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
PaddleSeg
提交
9efa0289
P
PaddleSeg
项目概览
PaddlePaddle
/
PaddleSeg
通知
285
Star
8
Fork
1
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
53
列表
看板
标记
里程碑
合并请求
3
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleSeg
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
53
Issue
53
列表
看板
标记
里程碑
合并请求
3
合并请求
3
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
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
9efa0289
编写于
9月 22, 2020
作者:
M
michaelowenliu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
re-design deeplab model
上级
ddc3d5cb
变更
7
隐藏空白更改
内联
并排
Showing
7 changed file
with
190 addition
and
140 deletion
+190
-140
dygraph/paddleseg/models/ann.py
dygraph/paddleseg/models/ann.py
+15
-17
dygraph/paddleseg/models/common/pyramid_pool.py
dygraph/paddleseg/models/common/pyramid_pool.py
+23
-25
dygraph/paddleseg/models/deeplab.py
dygraph/paddleseg/models/deeplab.py
+117
-64
dygraph/paddleseg/models/fast_scnn.py
dygraph/paddleseg/models/fast_scnn.py
+12
-12
dygraph/paddleseg/models/gcnet.py
dygraph/paddleseg/models/gcnet.py
+9
-9
dygraph/paddleseg/models/ocrnet.py
dygraph/paddleseg/models/ocrnet.py
+9
-9
dygraph/paddleseg/models/pspnet.py
dygraph/paddleseg/models/pspnet.py
+5
-4
未找到文件。
dygraph/paddleseg/models/ann.py
浏览文件 @
9efa0289
...
...
@@ -28,7 +28,7 @@ class ANN(nn.Layer):
"""
The ANN implementation based on PaddlePaddle.
The or
ginal arti
le refers to
The or
iginal artic
le refers to
Zhen, Zhu, et al. "Asymmetric Non-local Neural Networks for Semantic Segmentation."
(https://arxiv.org/pdf/1908.07678.pdf)
...
...
@@ -37,8 +37,8 @@ class ANN(nn.Layer):
Args:
num_classes (int): the unique number of target classes.
backbone (Paddle.nn.Layer): backbone network, currently support Resnet50/101.
model_pretrained (str): the path of pretrained model. Defaul
l
t to None.
backbone_indices (tuple): two values in the tuple indicte the indices of output of backbone.
model_pretrained (str): the path of pretrained model. Default to None.
backbone_indices (tuple): two values in the tuple indic
a
te the indices of output of backbone.
the first index will be taken as low-level features; the second one will be
taken as high-level features in AFNB module. Usually backbone consists of four
downsampling stage, and return an output of each stage, so we set default (2, 3),
...
...
@@ -48,7 +48,7 @@ class ANN(nn.Layer):
Default to 256.
inter_channels (int): both input and output channels of APNB modules.
psp_size (tuple): the out size of pooled feature maps. Default to (1, 3, 6, 8).
enable_auxiliary_loss (bool): a bool values indictes whether adding auxiliary loss. Default to True.
enable_auxiliary_loss (bool): a bool values indic
a
tes whether adding auxiliary loss. Default to True.
"""
def
__init__
(
self
,
...
...
@@ -79,7 +79,7 @@ class ANN(nn.Layer):
psp_size
=
psp_size
)
self
.
context
=
nn
.
Sequential
(
layer_libs
.
ConvB
nRelu
(
layer_libs
.
ConvB
NReLU
(
in_channels
=
high_in_channels
,
out_channels
=
inter_channels
,
kernel_size
=
3
,
...
...
@@ -94,9 +94,7 @@ class ANN(nn.Layer):
psp_size
=
psp_size
))
self
.
cls
=
nn
.
Conv2d
(
in_channels
=
inter_channels
,
out_channels
=
num_classes
,
kernel_size
=
1
)
in_channels
=
inter_channels
,
out_channels
=
num_classes
,
kernel_size
=
1
)
self
.
auxlayer
=
layer_libs
.
AuxLayer
(
in_channels
=
low_in_channels
,
inter_channels
=
low_in_channels
//
2
,
...
...
@@ -122,7 +120,8 @@ class ANN(nn.Layer):
if
self
.
enable_auxiliary_loss
:
auxiliary_logit
=
self
.
auxlayer
(
low_level_x
)
auxiliary_logit
=
F
.
resize_bilinear
(
auxiliary_logit
,
input
.
shape
[
2
:])
auxiliary_logit
=
F
.
resize_bilinear
(
auxiliary_logit
,
input
.
shape
[
2
:])
logit_list
.
append
(
auxiliary_logit
)
return
logit_list
...
...
@@ -219,7 +218,7 @@ class APNB(nn.Layer):
SelfAttentionBlock_APNB
(
in_channels
,
out_channels
,
key_channels
,
value_channels
,
size
)
for
size
in
sizes
])
self
.
conv_bn
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
*
2
,
out_channels
=
out_channels
,
kernel_size
=
1
)
...
...
@@ -280,11 +279,11 @@ class SelfAttentionBlock_AFNB(nn.Layer):
if
out_channels
==
None
:
self
.
out_channels
=
high_in_channels
self
.
pool
=
nn
.
Pool2D
(
pool_size
=
(
scale
,
scale
),
pool_type
=
"max"
)
self
.
f_key
=
layer_libs
.
ConvB
nRelu
(
self
.
f_key
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
low_in_channels
,
out_channels
=
key_channels
,
kernel_size
=
1
)
self
.
f_query
=
layer_libs
.
ConvB
nRelu
(
self
.
f_query
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
high_in_channels
,
out_channels
=
key_channels
,
kernel_size
=
1
)
...
...
@@ -315,7 +314,7 @@ class SelfAttentionBlock_AFNB(nn.Layer):
key
=
_pp_module
(
key
,
self
.
psp_size
)
sim_map
=
paddle
.
matmul
(
query
,
key
)
sim_map
=
(
self
.
key_channels
**
-
.
5
)
*
sim_map
sim_map
=
(
self
.
key_channels
**
-
.
5
)
*
sim_map
sim_map
=
F
.
softmax
(
sim_map
,
axis
=-
1
)
context
=
paddle
.
matmul
(
sim_map
,
value
)
...
...
@@ -358,7 +357,7 @@ class SelfAttentionBlock_APNB(nn.Layer):
self
.
value_channels
=
value_channels
self
.
pool
=
nn
.
Pool2D
(
pool_size
=
(
scale
,
scale
),
pool_type
=
"max"
)
self
.
f_key
=
layer_libs
.
ConvB
nRelu
(
self
.
f_key
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
self
.
in_channels
,
out_channels
=
self
.
key_channels
,
kernel_size
=
1
)
...
...
@@ -384,15 +383,14 @@ class SelfAttentionBlock_APNB(nn.Layer):
value
=
paddle
.
transpose
(
value
,
perm
=
(
0
,
2
,
1
))
query
=
self
.
f_query
(
x
)
query
=
paddle
.
reshape
(
query
,
shape
=
(
batch_size
,
self
.
key_channels
,
-
1
))
query
=
paddle
.
reshape
(
query
,
shape
=
(
batch_size
,
self
.
key_channels
,
-
1
))
query
=
paddle
.
transpose
(
query
,
perm
=
(
0
,
2
,
1
))
key
=
self
.
f_key
(
x
)
key
=
_pp_module
(
key
,
self
.
psp_size
)
sim_map
=
paddle
.
matmul
(
query
,
key
)
sim_map
=
(
self
.
key_channels
**
-
.
5
)
*
sim_map
sim_map
=
(
self
.
key_channels
**
-
.
5
)
*
sim_map
sim_map
=
F
.
softmax
(
sim_map
,
axis
=-
1
)
context
=
paddle
.
matmul
(
sim_map
,
value
)
...
...
dygraph/paddleseg/models/common/pyramid_pool.py
浏览文件 @
9efa0289
...
...
@@ -13,7 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import
paddle
from
paddle
import
nn
import
paddle.nn.functional
as
F
...
...
@@ -34,11 +33,11 @@ class ASPPModule(nn.Layer):
image_pooling: if augmented with image-level features.
"""
def
__init__
(
self
,
aspp_ratios
,
in_channels
,
out_channels
,
sep_conv
=
False
,
def
__init__
(
self
,
aspp_ratios
,
in_channels
,
out_channels
,
sep_conv
=
False
,
image_pooling
=
False
):
super
(
ASPPModule
,
self
).
__init__
()
...
...
@@ -47,42 +46,41 @@ class ASPPModule(nn.Layer):
for
ratio
in
aspp_ratios
:
if
sep_conv
and
ratio
>
1
:
conv_func
=
layer_libs
.
DepthwiseConvB
nRelu
conv_func
=
layer_libs
.
DepthwiseConvB
NReLU
else
:
conv_func
=
layer_libs
.
ConvB
nRelu
conv_func
=
layer_libs
.
ConvB
NReLU
block
=
conv_func
(
in_channels
=
in_channels
,
out_channels
=
out_channels
,
kernel_size
=
1
if
ratio
==
1
else
3
,
dilation
=
ratio
,
padding
=
0
if
ratio
==
1
else
ratio
)
padding
=
0
if
ratio
==
1
else
ratio
)
self
.
aspp_blocks
.
append
(
block
)
out_size
=
len
(
self
.
aspp_blocks
)
if
image_pooling
:
self
.
global_avg_pool
=
nn
.
Sequential
(
nn
.
AdaptiveAvgPool2d
(
output_size
=
(
1
,
1
)),
layer_libs
.
ConvB
nRelu
(
in_channels
,
out_channels
,
kernel_size
=
1
,
bias_attr
=
False
)
)
layer_libs
.
ConvB
NReLU
(
in_channels
,
out_channels
,
kernel_size
=
1
,
bias_attr
=
False
)
)
out_size
+=
1
self
.
image_pooling
=
image_pooling
self
.
conv_bn_relu
=
layer_libs
.
ConvB
nRelu
(
in_channels
=
out_channels
*
out_size
,
out_channels
=
out_channels
,
self
.
conv_bn_relu
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
out_channels
*
out_size
,
out_channels
=
out_channels
,
kernel_size
=
1
)
self
.
dropout
=
nn
.
Dropout
(
p
=
0.1
)
# drop rate
self
.
dropout
=
nn
.
Dropout
(
p
=
0.1
)
# drop rate
def
forward
(
self
,
x
):
outputs
=
[]
for
block
in
self
.
aspp_blocks
:
outputs
.
append
(
block
(
x
))
if
self
.
image_pooling
:
img_avg
=
self
.
global_avg_pool
(
x
)
img_avg
=
F
.
resize_bilinear
(
img_avg
,
out_shape
=
x
.
shape
[
2
:])
...
...
@@ -93,17 +91,17 @@ class ASPPModule(nn.Layer):
x
=
self
.
dropout
(
x
)
return
x
class
PPModule
(
nn
.
Layer
):
"""
Pyramid pooling module orginally in PSPNet
Pyramid pooling module or
i
ginally in PSPNet
Args:
in_channels (int): the number of intput channels to pyramid pooling module.
out_channels (int): the number of output channels after pyramid pooling module.
bin_sizes (tuple): the out size of pooled feature maps. Default to (1,2,3,6).
dim_reduction (bool): a bool value represent if redu
ing diment
ion after pooling. Default to True.
dim_reduction (bool): a bool value represent if redu
cing dimens
ion after pooling. Default to True.
"""
def
__init__
(
self
,
...
...
@@ -125,7 +123,7 @@ class PPModule(nn.Layer):
for
size
in
bin_sizes
])
self
.
conv_bn_relu2
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu2
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
+
inter_channels
*
len
(
bin_sizes
),
out_channels
=
out_channels
,
kernel_size
=
3
,
...
...
@@ -135,7 +133,7 @@ class PPModule(nn.Layer):
"""
Create one pooling layer.
In our implementation, we adopt the same dimen
t
ion reduction as the original paper that might be
In our implementation, we adopt the same dimen
s
ion reduction as the original paper that might be
slightly different with other implementations.
After pooling, the channels are reduced to 1/len(bin_sizes) immediately, while some other implementations
...
...
@@ -151,7 +149,7 @@ class PPModule(nn.Layer):
"""
prior
=
nn
.
AdaptiveAvgPool2d
(
output_size
=
(
size
,
size
))
conv
=
layer_libs
.
ConvB
nRelu
(
conv
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
,
out_channels
=
out_channels
,
kernel_size
=
1
)
return
nn
.
Sequential
(
prior
,
conv
)
...
...
@@ -167,4 +165,4 @@ class PPModule(nn.Layer):
cat
=
paddle
.
concat
(
cat_layers
,
axis
=
1
)
out
=
self
.
conv_bn_relu2
(
cat
)
return
out
\ No newline at end of file
return
out
dygraph/paddleseg/models/deeplab.py
浏览文件 @
9efa0289
...
...
@@ -29,140 +29,193 @@ class DeepLabV3P(nn.Layer):
"""
The DeepLabV3Plus implementation based on PaddlePaddle.
The orginal artile refers to
"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation"
Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam.
The original article refers to
Liang-Chieh Chen, et, al. "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation"
(https://arxiv.org/abs/1802.02611)
The DeepLabV3P consists of three main components, Backbone, ASPP and Decoder.
Args:
num_classes (int): the unique number of target classes.
backbone (paddle.nn.Layer): backbone network, currently support Xception65, Resnet101_vd.
model_pretrained (str): the path of pretrained model.
aspp_ratios (tuple): the dilation rate using in ASSP module.
if output_stride=16, aspp_ratios should be set as (1, 6, 12, 18).
if output_stride=8, aspp_ratios is (1, 12, 24, 36).
backbone_indices (tuple): two values in the tuple indicte the indices of output of backbone.
the first index will be taken as a low-level feature in Deconder component;
backbone (paddle.nn.Layer): backbone network, currently support Resnet50_vd/Resnet101_vd/Xception65.
backbone_indices (tuple): two values in the tuple indicate the indices of output of backbone.
the first index will be taken as a low-level feature in Decoder component;
the second one will be taken as input of ASPP component.
Usually backbone consists of four downsampling stage, and return an output of
each stage, so we set default (0, 3), which means taking feature map of the first
stage in backbone as low-level feature used in Decoder, and feature map of the fourth
stage as input of ASPP.
backbone_channels (tuple): the same length with "backbone_indices". It indicates the channels of corresponding index.
aspp_ratios (tuple): the dilation rate using in ASSP module.
if output_stride=16, aspp_ratios should be set as (1, 6, 12, 18).
if output_stride=8, aspp_ratios is (1, 12, 24, 36).
aspp_out_channels (int): the output channels of ASPP module.
pretrained (str): the path of pretrained model for fine tuning.
"""
def
__init__
(
self
,
num_classes
,
backbone
,
backbone_pretrained
=
None
,
model_pretrained
=
None
,
backbone_indices
=
(
0
,
3
),
backbone_channels
=
(
256
,
2048
),
aspp_ratios
=
(
1
,
6
,
12
,
18
),
aspp_out_channels
=
256
):
aspp_out_channels
=
256
,
pretrained
=
None
):
super
(
DeepLabV3P
,
self
).
__init__
()
self
.
backbone
=
backbone
self
.
backbone_pretrained
=
backbone_pretrained
self
.
model_pretrained
=
model_pretrained
backbone_channels
=
backbone
.
backbone_channels
self
.
head
=
DeepLabV3PHead
(
num_classes
,
backbone_indices
,
backbone_channels
,
aspp_ratios
,
aspp_out_channels
)
utils
.
load_entire_model
(
self
,
pretrained
)
def
forward
(
self
,
input
):
feat_list
=
self
.
backbone
(
input
)
logit_list
=
self
.
head
(
feat_list
)
return
[
F
.
resize_bilinear
(
logit
,
input
.
shape
[
2
:])
for
logit
in
logit_list
]
class
DeepLabV3PHead
(
nn
.
Layer
):
"""
The DeepLabV3PHead implementation based on PaddlePaddle.
Args:
num_classes (int): the unique number of target classes.
backbone_indices (tuple): two values in the tuple indicate the indices of output of backbone.
the first index will be taken as a low-level feature in Decoder component;
the second one will be taken as input of ASPP component.
Usually backbone consists of four downsampling stage, and return an output of
each stage, so we set default (0, 3), which means taking feature map of the first
stage in backbone as low-level feature used in Decoder, and feature map of the fourth
stage as input of ASPP.
backbone_channels (tuple): returned channels of backbone
aspp_ratios (tuple): the dilation rate using in ASSP module.
if output_stride=16, aspp_ratios should be set as (1, 6, 12, 18).
if output_stride=8, aspp_ratios is (1, 12, 24, 36).
aspp_out_channels (int): the output channels of ASPP module.
"""
def
__init__
(
self
,
num_classes
,
backbone_indices
,
backbone_channels
,
aspp_ratios
=
(
1
,
6
,
12
,
18
),
aspp_out_channels
=
256
):
super
(
DeepLabV3PHead
,
self
).
__init__
()
self
.
aspp
=
pyramid_pool
.
ASPPModule
(
aspp_ratios
,
backbone_channels
[
1
],
aspp_out_channels
,
sep_conv
=
True
,
image_pooling
=
True
)
self
.
decoder
=
Decoder
(
num_classes
,
backbone_channels
[
0
])
aspp_ratios
,
backbone_channels
[
backbone_indices
[
1
]],
aspp_out_channels
,
sep_conv
=
True
,
image_pooling
=
True
)
self
.
decoder
=
Decoder
(
num_classes
,
backbone_channels
[
backbone_indices
[
0
]])
self
.
backbone_indices
=
backbone_indices
self
.
init_weight
()
def
forward
(
self
,
input
,
label
=
None
):
def
forward
(
self
,
feat_list
):
logit_list
=
[]
_
,
feat_list
=
self
.
backbone
(
input
)
low_level_feat
=
feat_list
[
self
.
backbone_indices
[
0
]]
x
=
feat_list
[
self
.
backbone_indices
[
1
]]
x
=
self
.
aspp
(
x
)
logit
=
self
.
decoder
(
x
,
low_level_feat
)
logit
=
F
.
resize_bilinear
(
logit
,
input
.
shape
[
2
:])
logit_list
.
append
(
logit
)
return
logit_list
def
init_weight
(
self
):
"""
Initialize the parameters of model parts.
Args:
pretrained_model ([str], optional): the path of pretrained model. Defaults to None.
"""
if
self
.
model_pretrained
is
not
None
:
utils
.
load_pretrained_model
(
self
,
self
.
model_pretrained
)
elif
self
.
backbone_pretrained
is
not
None
:
utils
.
load_pretrained_model
(
self
.
backbone
,
self
.
backbone_pretrained
)
pass
@
manager
.
MODELS
.
add_component
class
DeepLabV3
(
nn
.
Layer
):
"""
The DeepLabV3 implementation based on PaddlePaddle.
The orginal article refers to
"Rethinking Atrous Convolution for Semantic Image Segmentation"
Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam.
The original article refers to
Liang-Chieh Chen, et, al. "Rethinking Atrous Convolution for Semantic Image Segmentation"
(https://arxiv.org/pdf/1706.05587.pdf)
Args:
Refer to DeepLabV3P above
"""
def
__init__
(
self
,
num_classes
,
backbone
,
backbone_pretrained
=
None
,
model_pretrained
=
None
,
backbone_indices
=
(
3
,),
backbone_channels
=
(
2048
,),
pretrained
=
None
,
backbone_indices
=
(
3
,
),
aspp_ratios
=
(
1
,
6
,
12
,
18
),
aspp_out_channels
=
256
):
super
(
DeepLabV3
,
self
).
__init__
()
self
.
backbone
=
backbone
backbone_channels
=
backbone
.
backbone_channels
self
.
head
=
DeepLabV3Head
(
num_classes
,
backbone_indices
,
backbone_channels
,
aspp_ratios
,
aspp_out_channels
)
utils
.
load_entire_model
(
self
,
pretrained
)
def
forward
(
self
,
input
):
feat_list
=
self
.
backbone
(
input
)
logit_list
=
self
.
head
(
feat_list
)
return
[
F
.
resize_bilinear
(
logit
,
input
.
shape
[
2
:])
for
logit
in
logit_list
]
class
DeepLabV3Head
(
nn
.
Layer
):
def
__init__
(
self
,
num_classes
,
backbone_indices
=
(
3
,
),
backbone_channels
=
(
2048
,
),
aspp_ratios
=
(
1
,
6
,
12
,
18
),
aspp_out_channels
=
256
):
super
(
DeepLabV3Head
,
self
).
__init__
()
self
.
aspp
=
pyramid_pool
.
ASPPModule
(
aspp_ratios
,
backbone_channels
[
0
],
aspp_out_channels
,
sep_conv
=
False
,
image_pooling
=
True
)
aspp_ratios
,
backbone_channels
[
backbone_indices
[
0
]],
aspp_out_channels
,
sep_conv
=
False
,
image_pooling
=
True
)
self
.
cls
=
nn
.
Conv2d
(
in_channels
=
backbone_channels
[
0
],
in_channels
=
backbone_channels
[
backbone_indices
[
0
]
],
out_channels
=
num_classes
,
kernel_size
=
1
)
self
.
backbone_indices
=
backbone_indices
self
.
init_weight
(
model_pretrained
)
self
.
init_weight
()
def
forward
(
self
,
input
,
label
=
None
):
def
forward
(
self
,
feat_list
):
logit_list
=
[]
_
,
feat_list
=
self
.
backbone
(
input
)
x
=
feat_list
[
self
.
backbone_indices
[
0
]]
logit
=
self
.
cls
(
x
)
logit
=
F
.
resize_bilinear
(
logit
,
input
.
shape
[
2
:])
logit_list
.
append
(
logit
)
return
logit_list
def
init_weight
(
self
,
pretrained_model
=
None
):
"""
Initialize the parameters of model parts.
Args:
pretrained_model ([str], optional): the path of pretrained model. Defaults to None.
"""
if
pretrained_model
is
not
None
:
if
os
.
path
.
exists
(
pretrained_model
):
utils
.
load_pretrained_model
(
self
,
pretrained_model
)
else
:
raise
Exception
(
'Pretrained model is not found: {}'
.
format
(
pretrained_model
))
def
init_weight
(
self
):
pass
class
Decoder
(
nn
.
Layer
):
...
...
@@ -178,12 +231,12 @@ class Decoder(nn.Layer):
def
__init__
(
self
,
num_classes
,
in_channels
):
super
(
Decoder
,
self
).
__init__
()
self
.
conv_bn_relu1
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu1
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
,
out_channels
=
48
,
kernel_size
=
1
)
self
.
conv_bn_relu2
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
conv_bn_relu2
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
304
,
out_channels
=
256
,
kernel_size
=
3
,
padding
=
1
)
self
.
conv_bn_relu3
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
conv_bn_relu3
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
256
,
out_channels
=
256
,
kernel_size
=
3
,
padding
=
1
)
self
.
conv
=
nn
.
Conv2d
(
in_channels
=
256
,
out_channels
=
num_classes
,
kernel_size
=
1
)
...
...
dygraph/paddleseg/models/fast_scnn.py
浏览文件 @
9efa0289
...
...
@@ -26,15 +26,15 @@ class FastSCNN(nn.Layer):
As mentioned in the original paper, FastSCNN is a real-time segmentation algorithm (123.5fps)
even for high resolution images (1024x2048).
The or
ginal arti
le refers to
The or
iginal artic
le refers to
Poudel, Rudra PK, et al. "Fast-scnn: Fast semantic segmentation network."
(https://arxiv.org/pdf/1902.04502.pdf)
Args:
num_classes (int): the unique number of target classes. Default to 2.
model_pretrained (str): the path of pretrained model. Defaul
l
t to None.
enable_auxiliary_loss (bool): a bool values indictes whether adding auxiliary loss.
model_pretrained (str): the path of pretrained model. Default to None.
enable_auxiliary_loss (bool): a bool values indic
a
tes whether adding auxiliary loss.
if true, auxiliary loss will be added after LearningToDownsample module, where the weight is 0.4. Default to False.
"""
...
...
@@ -105,15 +105,15 @@ class LearningToDownsample(nn.Layer):
def
__init__
(
self
,
dw_channels1
=
32
,
dw_channels2
=
48
,
out_channels
=
64
):
super
(
LearningToDownsample
,
self
).
__init__
()
self
.
conv_bn_relu
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
3
,
out_channels
=
dw_channels1
,
kernel_size
=
3
,
stride
=
2
)
self
.
dsconv_bn_relu1
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
dsconv_bn_relu1
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
dw_channels1
,
out_channels
=
dw_channels2
,
kernel_size
=
3
,
stride
=
2
,
padding
=
1
)
self
.
dsconv_bn_relu2
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
dsconv_bn_relu2
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
dw_channels2
,
out_channels
=
out_channels
,
kernel_size
=
3
,
...
...
@@ -208,13 +208,13 @@ class LinearBottleneck(nn.Layer):
expand_channels
=
in_channels
*
expansion
self
.
block
=
nn
.
Sequential
(
# pw
layer_libs
.
ConvB
nRelu
(
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
,
out_channels
=
expand_channels
,
kernel_size
=
1
,
bias_attr
=
False
),
# dw
layer_libs
.
ConvB
nRelu
(
layer_libs
.
ConvB
NReLU
(
in_channels
=
expand_channels
,
out_channels
=
expand_channels
,
kernel_size
=
3
,
...
...
@@ -239,7 +239,7 @@ class LinearBottleneck(nn.Layer):
class
FeatureFusionModule
(
nn
.
Layer
):
"""
Feature Fusion Module Impleme
m
tation.
Feature Fusion Module Impleme
n
tation.
This module fuses high-resolution feature and low-resolution feature.
...
...
@@ -253,7 +253,7 @@ class FeatureFusionModule(nn.Layer):
super
(
FeatureFusionModule
,
self
).
__init__
()
# There only depth-wise conv is used WITHOUT point-wise conv
self
.
dwconv
=
layer_libs
.
ConvB
nRelu
(
self
.
dwconv
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
low_in_channels
,
out_channels
=
out_channels
,
kernel_size
=
3
,
...
...
@@ -301,13 +301,13 @@ class Classifier(nn.Layer):
def
__init__
(
self
,
input_channels
,
num_classes
):
super
(
Classifier
,
self
).
__init__
()
self
.
dsconv1
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
dsconv1
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
input_channels
,
out_channels
=
input_channels
,
kernel_size
=
3
,
padding
=
1
)
self
.
dsconv2
=
layer_libs
.
DepthwiseConvB
nRelu
(
self
.
dsconv2
=
layer_libs
.
DepthwiseConvB
NReLU
(
in_channels
=
input_channels
,
out_channels
=
input_channels
,
kernel_size
=
3
,
...
...
dygraph/paddleseg/models/gcnet.py
浏览文件 @
9efa0289
...
...
@@ -27,15 +27,15 @@ class GCNet(nn.Layer):
"""
The GCNet implementation based on PaddlePaddle.
The or
ginal arti
le refers to
The or
iginal artic
le refers to
Cao, Yue, et al. "GCnet: Non-local networks meet squeeze-excitation networks and beyond."
(https://arxiv.org/pdf/1904.11492.pdf)
Args:
num_classes (int): the unique number of target classes.
backbone (Paddle.nn.Layer): backbone network, currently support Resnet50/101.
model_pretrained (str): the path of pretrained model. Defaul
l
t to None.
backbone_indices (tuple): two values in the tuple indicte the indices of output of backbone.
model_pretrained (str): the path of pretrained model. Default to None.
backbone_indices (tuple): two values in the tuple indic
a
te the indices of output of backbone.
the first index will be taken as a deep-supervision feature in auxiliary layer;
the second one will be taken as input of GlobalContextBlock. Usually backbone
consists of four downsampling stage, and return an output of each stage, so we
...
...
@@ -43,8 +43,8 @@ class GCNet(nn.Layer):
and the fourth stage (res5c) in backbone.
backbone_channels (tuple): the same length with "backbone_indices". It indicates the channels of corresponding index.
gc_channels (int): input channels to Global Context Block. Default to 512.
ratio (float): it indictes the ratio of attention channels and gc_channels. Default to 1/4.
enable_auxiliary_loss (bool): a bool values indictes whether adding auxiliary loss. Default to True.
ratio (float): it indic
a
tes the ratio of attention channels and gc_channels. Default to 1/4.
enable_auxiliary_loss (bool): a bool values indic
a
tes whether adding auxiliary loss. Default to True.
"""
def
__init__
(
self
,
...
...
@@ -63,7 +63,7 @@ class GCNet(nn.Layer):
self
.
backbone
=
backbone
in_channels
=
backbone_channels
[
1
]
self
.
conv_bn_relu1
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu1
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
,
out_channels
=
gc_channels
,
kernel_size
=
3
,
...
...
@@ -71,13 +71,13 @@ class GCNet(nn.Layer):
self
.
gc_block
=
GlobalContextBlock
(
in_channels
=
gc_channels
,
ratio
=
ratio
)
self
.
conv_bn_relu2
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu2
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
gc_channels
,
out_channels
=
gc_channels
,
kernel_size
=
3
,
padding
=
1
)
self
.
conv_bn_relu3
=
layer_libs
.
ConvB
nRelu
(
self
.
conv_bn_relu3
=
layer_libs
.
ConvB
NReLU
(
in_channels
=
in_channels
+
gc_channels
,
out_channels
=
gc_channels
,
kernel_size
=
3
,
...
...
@@ -154,7 +154,7 @@ class GlobalContextBlock(nn.Layer):
in_channels
=
in_channels
,
out_channels
=
1
,
kernel_size
=
1
)
self
.
softmax
=
nn
.
Softmax
(
axis
=
2
)
inter_channels
=
int
(
in_channels
*
ratio
)
self
.
channel_add_conv
=
nn
.
Sequential
(
nn
.
Conv2d
(
...
...
dygraph/paddleseg/models/ocrnet.py
浏览文件 @
9efa0289
...
...
@@ -18,7 +18,7 @@ import paddle.fluid as fluid
from
paddle.fluid.dygraph
import
Sequential
,
Conv2D
from
paddleseg.cvlibs
import
manager
from
paddleseg.models.common.layer_libs
import
ConvB
nRelu
from
paddleseg.models.common.layer_libs
import
ConvB
NReLU
from
paddleseg
import
utils
...
...
@@ -73,16 +73,16 @@ class ObjectAttentionBlock(fluid.dygraph.Layer):
self
.
key_channels
=
key_channels
self
.
f_pixel
=
Sequential
(
ConvB
nRelu
(
in_channels
,
key_channels
,
1
),
ConvB
nRelu
(
key_channels
,
key_channels
,
1
))
ConvB
NReLU
(
in_channels
,
key_channels
,
1
),
ConvB
NReLU
(
key_channels
,
key_channels
,
1
))
self
.
f_object
=
Sequential
(
ConvB
nRelu
(
in_channels
,
key_channels
,
1
),
ConvB
nRelu
(
key_channels
,
key_channels
,
1
))
ConvB
NReLU
(
in_channels
,
key_channels
,
1
),
ConvB
NReLU
(
key_channels
,
key_channels
,
1
))
self
.
f_down
=
ConvB
nRelu
(
in_channels
,
key_channels
,
1
)
self
.
f_down
=
ConvB
NReLU
(
in_channels
,
key_channels
,
1
)
self
.
f_up
=
ConvB
nRelu
(
key_channels
,
in_channels
,
1
)
self
.
f_up
=
ConvB
NReLU
(
key_channels
,
in_channels
,
1
)
def
forward
(
self
,
x
,
proxy
):
n
,
_
,
h
,
w
=
x
.
shape
...
...
@@ -135,12 +135,12 @@ class OCRNet(fluid.dygraph.Layer):
self
.
spatial_gather
=
SpatialGatherBlock
()
self
.
spatial_ocr
=
SpatialOCRModule
(
ocr_mid_channels
,
ocr_key_channels
,
ocr_mid_channels
)
self
.
conv3x3_ocr
=
ConvB
nRelu
(
self
.
conv3x3_ocr
=
ConvB
NReLU
(
in_channels
,
ocr_mid_channels
,
3
,
padding
=
1
)
self
.
cls_head
=
Conv2D
(
ocr_mid_channels
,
self
.
num_classes
,
1
)
self
.
aux_head
=
Sequential
(
ConvB
nRelu
(
in_channels
,
in_channels
,
3
,
padding
=
1
),
ConvB
NReLU
(
in_channels
,
in_channels
,
3
,
padding
=
1
),
Conv2D
(
in_channels
,
self
.
num_classes
,
1
))
self
.
init_weight
(
model_pretrained
)
...
...
dygraph/paddleseg/models/pspnet.py
浏览文件 @
9efa0289
...
...
@@ -26,7 +26,7 @@ class PSPNet(nn.Layer):
"""
The PSPNet implementation based on PaddlePaddle.
The or
ginal arti
le refers to
The or
iginal artic
le refers to
Zhao, Hengshuang, et al. "Pyramid scene parsing network."
Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
(https://openaccess.thecvf.com/content_cvpr_2017/papers/Zhao_Pyramid_Scene_Parsing_CVPR_2017_paper.pdf)
...
...
@@ -34,8 +34,8 @@ class PSPNet(nn.Layer):
Args:
num_classes (int): the unique number of target classes.
backbone (Paddle.nn.Layer): backbone network, currently support Resnet50/101.
model_pretrained (str): the path of pretrained model. Defaul
l
t to None.
backbone_indices (tuple): two values in the tuple indicte the indices of output of backbone.
model_pretrained (str): the path of pretrained model. Default to None.
backbone_indices (tuple): two values in the tuple indic
a
te the indices of output of backbone.
the first index will be taken as a deep-supervision feature in auxiliary layer;
the second one will be taken as input of Pyramid Pooling Module (PPModule).
Usually backbone consists of four downsampling stage, and return an output of
...
...
@@ -44,7 +44,7 @@ class PSPNet(nn.Layer):
backbone_channels (tuple): the same length with "backbone_indices". It indicates the channels of corresponding index.
pp_out_channels (int): output channels after Pyramid Pooling Module. Default to 1024.
bin_sizes (tuple): the out size of pooled feature maps. Default to (1,2,3,6).
enable_auxiliary_loss (bool): a bool values indictes whether adding auxiliary loss. Default to True.
enable_auxiliary_loss (bool): a bool values indic
a
tes whether adding auxiliary loss. Default to True.
"""
def
__init__
(
self
,
...
...
@@ -107,6 +107,7 @@ class PSPNet(nn.Layer):
def
init_weight
(
self
,
pretrained_model
=
None
):
"""
Initialize the parameters of model parts.
Args:
pretrained_model ([str], optional): the path of pretrained model. Defaults to None.
"""
...
...
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