Returns:
...
...
@@ -6965,10 +6965,10 @@ def mean_iou(input, label, num_classes):
num_classes (int): The possible number of labels.
Returns:
mean_iou (Variable),out_wrong(Variable),out_correct(Variable):
mean_iou (Variable),out_wrong(Variable),out_correct(Variable):
Three variables:
- mean_iou : A Tensor representing the mean intersection-over-union with shape [1].
- out_wrong: A Tensor with shape [num_classes]. The wrong numbers of each class.
- out_correct: A Tensor with shape [num_classes]. The correct numbers of each class.
...
...
@@ -7166,7 +7166,7 @@ def affine_grid(theta, out_shape, name=None):
Args:
theta (Variable): A batch of affine transform parameters with shape [N, 2, 3].
out_shape (Variable | list | tuple): The shape of target output with format [N, C, H, W].
out_shape (Variable | list | tuple): The shape of target output with format [N, C, H, W].
``out_shape`` can be a Variable or a list or tuple.
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
...
...
@@ -7762,9 +7762,9 @@ def flatten(x, axis=1, name=None):
"""
**Flatten layer**
Flattens the input tensor into a 2D matrix.
For Example:
.. code-block:: text
Case 1:
...
...
@@ -8942,7 +8942,7 @@ def similarity_focus(input, axis, indexes, name=None):
SimilarityFocus Operator
Generate a similarity focus mask with the same shape of input using the following method:
1. Extract the 3-D tensor(here the first dimension is BatchSize) corresponding
to the axis according to the indexes. For example, if axis=1 and indexes=[a],
it will get the matrix T=X[:, a, :, :]. In this case, if the shape of input X
...
...
@@ -9713,47 +9713,3 @@ def huber_loss(input, label, delta):
'Residual'
:
residual
},
attrs
=
{
'delta'
:
delta
})
return
out
class
FC
(
layers
.
PyLayer
):
def
__init__
(
self
,
size
,
param_attr
=
None
,
num_flatten_dims
=
1
,
dtype
=
core
.
VarDesc
.
VarType
.
FP32
):
super
(
FC
,
self
).
__init__
(
param_attr
=
param_attr
)
self
.
_size
=
size
self
.
_num_flatten_dims
=
num_flatten_dims
self
.
_dtype
=
dtype
self
.
_tmp
=
self
.
_helper
.
create_variable_for_type_inference
(
self
.
_dtype
)
self
.
_out
=
self
.
_helper
.
create_variable_for_type_inference
(
self
.
_dtype
)
def
_build_once
(
self
,
inputs
):
input_shape
=
inputs
.
shape
param_shape
=
[
reduce
(
lambda
a
,
b
:
a
*
b
,
input_shape
[
self
.
_num_flatten_dims
:],
1
)
]
+
[
self
.
_size
]
self
.
_w
=
self
.
_helper
.
create_parameter
(
attr
=
self
.
_helper
.
param_attr
,
shape
=
param_shape
,
dtype
=
self
.
_dtype
,
is_bias
=
False
)
def
forward
(
self
,
inputs
):
self
.
_helper
.
append_op
(
type
=
"mul"
,
inputs
=
{
"X"
:
inputs
,
"Y"
:
self
.
_w
},
outputs
=
{
"Out"
:
self
.
_tmp
},
attrs
=
{
"x_num_col_dims"
:
self
.
_num_flatten_dims
,
"y_num_col_dims"
:
1
})
self
.
_helper
.
append_op
(
type
=
"sum"
,
inputs
=
{
"X"
:
[
self
.
_tmp
]},
outputs
=
{
"Out"
:
self
.
_out
},
attrs
=
{
"use_mkldnn"
:
False
})
return
self
.
_out
python/paddle/fluid/tests/unittests/test_imperative.py
浏览文件 @
22956530
...
...
@@ -18,7 +18,7 @@ import numpy as np
import
paddle.fluid
as
fluid
from
paddle.fluid
import
core
from
paddle.fluid.
layers
.nn
import
FC
from
paddle.fluid.
imperative
.nn
import
FC
from
test_imperative_base
import
new_program_scope
...
...
python/paddle/fluid/tests/unittests/test_imperative_optimizer.py
浏览文件 @
22956530
...
...
@@ -74,7 +74,7 @@ class SimpleImgConvPool(fluid.imperative.PyLayer):
class
MNIST
(
fluid
.
imperative
.
PyLayer
):
def
__init__
(
self
,
param_attr
=
None
,
bias_attr
=
None
):
super
(
MNIST
,
self
).
__init__
(
param_attr
=
param_attr
,
bias_attr
=
bias_attr
)
super
(
MNIST
,
self
).
__init__
()
self
.
_simple_img_conv_pool_1
=
SimpleImgConvPool
(
1
,
20
,
5
,
2
,
2
,
act
=
"relu"
)
...
...
@@ -85,8 +85,7 @@ class MNIST(fluid.imperative.PyLayer):
pool_2_shape
=
50
*
8
*
8
SIZE
=
10
scale
=
(
2.0
/
(
pool_2_shape
**
2
*
SIZE
))
**
0.5
self
.
_fc
=
FC
(
-
1
,
10
,
self
.
_fc
=
FC
(
10
,
param_attr
=
fluid
.
param_attr
.
ParamAttr
(
initializer
=
fluid
.
initializer
.
NormalInitializer
(
loc
=
0.0
,
scale
=
scale
)))
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录