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
PaddlePaddle
Paddle
提交
e402c0ec
P
Paddle
项目概览
PaddlePaddle
/
Paddle
12 个月 前同步成功
通知
2292
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
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
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
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
e402c0ec
编写于
1月 30, 2019
作者:
J
jerrywgz
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
test=develop
上级
334f697d
变更
7
隐藏空白更改
内联
并排
Showing
7 changed file
with
551 addition
and
107 deletion
+551
-107
paddle/fluid/API.spec
paddle/fluid/API.spec
+3
-3
paddle/fluid/operators/interpolate_op.cc
paddle/fluid/operators/interpolate_op.cc
+70
-0
paddle/fluid/operators/interpolate_op.cu
paddle/fluid/operators/interpolate_op.cu
+76
-28
paddle/fluid/operators/interpolate_op.h
paddle/fluid/operators/interpolate_op.h
+76
-35
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+190
-12
python/paddle/fluid/tests/unittests/test_bilinear_interp_op.py
...n/paddle/fluid/tests/unittests/test_bilinear_interp_op.py
+87
-15
python/paddle/fluid/tests/unittests/test_nearest_interp_op.py
...on/paddle/fluid/tests/unittests/test_nearest_interp_op.py
+49
-14
未找到文件。
paddle/fluid/API.spec
浏览文件 @
e402c0ec
...
...
@@ -142,10 +142,10 @@ paddle.fluid.layers.label_smooth ArgSpec(args=['label', 'prior_dist', 'epsilon',
paddle.fluid.layers.roi_pool ArgSpec(args=['input', 'rois', 'pooled_height', 'pooled_width', 'spatial_scale'], varargs=None, keywords=None, defaults=(1, 1, 1.0))
paddle.fluid.layers.roi_align ArgSpec(args=['input', 'rois', 'pooled_height', 'pooled_width', 'spatial_scale', 'sampling_ratio', 'name'], varargs=None, keywords=None, defaults=(1, 1, 1.0, -1, None))
paddle.fluid.layers.dice_loss ArgSpec(args=['input', 'label', 'epsilon'], varargs=None, keywords=None, defaults=(1e-05,))
paddle.fluid.layers.image_resize ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'resample', 'actual_shape'
], varargs=None, keywords=None, defaults=(None, None, None, 'BILINEAR', None
))
paddle.fluid.layers.image_resize ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'resample', 'actual_shape'
, 'align_corners', 'align_mode'], varargs=None, keywords=None, defaults=(None, None, None, 'BILINEAR', None, True, 1
))
paddle.fluid.layers.image_resize_short ArgSpec(args=['input', 'out_short_len', 'resample'], varargs=None, keywords=None, defaults=('BILINEAR',))
paddle.fluid.layers.resize_bilinear ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'actual_shape'
], varargs=None, keywords=None, defaults=(None, None, None, None
))
paddle.fluid.layers.resize_nearest ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'actual_shape'
], varargs=None, keywords=None, defaults=(None, None, None, Non
e))
paddle.fluid.layers.resize_bilinear ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'actual_shape'
, 'align_corners', 'align_mode'], varargs=None, keywords=None, defaults=(None, None, None, None, True, 1
))
paddle.fluid.layers.resize_nearest ArgSpec(args=['input', 'out_shape', 'scale', 'name', 'actual_shape'
, 'align_corners'], varargs=None, keywords=None, defaults=(None, None, None, None, Tru
e))
paddle.fluid.layers.gather ArgSpec(args=['input', 'index'], varargs=None, keywords=None, defaults=None)
paddle.fluid.layers.scatter ArgSpec(args=['input', 'index', 'updates', 'name'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.sequence_scatter ArgSpec(args=['input', 'index', 'updates', 'name'], varargs=None, keywords=None, defaults=(None,))
...
...
paddle/fluid/operators/interpolate_op.cc
浏览文件 @
e402c0ec
...
...
@@ -82,6 +82,18 @@ class InterpolateOpMaker : public framework::OpProtoAndCheckerMaker {
"bilinear interpolation and
\"
nearest
\"
for nearest "
"neighbor interpolation."
)
.
SetDefault
(
"bilinear"
);
AddAttr
<
bool
>
(
"align_corners"
,
"an optinal bool. Defaults to True. "
"If True, the centers of 4 corner pixels of the input and output "
"tensors are aligned, preserving the values at the corner pixels, "
"if Flase, are not aligned"
)
.
SetDefault
(
true
);
AddAttr
<
int
>
(
"align_mode"
,
"(int, default
\'
1
\'
), optional for bilinear interpolation"
"can be
\'
0
\'
for src_idx = scale*(dst_indx+0.5)-0.5 , "
"can be
\'
1
\'
for src_idx = scale*dst_index ."
)
.
SetDefault
(
1
);
AddComment
(
R"DOC(
This operator samples input X to given output shape by using specified
interpolation method, the interpolation methods can be \"nearest\"
...
...
@@ -98,6 +110,64 @@ class InterpolateOpMaker : public framework::OpProtoAndCheckerMaker {
to perform linear interpolation first in one direction, and then
again in the other direction.
Align_corners and align_mode are optinal parameters,the calculation method
of interpolation can be selected by them.
Example:
For scale:
if align_corners = True and out_{size}>1 :
scale_{factor} = (in_{size}-1.0)/(out_{size}-1.0)
else:
scale_{factor} = float(in_{size}/out_{size})
Nearest neighbor interpolation:
if:
align_corners = False
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = \left \lfloor {H_{in} * scale_{}factor}} \right \rfloor
W_out = \left \lfloor {W_{in} * scale_{}factor}} \right \rfloor
else:
align_corners = True
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = round(H_{in} * scale_{factor})
W_out = round(W_{in} * scale_{factor})
Bilinear interpolation:
if:
align_corners = False , align_mode = 0
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = (H_{in}+0.5) * scale_{factor} - 0.5
W_out = (W_{in}+0.5) * scale_{factor} - 0.5
else:
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = H_{in} * scale_{factor}
W_out = W_{in} * scale_{factor}
For details of nearest neighbor interpolation, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation
...
...
paddle/fluid/operators/interpolate_op.cu
浏览文件 @
e402c0ec
...
...
@@ -23,7 +23,8 @@ __global__ void KeNearestNeighborInterpFw(
const
T
*
in
,
const
size_t
in_img_h
,
const
size_t
in_img_w
,
const
size_t
input_h
,
const
size_t
input_w
,
T
*
out
,
const
size_t
out_img_h
,
const
size_t
out_img_w
,
const
size_t
output_h
,
const
size_t
output_w
,
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
)
{
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
,
const
bool
align_corners
)
{
int
nthreads
=
output_h
*
output_w
;
int
tid
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
int
stride
=
blockDim
.
x
*
gridDim
.
x
;
...
...
@@ -35,10 +36,14 @@ __global__ void KeNearestNeighborInterpFw(
int
channel_id
=
out_id_w
/
out_img_size
;
int
out_img_idy
=
(
out_id_w
%
out_img_size
)
/
out_img_w
;
int
in_img_idy
=
static_cast
<
int
>
(
ratio_h
*
out_img_idy
+
0.5
);
int
in_img_idy
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_h
*
out_img_idy
+
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
out_img_idy
);
int
out_img_idx
=
tid
%
out_img_w
;
int
in_img_idx
=
static_cast
<
int
>
(
ratio_w
*
out_img_idx
+
0.5
);
int
in_img_idx
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_w
*
out_img_idx
+
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
out_img_idx
);
out
[
tid
]
=
in
[
out_id_h
*
input_w
+
channel_id
*
in_img_size
+
in_img_idy
*
in_img_w
+
in_img_idx
];
...
...
@@ -50,7 +55,8 @@ __global__ void KeNearestNeighborInterpBw(
T
*
in
,
const
size_t
in_img_h
,
const
size_t
in_img_w
,
const
size_t
input_h
,
const
size_t
input_w
,
const
T
*
out
,
const
size_t
out_img_h
,
const
size_t
out_img_w
,
const
size_t
output_h
,
const
size_t
output_w
,
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
)
{
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
,
const
bool
align_corners
)
{
int
nthreads
=
output_h
*
output_w
;
int
tid
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
int
stride
=
blockDim
.
x
*
gridDim
.
x
;
...
...
@@ -62,10 +68,14 @@ __global__ void KeNearestNeighborInterpBw(
int
channel_id
=
out_id_w
/
out_img_size
;
int
out_img_idy
=
(
out_id_w
%
out_img_size
)
/
out_img_w
;
int
in_img_idy
=
static_cast
<
int
>
(
ratio_h
*
out_img_idy
+
0.5
);
int
in_img_idy
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_h
*
out_img_idy
+
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
out_img_idy
);
int
out_img_idx
=
tid
%
out_img_w
;
int
in_img_idx
=
static_cast
<
int
>
(
ratio_w
*
out_img_idx
+
0.5
);
int
in_img_idx
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_w
*
out_img_idx
+
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
out_img_idx
);
T
*
in_pos
=
&
in
[
out_id_h
*
input_w
+
channel_id
*
in_img_size
+
in_img_idy
*
in_img_w
+
in_img_idx
];
...
...
@@ -79,10 +89,12 @@ __global__ void KeBilinearInterpFw(
const
T
*
in
,
const
size_t
in_img_h
,
const
size_t
in_img_w
,
const
size_t
input_h
,
const
size_t
input_w
,
T
*
out
,
const
size_t
out_img_h
,
const
size_t
out_img_w
,
const
size_t
output_h
,
const
size_t
output_w
,
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
)
{
const
size_t
num_channels
,
const
float
ratio_h
,
const
float
ratio_w
,
const
bool
align_corners
,
const
int
align_mode
)
{
int
nthreads
=
output_h
*
output_w
;
int
tid
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
int
stride
=
blockDim
.
x
*
gridDim
.
x
;
bool
align_flag
=
(
align_mode
==
0
&&
!
align_corners
);
for
(;
tid
<
nthreads
;
tid
+=
stride
)
{
int
out_id_h
=
tid
/
output_w
;
int
out_id_w
=
tid
%
output_w
;
...
...
@@ -91,15 +103,23 @@ __global__ void KeBilinearInterpFw(
int
channel_id
=
out_id_w
/
out_img_size
;
int
out_img_idy
=
(
out_id_w
%
out_img_size
)
/
out_img_w
;
int
in_img_idy
=
ratio_h
*
out_img_idy
;
int
in_img_idy
=
align_flag
?
static_cast
<
int
>
(
ratio_h
*
(
out_img_idy
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
out_img_idy
);
in_img_idy
=
(
in_img_idy
>
0
)
?
in_img_idy
:
0
;
int
h_id
=
(
in_img_idy
<
in_img_h
-
1
)
?
1
:
0
;
T
h1lambda
=
ratio_h
*
out_img_idy
-
in_img_idy
;
T
h1lambda
=
align_flag
?
ratio_h
*
(
out_img_idy
+
0.5
)
-
0.5
-
in_img_idy
:
ratio_h
*
out_img_idy
-
in_img_idy
;
T
h2lambda
=
1.
f
-
h1lambda
;
int
out_img_idx
=
tid
%
out_img_w
;
int
in_img_idx
=
ratio_w
*
out_img_idx
;
int
in_img_idx
=
align_flag
?
static_cast
<
int
>
(
ratio_w
*
(
out_img_idx
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
out_img_idx
);
in_img_idx
=
(
in_img_idx
>
0
)
?
in_img_idx
:
0
;
int
w_id
=
(
in_img_idx
<
in_img_w
-
1
)
?
1
:
0
;
T
w1lambda
=
ratio_w
*
out_img_idx
-
in_img_idx
;
T
w1lambda
=
align_flag
?
ratio_w
*
(
out_img_idx
+
0.5
)
-
0.5
-
in_img_idx
:
ratio_w
*
out_img_idx
-
in_img_idx
;
T
w2lambda
=
1.
f
-
w1lambda
;
const
T
*
in_pos
=
&
in
[
out_id_h
*
input_w
+
channel_id
*
in_img_size
+
...
...
@@ -118,10 +138,12 @@ __global__ void KeBilinearInterpBw(
T
*
in
,
const
size_t
in_img_h
,
const
size_t
in_img_w
,
const
size_t
input_h
,
const
size_t
input_w
,
const
T
*
out
,
const
size_t
out_img_h
,
const
size_t
out_img_w
,
const
size_t
output_h
,
const
size_t
output_w
,
const
size_t
num_channels
,
const
T
ratio_h
,
const
T
ratio_w
)
{
const
size_t
num_channels
,
const
T
ratio_h
,
const
T
ratio_w
,
const
bool
align_corners
,
const
int
align_mode
)
{
int
nthreads
=
output_h
*
output_w
;
int
tid
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
int
stride
=
blockDim
.
x
*
gridDim
.
x
;
bool
align_flag
=
(
align_mode
==
0
&&
!
align_corners
);
for
(;
tid
<
nthreads
;
tid
+=
stride
)
{
int
out_id_h
=
tid
/
output_w
;
int
out_id_w
=
tid
%
output_w
;
...
...
@@ -130,15 +152,22 @@ __global__ void KeBilinearInterpBw(
int
channel_id
=
out_id_w
/
out_img_size
;
int
out_img_idy
=
(
out_id_w
%
out_img_size
)
/
out_img_w
;
int
in_img_idy
=
ratio_h
*
out_img_idy
;
int
in_img_idy
=
align_flag
?
ratio_h
*
(
out_img_idy
+
0.5
)
-
0.5
:
ratio_h
*
out_img_idy
;
in_img_idy
=
(
in_img_idy
>
0
)
?
in_img_idy
:
0
;
int
h_id
=
(
in_img_idy
<
in_img_h
-
1
)
?
1
:
0
;
T
h1lambda
=
ratio_h
*
out_img_idy
-
in_img_idy
;
T
h1lambda
=
align_flag
?
ratio_h
*
(
out_img_idy
+
0.5
)
-
0.5
-
in_img_idy
:
ratio_h
*
out_img_idy
-
in_img_idy
;
T
h2lambda
=
1.
f
-
h1lambda
;
int
out_img_idx
=
tid
%
out_img_w
;
int
in_img_idx
=
ratio_w
*
out_img_idx
;
int
in_img_idx
=
align_flag
?
ratio_w
*
(
out_img_idx
+
0.5
)
-
0.5
:
ratio_w
*
out_img_idx
;
in_img_idx
=
(
in_img_idx
>
0
)
?
in_img_idx
:
0
;
int
w_id
=
(
in_img_idx
<
in_img_w
-
1
)
?
1
:
0
;
T
w1lambda
=
ratio_w
*
out_img_idx
-
in_img_idx
;
T
w1lambda
=
align_flag
?
ratio_w
*
(
out_img_idx
+
0.5
)
-
0.5
-
in_img_idx
:
ratio_w
*
out_img_idx
-
in_img_idx
;
T
w2lambda
=
1.
f
-
w1lambda
;
T
*
in_pos
=
&
in
[
out_id_h
*
input_w
+
channel_id
*
in_img_size
+
...
...
@@ -175,6 +204,9 @@ class InterpolateOpCUDAKernel : public framework::OpKernel<T> {
out_w
=
size_data
[
1
];
}
bool
align_corners
=
ctx
.
Attr
<
bool
>
(
"align_corners"
);
int
align_mode
=
ctx
.
Attr
<
int
>
(
"align_mode"
);
int
n
=
input
->
dims
()[
0
];
int
c
=
input
->
dims
()[
1
];
int
in_h
=
input
->
dims
()[
2
];
...
...
@@ -188,10 +220,16 @@ class InterpolateOpCUDAKernel : public framework::OpKernel<T> {
int
in_chw
=
c
*
in_hw
;
int
out_chw
=
c
*
out_hw
;
float
ratio_h
=
(
out_h
>
1
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
0.
f
;
float
ratio_w
=
(
out_w
>
1
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
0.
f
;
float
ratio_h
=
0.
f
;
float
ratio_w
=
0.
f
;
if
(
out_h
>
1
)
{
ratio_h
=
(
align_corners
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
static_cast
<
float
>
(
in_h
)
/
out_h
;
}
if
(
out_w
>
1
)
{
ratio_w
=
(
align_corners
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
static_cast
<
float
>
(
in_w
)
/
out_w
;
}
if
(
in_h
==
out_h
&&
in_w
==
out_w
)
{
framework
::
TensorCopy
(
*
input
,
ctx
.
GetPlace
(),
output
);
...
...
@@ -206,12 +244,12 @@ class InterpolateOpCUDAKernel : public framework::OpKernel<T> {
KeNearestNeighborInterpFw
<
T
><<<
grid_dim
,
512
,
0
,
ctx
.
cuda_device_context
().
stream
()
>>>
(
input_data
,
in_h
,
in_w
,
n
,
in_chw
,
output_data
,
out_h
,
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
);
out_chw
,
c
,
ratio_h
,
ratio_w
,
align_corners
);
}
else
if
(
"bilinear"
==
interp_method
)
{
KeBilinearInterpFw
<
T
><<<
grid_dim
,
512
,
0
,
ctx
.
cuda_device_context
().
stream
()
>>>
(
input_data
,
in_h
,
in_w
,
n
,
in_chw
,
output_data
,
out_h
,
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
);
out_chw
,
c
,
ratio_h
,
ratio_w
,
align_corners
,
align_mode
);
}
}
};
...
...
@@ -234,6 +272,10 @@ class InterpolateGradOpCUDAKernel : public framework::OpKernel<T> {
int
out_h
=
ctx
.
Attr
<
int
>
(
"out_h"
);
int
out_w
=
ctx
.
Attr
<
int
>
(
"out_w"
);
auto
out_size
=
ctx
.
Input
<
Tensor
>
(
"OutSize"
);
bool
align_corners
=
ctx
.
Attr
<
bool
>
(
"align_corners"
);
int
align_mode
=
ctx
.
Attr
<
int
>
(
"align_mode"
);
if
(
out_size
!=
nullptr
)
{
Tensor
sizes
;
framework
::
TensorCopy
(
*
out_size
,
platform
::
CPUPlace
(),
&
sizes
);
...
...
@@ -252,10 +294,16 @@ class InterpolateGradOpCUDAKernel : public framework::OpKernel<T> {
int
in_chw
=
c
*
in_hw
;
int
out_chw
=
c
*
out_hw
;
float
ratio_h
=
(
out_h
>
1
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
0.
f
;
float
ratio_w
=
(
out_w
>
1
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
0.
f
;
float
ratio_h
=
0.
f
;
float
ratio_w
=
0.
f
;
if
(
out_h
>
1
)
{
ratio_h
=
(
align_corners
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
static_cast
<
float
>
(
in_h
)
/
out_h
;
}
if
(
out_w
>
1
)
{
ratio_w
=
(
align_corners
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
static_cast
<
float
>
(
in_w
)
/
out_w
;
}
if
(
in_h
==
out_h
&&
in_w
==
out_w
)
{
framework
::
TensorCopy
(
*
output_grad
,
ctx
.
GetPlace
(),
input_grad
);
...
...
@@ -270,12 +318,12 @@ class InterpolateGradOpCUDAKernel : public framework::OpKernel<T> {
KeNearestNeighborInterpBw
<
T
><<<
grid_dim
,
512
,
0
,
ctx
.
cuda_device_context
().
stream
()
>>>
(
input_grad_data
,
in_h
,
in_w
,
n
,
in_chw
,
output_grad_data
,
out_h
,
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
);
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
,
align_corners
);
}
else
if
(
"bilinear"
==
interp_method
)
{
KeBilinearInterpBw
<
T
><<<
grid_dim
,
512
,
0
,
ctx
.
cuda_device_context
().
stream
()
>>>
(
input_grad_data
,
in_h
,
in_w
,
n
,
in_chw
,
output_grad_data
,
out_h
,
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
);
out_w
,
n
,
out_chw
,
c
,
ratio_h
,
ratio_w
,
align_corners
,
align_mode
);
}
}
};
...
...
paddle/fluid/operators/interpolate_op.h
浏览文件 @
e402c0ec
...
...
@@ -26,14 +26,17 @@ template <typename T>
static
void
NearestNeighborInterpolate
(
const
Tensor
&
input
,
Tensor
*
output
,
const
float
ratio_h
,
const
float
ratio_w
,
const
int
n
,
const
int
c
,
const
int
out_h
,
const
int
out_w
)
{
const
int
out_h
,
const
int
out_w
,
const
bool
align_corners
)
{
auto
input_t
=
EigenTensor
<
T
,
4
>::
From
(
input
);
auto
output_t
=
EigenTensor
<
T
,
4
>::
From
(
*
output
);
for
(
int
k
=
0
;
k
<
out_h
;
k
++
)
{
// loop for images
int
in_k
=
static_cast
<
int
>
(
ratio_h
*
k
+
0.5
);
int
in_k
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_h
*
k
+
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
k
);
for
(
int
l
=
0
;
l
<
out_w
;
l
++
)
{
int
in_l
=
static_cast
<
int
>
(
ratio_w
*
l
+
0.5
);
int
in_l
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_w
*
l
+
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
l
);
for
(
int
i
=
0
;
i
<
n
;
i
++
)
{
// loop for batches
for
(
int
j
=
0
;
j
<
c
;
j
++
)
{
// loop for channels
...
...
@@ -48,20 +51,29 @@ template <typename T>
static
void
BilinearInterpolation
(
const
Tensor
&
input
,
Tensor
*
output
,
const
float
ratio_h
,
const
float
ratio_w
,
const
int
in_h
,
const
int
in_w
,
const
int
n
,
const
int
c
,
const
int
out_h
,
const
int
out_w
)
{
const
int
c
,
const
int
out_h
,
const
int
out_w
,
const
bool
align_corners
,
const
bool
align_mode
)
{
auto
input_t
=
EigenTensor
<
T
,
4
>::
From
(
input
);
auto
output_t
=
EigenTensor
<
T
,
4
>::
From
(
*
output
);
bool
align_flag
=
(
align_mode
==
0
&&
!
align_corners
);
for
(
int
k
=
0
;
k
<
out_h
;
k
++
)
{
// loop for images
int
y_n
=
static_cast
<
int
>
(
ratio_h
*
k
);
int
y_n
=
align_flag
?
static_cast
<
int
>
(
ratio_h
*
(
k
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
k
);
y_n
=
(
y_n
>
0
)
?
y_n
:
0
;
int
y_s
=
(
y_n
+
1
)
<
(
in_h
-
1
)
?
(
y_n
+
1
)
:
(
in_h
-
1
);
float
d_n
=
ratio_h
*
k
-
y_n
;
float
d_n
=
align_flag
?
ratio_h
*
(
k
+
0.5
)
-
0.5
-
y_n
:
ratio_h
*
k
-
y_n
;
float
d_s
=
1.
f
-
d_n
;
for
(
int
l
=
0
;
l
<
out_w
;
l
++
)
{
int
x_w
=
static_cast
<
int
>
(
ratio_w
*
l
);
int
x_w
=
(
align_mode
==
0
&&
!
align_corners
)
?
static_cast
<
int
>
(
ratio_w
*
(
l
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
l
);
x_w
=
(
x_w
>
0
)
?
x_w
:
0
;
int
x_e
=
(
x_w
+
1
)
<
(
in_w
-
1
)
?
(
x_w
+
1
)
:
(
in_w
-
1
);
float
d_w
=
ratio_w
*
l
-
x_w
;
float
d_w
=
align_flag
?
ratio_w
*
(
l
+
0.5
)
-
0.5
-
x_w
:
ratio_w
*
l
-
x_w
;
float
d_e
=
1.
f
-
d_w
;
for
(
int
i
=
0
;
i
<
n
;
i
++
)
{
// loop for batches
...
...
@@ -78,19 +90,20 @@ static void BilinearInterpolation(const Tensor& input, Tensor* output,
}
template
<
typename
T
>
static
void
NearestNeighborInterpolateGrad
(
const
Tensor
&
output_grad
,
Tensor
*
input_grad
,
const
float
ratio_h
,
const
float
ratio_w
,
const
int
n
,
const
int
c
,
const
int
out_h
,
const
int
out_w
)
{
static
void
NearestNeighborInterpolateGrad
(
const
Tensor
&
output_grad
,
Tensor
*
input_grad
,
const
float
ratio_h
,
const
float
ratio_w
,
const
int
n
,
const
int
c
,
const
int
out_h
,
const
int
out_w
,
const
bool
align_corners
)
{
auto
input_grad_t
=
EigenTensor
<
T
,
4
>::
From
(
*
input_grad
);
auto
output_grad_t
=
EigenTensor
<
T
,
4
>::
From
(
output_grad
);
for
(
int
k
=
0
;
k
<
out_h
;
k
++
)
{
// loop for images
int
in_k
=
static_cast
<
int
>
(
ratio_h
*
k
+
0.5
);
int
in_k
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_h
*
k
+
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
k
);
for
(
int
l
=
0
;
l
<
out_w
;
l
++
)
{
int
in_l
=
static_cast
<
int
>
(
ratio_w
*
l
+
0.5
);
int
in_l
=
(
align_corners
)
?
static_cast
<
int
>
(
ratio_w
*
l
+
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
l
);
for
(
int
i
=
0
;
i
<
n
;
i
++
)
{
// loop for batches
for
(
int
j
=
0
;
j
<
c
;
j
++
)
{
// loop for channels
...
...
@@ -106,19 +119,28 @@ static void BilinearInterpolationGrad(const Tensor& output_grad,
Tensor
*
input_grad
,
const
float
ratio_h
,
const
float
ratio_w
,
const
int
in_h
,
const
int
in_w
,
const
int
n
,
const
int
c
,
const
int
out_h
,
const
int
out_w
)
{
const
int
out_h
,
const
int
out_w
,
const
bool
align_corners
,
const
int
align_mode
)
{
auto
input_grad_t
=
EigenTensor
<
T
,
4
>::
From
(
*
input_grad
);
auto
output_grad_t
=
EigenTensor
<
T
,
4
>::
From
(
output_grad
);
bool
align_flag
=
(
align_mode
==
0
&&
!
align_corners
);
for
(
int
k
=
0
;
k
<
out_h
;
k
++
)
{
// loop for images
int
y_n
=
static_cast
<
int
>
(
ratio_h
*
k
);
int
y_n
=
align_flag
?
static_cast
<
int
>
(
ratio_h
*
(
k
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_h
*
k
);
y_n
=
(
y_n
>
0
)
?
y_n
:
0
;
int
y_s
=
(
y_n
+
1
)
<
(
in_h
-
1
)
?
(
y_n
+
1
)
:
(
in_h
-
1
);
float
d_n
=
ratio_h
*
k
-
y_n
;
float
d_n
=
align_flag
?
ratio_h
*
(
k
+
0.5
)
-
0.5
-
y_n
:
ratio_h
*
k
-
y_n
;
float
d_s
=
1.
f
-
d_n
;
for
(
int
l
=
0
;
l
<
out_w
;
l
++
)
{
int
x_w
=
static_cast
<
int
>
(
ratio_w
*
l
);
int
x_w
=
align_flag
?
static_cast
<
int
>
(
ratio_w
*
(
l
+
0.5
)
-
0.5
)
:
static_cast
<
int
>
(
ratio_w
*
l
);
x_w
=
(
x_w
>
0
)
?
x_w
:
0
;
int
x_e
=
(
x_w
+
1
)
<
(
in_w
-
1
)
?
(
x_w
+
1
)
:
(
in_w
-
1
);
float
d_w
=
ratio_w
*
l
-
x_w
;
float
d_w
=
align_flag
?
ratio_w
*
(
l
+
0.5
)
-
0.5
-
x_w
:
ratio_w
*
l
-
x_w
;
float
d_e
=
1.
f
-
d_w
;
for
(
int
i
=
0
;
i
<
n
;
i
++
)
{
// loop for batches
...
...
@@ -134,7 +156,6 @@ static void BilinearInterpolationGrad(const Tensor& output_grad,
}
}
}
template
<
typename
T
>
class
InterpolateKernel
:
public
framework
::
OpKernel
<
T
>
{
public:
...
...
@@ -151,6 +172,8 @@ class InterpolateKernel : public framework::OpKernel<T> {
out_h
=
out_size_data
[
0
];
out_w
=
out_size_data
[
1
];
}
bool
align_corners
=
ctx
.
Attr
<
bool
>
(
"align_corners"
);
int
align_mode
=
ctx
.
Attr
<
int
>
(
"align_mode"
);
const
int
n
=
input
->
dims
()[
0
];
const
int
c
=
input
->
dims
()[
1
];
...
...
@@ -168,17 +191,24 @@ class InterpolateKernel : public framework::OpKernel<T> {
return
;
}
float
ratio_h
=
(
out_h
>
1
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
0.
f
;
float
ratio_w
=
(
out_w
>
1
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
0.
f
;
float
ratio_h
=
0.
f
;
float
ratio_w
=
0.
f
;
if
(
out_h
>
1
)
{
ratio_h
=
(
align_corners
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
static_cast
<
float
>
(
in_h
)
/
out_h
;
}
if
(
out_w
>
1
)
{
ratio_w
=
(
align_corners
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
static_cast
<
float
>
(
in_w
)
/
out_w
;
}
if
(
"bilinear"
==
interp_method
)
{
BilinearInterpolation
<
T
>
(
*
input
,
output
,
ratio_h
,
ratio_w
,
in_h
,
in_w
,
n
,
c
,
out_h
,
out_w
);
c
,
out_h
,
out_w
,
align_corners
,
align_mode
);
}
else
if
(
"nearest"
==
interp_method
)
{
NearestNeighborInterpolate
<
T
>
(
*
input
,
output
,
ratio_h
,
ratio_w
,
n
,
c
,
out_h
,
out_w
);
out_h
,
out_w
,
align_corners
);
}
}
};
...
...
@@ -200,6 +230,8 @@ class InterpolateGradKernel : public framework::OpKernel<T> {
out_h
=
out_size_data
[
0
];
out_w
=
out_size_data
[
1
];
}
bool
align_corners
=
ctx
.
Attr
<
bool
>
(
"align_corners"
);
int
align_mode
=
ctx
.
Attr
<
int
>
(
"align_mode"
);
const
int
n
=
input
->
dims
()[
0
];
const
int
c
=
input
->
dims
()[
1
];
...
...
@@ -217,17 +249,26 @@ class InterpolateGradKernel : public framework::OpKernel<T> {
return
;
}
float
ratio_h
=
(
out_h
>
1
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
0.
f
;
float
ratio_w
=
(
out_w
>
1
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
0.
f
;
float
ratio_h
=
0.
f
;
float
ratio_w
=
0.
f
;
if
(
out_h
>
1
)
{
ratio_h
=
(
align_corners
)
?
static_cast
<
float
>
(
in_h
-
1
)
/
(
out_h
-
1
)
:
static_cast
<
float
>
(
in_h
)
/
out_h
;
}
if
(
out_w
>
1
)
{
ratio_w
=
(
align_corners
)
?
static_cast
<
float
>
(
in_w
-
1
)
/
(
out_w
-
1
)
:
static_cast
<
float
>
(
in_w
)
/
out_w
;
}
if
(
"bilinear"
==
interp_method
)
{
BilinearInterpolationGrad
<
T
>
(
*
output_grad
,
input_grad
,
ratio_h
,
ratio_w
,
in_h
,
in_w
,
n
,
c
,
out_h
,
out_w
);
in_h
,
in_w
,
n
,
c
,
out_h
,
out_w
,
align_corners
,
align_mode
);
}
else
if
(
"nearest"
==
interp_method
)
{
NearestNeighborInterpolateGrad
<
T
>
(
*
output_grad
,
input_grad
,
ratio_h
,
ratio_w
,
n
,
c
,
out_h
,
out_w
);
ratio_w
,
n
,
c
,
out_h
,
out_w
,
align_corners
);
}
}
};
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
e402c0ec
...
...
@@ -932,7 +932,7 @@ def dynamic_gru(input,
create ParamAttr as param_attr. If the Initializer of the param_attr
is not set, the parameter is initialized with Xavier. Default: None.
bias_attr (ParamAttr|bool|None): The parameter attribute for the bias
of GRU.
Note that the bias with :math:`(1
\\
times 3D)` concatenates
of GRU.Note that the bias with :math:`(1
\\
times 3D)` concatenates
the bias in the update gate, reset gate and candidate calculations.
If it is set to False, no bias will be applied to the update gate,
reset gate and candidate calculations. If it is set to None or one
...
...
@@ -1073,7 +1073,7 @@ def gru_unit(input,
create ParamAttr as param_attr. If the Initializer of the param_attr
is not set, the parameter is initialized with Xavier. Default: None.
bias_attr (ParamAttr|bool|None): The parameter attribute for the bias
of GRU.
Note that the bias with :math:`(1
\\
times 3D)` concatenates
of GRU.Note that the bias with :math:`(1
\\
times 3D)` concatenates
the bias in the update gate, reset gate and candidate calculations.
If it is set to False, no bias will be applied to the update gate,
reset gate and candidate calculations. If it is set to None or one
...
...
@@ -5403,7 +5403,7 @@ def transpose(x, perm, name=None):
Examples:
.. code-block:: python
# use append_batch_size=False to avoid prepend
ing extra
# use append_batch_size=False to avoid prepending extra
# batch size in shape
x = fluid.layers.data(name='x', shape=[5, 10, 15],
dtype='float32', append_batch_size=False)
...
...
@@ -5920,7 +5920,7 @@ def reshape(x, shape, actual_shape=None, act=None, inplace=False, name=None):
than :attr:`shape`.
act (str): The non-linear activation to be applied to the reshaped tensor
variable.
inplace(bool):
Must use :attr:`False` if :attr:`x` is used in multiple
inplace(bool): Must use :attr:`False` if :attr:`x` is used in multiple
operators. If this flag is set :attr:`True`, reuse input
:attr:`x` to reshape, which will change the shape of
tensor variable :attr:`x` and might cause errors when
...
...
@@ -6581,7 +6581,9 @@ def image_resize(input,
scale
=
None
,
name
=
None
,
resample
=
'BILINEAR'
,
actual_shape
=
None
):
actual_shape
=
None
,
align_corners
=
True
,
align_mode
=
1
):
"""
**Resize a Batch of Images**
...
...
@@ -6594,6 +6596,80 @@ def image_resize(input,
'NEAREST' : Nearest neighbor interpolation
Nearest neighbor interpolation is to perform nearest neighbor interpolation
in both the 3rd dimention(in height direction) and the 4th dimention(in width
direction) on input tensor.
Bilinear interpolation is an extension of linear interpolation for
interpolating functions of two variables (e.g. H-direction and
W-direction in this op) on a rectilinear 2D grid. The key idea is
to perform linear interpolation first in one direction, and then
again in the other direction.
Align_corners and align_mode are optinal parameters,the calculation method
of interpolation can be selected by them.
Example:
For scale:
if align_corners = True && out_size > 1 :
scale_factor = (in_size-1.0)/(out_size-1.0)
else:
scale_factor = float(in_size/out_size)
Nearest neighbor interpolation:
if:
align_corners = False
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = \left \lfloor {H_{in} * scale_{}factor}}
\r
ight
\r
floor
W_out = \left \lfloor {W_{in} * scale_{}factor}}
\r
ight
\r
floor
else:
align_corners = True
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = round(H_{in} * scale_{factor})
W_out = round(W_{in} * scale_{factor})
Bilinear interpolation:
if:
align_corners = False , align_mode = 0
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = (H_{in}+0.5) * scale_{factor} - 0.5
W_out = (W_{in}+0.5) * scale_{factor} - 0.5
else:
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = H_{in} * scale_{factor}
W_out = W_{in} * scale_{factor}
For details of nearest neighbor interpolation, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation.
For details of bilinear interpolation, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Bilinear_interpolation.
Args:
input (Variable): The input tensor of image resize layer,
This is a 4-D tensor of the shape
...
...
@@ -6623,6 +6699,13 @@ def image_resize(input,
set, otherwise errors would be occured in graph
constructing stage.
Default: None
align_corners(bool) : An optional bool, If True, the centers of the 4 corner pixels of the
input and output tensors are aligned, preserving the values at the
corner pixels.
Default: True
align_mode(int) : An optional for bilinear interpolation. can be
\'
0
\'
for src_idx = scale*(dst_indx+0.5)-0.5 , can be
\'
1
\'
for
src_idx = scale*dst_index .
Returns:
Variable: The output is a 4-D tensor of the shape
...
...
@@ -6635,6 +6718,8 @@ def image_resize(input,
or 'NEAREST' currently.
ValueError: One of out_shape and scale must not be None.
ValueError: out_shape length should be 2.
TypeError: align_corners shoule be a bool value
ValueError: align_mode can only be '0' or '1'
Examples:
.. code-block:: python
...
...
@@ -6650,6 +6735,12 @@ def image_resize(input,
"The 'resample' of image_resize can only be 'BILINEAR' or 'NEAREST' currently."
)
resample_type
=
resample_methods
[
resample
]
if
not
isinstance
(
align_corners
,
bool
):
raise
TypeError
(
"Attr align_corners should be a bool value"
)
if
align_mode
!=
0
and
align_mode
!=
1
:
raise
ValueError
(
"align_mode can only be 0 or 1"
)
if
out_shape
is
None
and
scale
is
None
:
raise
ValueError
(
"One of out_shape and scale must not be None."
)
helper
=
LayerHelper
(
'{}_interp'
.
format
(
resample_type
),
**
locals
())
...
...
@@ -6689,9 +6780,13 @@ def image_resize(input,
type
=
'{}_interp'
.
format
(
resample_type
),
inputs
=
inputs
,
outputs
=
{
"Out"
:
out
},
attrs
=
{
"out_h"
:
out_h
,
"out_w"
:
out_w
,
"interp_method"
:
resample_type
})
attrs
=
{
"out_h"
:
out_h
,
"out_w"
:
out_w
,
"interp_method"
:
resample_type
,
"align_corners"
:
align_corners
,
"align_mode"
:
align_mode
})
return
out
...
...
@@ -6700,7 +6795,9 @@ def resize_bilinear(input,
out_shape
=
None
,
scale
=
None
,
name
=
None
,
actual_shape
=
None
):
actual_shape
=
None
,
align_corners
=
True
,
align_mode
=
1
):
"""
Resize input by performing bilinear interpolation based on given
output shape which specified by actual_shape, out_shape and scale
...
...
@@ -6715,6 +6812,47 @@ def resize_bilinear(input,
For details of bilinear interpolation, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Bilinear_interpolation
Align_corners and align_mode are optinal parameters,the calculation
method of interpolation can be selected by them.
Align_corners and align_mode are optinal parameters,the calculation method
of interpolation can be selected by them.
Example:
For scale:
if align_corners = True && out_size > 1 :
scale_factor = (in_size-1.0)/(out_size-1.0)
else:
scale_factor = float(in_size/out_size)
Bilinear interpolation:
if:
align_corners = False , align_mode = 0
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = (H_{in}+0.5) * scale_{factor} - 0.5
W_out = (W_{in}+0.5) * scale_{factor} - 0.5
else:
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = H_{in} * scale_{factor}
W_out = W_{in} * scale_{factor}
Args:
input(${x_type}): ${x_comment}.
...
...
@@ -6738,6 +6876,8 @@ def resize_bilinear(input,
set, otherwise errors would be occured in graph
constructing stage.
Default: None
align_corners(bool): ${align_corners_comment}
align_mode(bool): ${align_mode_comment}
Returns:
${out_comment}.
...
...
@@ -6748,7 +6888,8 @@ def resize_bilinear(input,
out = fluid.layers.resize_bilinear(input, out_shape=[12, 12])
"""
return
image_resize
(
input
,
out_shape
,
scale
,
name
,
'BILINEAR'
,
actual_shape
)
return
image_resize
(
input
,
out_shape
,
scale
,
name
,
'BILINEAR'
,
actual_shape
,
align_corners
,
align_mode
)
@
templatedoc
(
op_type
=
"nearest_interp"
)
...
...
@@ -6756,13 +6897,48 @@ def resize_nearest(input,
out_shape
=
None
,
scale
=
None
,
name
=
None
,
actual_shape
=
None
):
actual_shape
=
None
,
align_corners
=
True
):
"""
Resize input by performing nearest neighbor interpolation in both the
3rd dimention(in height direction) and the 4th dimention(in width
direction) based on given output shape which specified by actual_shape,
out_shape and scale in priority order.
Example:
For scale:
if align_corners = True && out_size > 1 :
scale_factor = (in_size-1.0)/(out_size-1.0)
else:
scale_factor = float(in_size/out_size)
Nearest neighbor interpolation:
if:
align_corners = False
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = \left \lfloor {H_{in} * scale_{}factor}}
\r
ight
\r
floor
W_out = \left \lfloor {W_{in} * scale_{}factor}}
\r
ight
\r
floor
else:
align_corners = True
input : (N,C,H_in,W_in)
output: (N,C,H_out,W_out) where:
H_out = round(H_{in} * scale_{factor})
W_out = round(W_{in} * scale_{factor})
For details of nearest neighbor interpolation, please refer to Wikipedia:
https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation
...
...
@@ -6789,6 +6965,7 @@ def resize_nearest(input,
set, otherwise errors would be occured in graph
constructing stage.
Default: None
align_corners(bool): ${align_corners_comment}
Returns:
${out_comment}.
...
...
@@ -6799,7 +6976,8 @@ def resize_nearest(input,
out = fluid.layers.resize_nearest(input, out_shape=[12, 12])
"""
return
image_resize
(
input
,
out_shape
,
scale
,
name
,
'NEAREST'
,
actual_shape
)
return
image_resize
(
input
,
out_shape
,
scale
,
name
,
'NEAREST'
,
actual_shape
,
align_corners
)
def
image_resize_short
(
input
,
out_short_len
,
resample
=
'BILINEAR'
):
...
...
python/paddle/fluid/tests/unittests/test_bilinear_interp_op.py
浏览文件 @
e402c0ec
...
...
@@ -20,7 +20,13 @@ from op_test import OpTest
import
paddle.fluid.core
as
core
def
bilinear_interp_np
(
input
,
out_h
,
out_w
,
out_size
=
None
,
actual_shape
=
None
):
def
bilinear_interp_np
(
input
,
out_h
,
out_w
,
out_size
=
None
,
actual_shape
=
None
,
align_corners
=
True
,
align_mode
=
0
):
"""bilinear interpolation implement in shape [N, C, H, W]"""
if
out_size
is
not
None
:
out_h
=
out_size
[
0
]
...
...
@@ -29,25 +35,45 @@ def bilinear_interp_np(input, out_h, out_w, out_size=None, actual_shape=None):
out_h
=
actual_shape
[
0
]
out_w
=
actual_shape
[
1
]
batch_size
,
channel
,
in_h
,
in_w
=
input
.
shape
ratio_h
=
ratio_w
=
0.0
if
out_h
>
1
:
ratio_h
=
(
in_h
-
1.0
)
/
(
out_h
-
1.0
)
else
:
ratio_h
=
0.0
if
(
align_corners
):
ratio_h
=
(
in_h
-
1.0
)
/
(
out_h
-
1.0
)
else
:
ratio_h
=
1.0
*
in_h
/
out_h
if
out_w
>
1
:
ratio_w
=
(
in_w
-
1.0
)
/
(
out_w
-
1.0
)
else
:
ratio_w
=
0.0
if
(
align_corners
):
ratio_w
=
(
in_w
-
1.0
)
/
(
out_w
-
1.0
)
else
:
ratio_w
=
1.0
*
in_w
/
out_w
out
=
np
.
zeros
((
batch_size
,
channel
,
out_h
,
out_w
))
for
i
in
range
(
out_h
):
h
=
int
(
ratio_h
*
i
)
if
(
align_mode
==
0
and
not
align_corners
):
h
=
int
(
ratio_h
*
(
i
+
0.5
)
-
0.5
)
else
:
h
=
int
(
ratio_h
*
i
)
h
=
max
(
0
,
h
)
hid
=
1
if
h
<
in_h
-
1
else
0
h1lambda
=
ratio_h
*
i
-
h
if
(
align_mode
==
0
and
not
align_corners
):
h1lambda
=
ratio_h
*
(
i
+
0.5
)
-
0.5
-
h
else
:
h1lambda
=
ratio_h
*
i
-
h
h2lambda
=
1.0
-
h1lambda
for
j
in
range
(
out_w
):
w
=
int
(
ratio_w
*
j
)
if
(
align_mode
==
0
and
not
align_corners
):
w
=
int
(
ratio_w
*
(
j
+
0.5
)
-
0.5
)
else
:
w
=
int
(
ratio_w
*
j
)
w
=
max
(
0
,
w
)
wid
=
1
if
w
<
in_w
-
1
else
0
w1lambda
=
ratio_w
*
j
-
w
if
(
align_mode
==
0
and
not
align_corners
):
w1lambda
=
ratio_w
*
(
j
+
0.5
)
-
0.5
-
w
else
:
w1lambda
=
ratio_w
*
j
-
w
w2lambda
=
1.0
-
w1lambda
out
[:,
:,
i
,
j
]
=
h2lambda
*
(
w2lambda
*
input
[:,
:,
h
,
w
]
+
...
...
@@ -66,7 +92,8 @@ class TestBilinearInterpOp(OpTest):
input_np
=
np
.
random
.
random
(
self
.
input_shape
).
astype
(
"float32"
)
output_np
=
bilinear_interp_np
(
input_np
,
self
.
out_h
,
self
.
out_w
,
self
.
out_size
,
self
.
actual_shape
)
self
.
out_size
,
self
.
actual_shape
,
self
.
align_corners
,
self
.
align_mode
)
self
.
inputs
=
{
'X'
:
input_np
}
if
self
.
out_size
is
not
None
:
self
.
inputs
[
'OutSize'
]
=
self
.
out_size
...
...
@@ -75,7 +102,9 @@ class TestBilinearInterpOp(OpTest):
self
.
attrs
=
{
'out_h'
:
self
.
out_h
,
'out_w'
:
self
.
out_w
,
'interp_method'
:
self
.
interp_method
'interp_method'
:
self
.
interp_method
,
'align_corners'
:
self
.
align_corners
,
'align_mode'
:
self
.
align_mode
}
self
.
outputs
=
{
'Out'
:
output_np
}
...
...
@@ -91,6 +120,8 @@ class TestBilinearInterpOp(OpTest):
self
.
out_h
=
2
self
.
out_w
=
2
self
.
out_size
=
np
.
array
([
3
,
3
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase1
(
TestBilinearInterpOp
):
...
...
@@ -99,6 +130,8 @@ class TestBilinearInterpCase1(TestBilinearInterpOp):
self
.
input_shape
=
[
4
,
1
,
7
,
8
]
self
.
out_h
=
1
self
.
out_w
=
1
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase2
(
TestBilinearInterpOp
):
...
...
@@ -107,6 +140,8 @@ class TestBilinearInterpCase2(TestBilinearInterpOp):
self
.
input_shape
=
[
3
,
3
,
9
,
6
]
self
.
out_h
=
12
self
.
out_w
=
12
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase3
(
TestBilinearInterpOp
):
...
...
@@ -115,6 +150,8 @@ class TestBilinearInterpCase3(TestBilinearInterpOp):
self
.
input_shape
=
[
1
,
1
,
128
,
64
]
self
.
out_h
=
64
self
.
out_w
=
128
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase4
(
TestBilinearInterpOp
):
...
...
@@ -124,6 +161,8 @@ class TestBilinearInterpCase4(TestBilinearInterpOp):
self
.
out_h
=
1
self
.
out_w
=
1
self
.
out_size
=
np
.
array
([
2
,
2
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase5
(
TestBilinearInterpOp
):
...
...
@@ -133,6 +172,8 @@ class TestBilinearInterpCase5(TestBilinearInterpOp):
self
.
out_h
=
12
self
.
out_w
=
12
self
.
out_size
=
np
.
array
([
11
,
11
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase6
(
TestBilinearInterpOp
):
...
...
@@ -142,6 +183,8 @@ class TestBilinearInterpCase6(TestBilinearInterpOp):
self
.
out_h
=
64
self
.
out_w
=
128
self
.
out_size
=
np
.
array
([
65
,
129
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpActualShape
(
TestBilinearInterpOp
):
...
...
@@ -151,6 +194,8 @@ class TestBilinearInterpActualShape(TestBilinearInterpOp):
self
.
out_h
=
64
self
.
out_w
=
32
self
.
out_size
=
np
.
array
([
66
,
40
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpOpUint8
(
OpTest
):
...
...
@@ -162,14 +207,17 @@ class TestBilinearInterpOpUint8(OpTest):
input_np
=
np
.
random
.
randint
(
low
=
0
,
high
=
256
,
size
=
self
.
input_shape
).
astype
(
"uint8"
)
output_np
=
bilinear_interp_np
(
input_np
,
self
.
out_h
,
self
.
out_w
,
self
.
out_size
,
self
.
actual_shape
)
self
.
out_size
,
self
.
actual_shape
,
self
.
align_corners
,
self
.
align_mode
)
self
.
inputs
=
{
'X'
:
input_np
}
if
self
.
out_size
is
not
None
:
self
.
inputs
[
'OutSize'
]
=
self
.
out_size
self
.
attrs
=
{
'out_h'
:
self
.
out_h
,
'out_w'
:
self
.
out_w
,
'interp_method'
:
self
.
interp_method
'interp_method'
:
self
.
interp_method
,
'align_corners'
:
self
.
align_corners
,
'align_mode'
:
self
.
align_mode
}
self
.
outputs
=
{
'Out'
:
output_np
}
...
...
@@ -181,6 +229,8 @@ class TestBilinearInterpOpUint8(OpTest):
self
.
input_shape
=
[
1
,
3
,
9
,
6
]
self
.
out_h
=
10
self
.
out_w
=
9
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase1Uint8
(
TestBilinearInterpOpUint8
):
...
...
@@ -189,6 +239,8 @@ class TestBilinearInterpCase1Uint8(TestBilinearInterpOpUint8):
self
.
input_shape
=
[
2
,
3
,
128
,
64
]
self
.
out_h
=
120
self
.
out_w
=
50
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpCase2Uint8
(
TestBilinearInterpOpUint8
):
...
...
@@ -198,6 +250,26 @@ class TestBilinearInterpCase2Uint8(TestBilinearInterpOpUint8):
self
.
out_h
=
5
self
.
out_w
=
13
self
.
out_size
=
np
.
array
([
6
,
15
]).
astype
(
"int32"
)
self
.
align_corners
=
True
self
.
align_mode
=
1
class
TestBilinearInterpOtherMethod1
(
TestBilinearInterpOp
):
def
set_align_mode
(
self
):
self
.
align_corners
=
False
self
.
align_mode
=
1
class
TestBilinearInterpWithMethod2
(
TestBilinearInterpOp
):
def
set_align_mode
(
self
):
self
.
align_corners
=
False
self
.
align_mode
=
0
class
TestBilinearInterpWithMethod3
(
TestBilinearInterpOp
):
def
set_align_mode
(
self
):
self
.
align_corners
=
True
self
.
align_mode
=
0
if
__name__
==
"__main__"
:
...
...
python/paddle/fluid/tests/unittests/test_nearest_interp_op.py
浏览文件 @
e402c0ec
...
...
@@ -24,7 +24,8 @@ def nearest_neighbor_interp_np(X,
out_h
,
out_w
,
out_size
=
None
,
actual_shape
=
None
):
actual_shape
=
None
,
align_corners
=
True
):
"""nearest neighbor interpolation implement in shape [N, C, H, W]"""
if
out_size
is
not
None
:
out_h
=
out_size
[
0
]
...
...
@@ -35,17 +36,31 @@ def nearest_neighbor_interp_np(X,
n
,
c
,
in_h
,
in_w
=
X
.
shape
ratio_h
=
ratio_w
=
0.0
if
out_h
>
1
:
ratio_h
=
(
in_h
-
1.0
)
/
(
out_h
-
1.0
)
if
out_w
>
1
:
ratio_w
=
(
in_w
-
1.0
)
/
(
out_w
-
1.0
)
if
(
out_h
>
1
):
if
(
align_corners
):
ratio_h
=
(
in_h
-
1.0
)
/
(
out_h
-
1.0
)
else
:
ratio_h
=
1.0
*
in_h
/
out_h
if
(
out_w
>
1
):
if
(
align_corners
):
ratio_w
=
(
in_w
-
1.0
)
/
(
out_w
-
1.0
)
else
:
ratio_w
=
1.0
*
in_w
/
out_w
out
=
np
.
zeros
((
n
,
c
,
out_h
,
out_w
))
for
i
in
range
(
out_h
):
in_i
=
int
(
ratio_h
*
i
+
0.5
)
for
j
in
range
(
out_w
):
in_j
=
int
(
ratio_w
*
j
+
0.5
)
out
[:,
:,
i
,
j
]
=
X
[:,
:,
in_i
,
in_j
]
if
align_corners
:
for
i
in
range
(
out_h
):
in_i
=
int
(
ratio_h
*
i
+
0.5
)
for
j
in
range
(
out_w
):
in_j
=
int
(
ratio_w
*
j
+
0.5
)
out
[:,
:,
i
,
j
]
=
X
[:,
:,
in_i
,
in_j
]
else
:
for
i
in
range
(
out_h
):
in_i
=
int
(
ratio_h
*
i
)
for
j
in
range
(
out_w
):
in_j
=
int
(
ratio_w
*
j
)
out
[:,
:,
i
,
j
]
=
X
[:,
:,
in_i
,
in_j
]
return
out
.
astype
(
X
.
dtype
)
...
...
@@ -59,7 +74,8 @@ class TestNearestInterpOp(OpTest):
input_np
=
np
.
random
.
random
(
self
.
input_shape
).
astype
(
"float32"
)
output_np
=
nearest_neighbor_interp_np
(
input_np
,
self
.
out_h
,
self
.
out_w
,
self
.
out_size
,
self
.
actual_shape
)
self
.
out_size
,
self
.
actual_shape
,
self
.
align_corners
)
self
.
inputs
=
{
'X'
:
input_np
}
if
self
.
out_size
is
not
None
:
self
.
inputs
[
'OutSize'
]
=
self
.
out_size
...
...
@@ -68,7 +84,8 @@ class TestNearestInterpOp(OpTest):
self
.
attrs
=
{
'out_h'
:
self
.
out_h
,
'out_w'
:
self
.
out_w
,
'interp_method'
:
self
.
interp_method
'interp_method'
:
self
.
interp_method
,
'align_corners'
:
self
.
align_corners
,
}
self
.
outputs
=
{
'Out'
:
output_np
}
...
...
@@ -84,6 +101,7 @@ class TestNearestInterpOp(OpTest):
self
.
out_h
=
2
self
.
out_w
=
2
self
.
out_size
=
np
.
array
([
3
,
3
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase1
(
TestNearestInterpOp
):
...
...
@@ -92,6 +110,7 @@ class TestNearestNeighborInterpCase1(TestNearestInterpOp):
self
.
input_shape
=
[
4
,
1
,
7
,
8
]
self
.
out_h
=
1
self
.
out_w
=
1
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase2
(
TestNearestInterpOp
):
...
...
@@ -100,6 +119,7 @@ class TestNearestNeighborInterpCase2(TestNearestInterpOp):
self
.
input_shape
=
[
3
,
3
,
9
,
6
]
self
.
out_h
=
12
self
.
out_w
=
12
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase3
(
TestNearestInterpOp
):
...
...
@@ -108,6 +128,7 @@ class TestNearestNeighborInterpCase3(TestNearestInterpOp):
self
.
input_shape
=
[
1
,
1
,
128
,
64
]
self
.
out_h
=
64
self
.
out_w
=
128
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase4
(
TestNearestInterpOp
):
...
...
@@ -117,6 +138,7 @@ class TestNearestNeighborInterpCase4(TestNearestInterpOp):
self
.
out_h
=
1
self
.
out_w
=
1
self
.
out_size
=
np
.
array
([
2
,
2
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase5
(
TestNearestInterpOp
):
...
...
@@ -126,6 +148,7 @@ class TestNearestNeighborInterpCase5(TestNearestInterpOp):
self
.
out_h
=
12
self
.
out_w
=
12
self
.
out_size
=
np
.
array
([
11
,
11
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase6
(
TestNearestInterpOp
):
...
...
@@ -135,6 +158,7 @@ class TestNearestNeighborInterpCase6(TestNearestInterpOp):
self
.
out_h
=
64
self
.
out_w
=
128
self
.
out_size
=
np
.
array
([
65
,
129
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestNeighborInterpActualShape
(
TestNearestInterpOp
):
...
...
@@ -144,6 +168,7 @@ class TestNearestNeighborInterpActualShape(TestNearestInterpOp):
self
.
out_h
=
64
self
.
out_w
=
32
self
.
out_size
=
np
.
array
([
66
,
40
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestInterpOpUint8
(
OpTest
):
...
...
@@ -155,14 +180,16 @@ class TestNearestInterpOpUint8(OpTest):
input_np
=
np
.
random
.
randint
(
low
=
0
,
high
=
256
,
size
=
self
.
input_shape
).
astype
(
"uint8"
)
output_np
=
nearest_neighbor_interp_np
(
input_np
,
self
.
out_h
,
self
.
out_w
,
self
.
out_size
,
self
.
actual_shape
)
self
.
out_size
,
self
.
actual_shape
,
self
.
align_corners
)
self
.
inputs
=
{
'X'
:
input_np
}
if
self
.
out_size
is
not
None
:
self
.
inputs
[
'OutSize'
]
=
self
.
out_size
self
.
attrs
=
{
'out_h'
:
self
.
out_h
,
'out_w'
:
self
.
out_w
,
'interp_method'
:
self
.
interp_method
'interp_method'
:
self
.
interp_method
,
'align_corners'
:
self
.
align_corners
}
self
.
outputs
=
{
'Out'
:
output_np
}
...
...
@@ -174,6 +201,7 @@ class TestNearestInterpOpUint8(OpTest):
self
.
input_shape
=
[
1
,
3
,
9
,
6
]
self
.
out_h
=
10
self
.
out_w
=
9
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase1Uint8
(
TestNearestInterpOpUint8
):
...
...
@@ -182,6 +210,7 @@ class TestNearestNeighborInterpCase1Uint8(TestNearestInterpOpUint8):
self
.
input_shape
=
[
2
,
3
,
128
,
64
]
self
.
out_h
=
120
self
.
out_w
=
50
self
.
align_corners
=
True
class
TestNearestNeighborInterpCase2Uint8
(
TestNearestInterpOpUint8
):
...
...
@@ -191,6 +220,12 @@ class TestNearestNeighborInterpCase2Uint8(TestNearestInterpOpUint8):
self
.
out_h
=
5
self
.
out_w
=
13
self
.
out_size
=
np
.
array
([
6
,
15
]).
astype
(
"int32"
)
self
.
align_corners
=
True
class
TestNearestInterpWithoutCorners
(
TestNearestInterpOp
):
def
set_align_corners
(
self
):
self
.
align_corners
=
False
if
__name__
==
"__main__"
:
...
...
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