Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Sign in
Toggle navigation
C
CNNArch2Caffe2
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Iterations
Merge Requests
0
Merge Requests
0
Requirements
Requirements
List
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Test Cases
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Operations
Operations
Incidents
Environments
Packages & Registries
Packages & Registries
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issue
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
monticore
EmbeddedMontiArc
generators
CNNArch2Caffe2
Commits
708625a4
Commit
708625a4
authored
Jan 31, 2019
by
Carlos Alfredo Yeverino Rodriguez
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Updated layer templates for Flatten, FullyConnected, GlobalPooling and Lrn
parent
26320c32
Changes
7
Hide whitespace changes
Inline
Side-by-side
Showing
7 changed files
with
32 additions
and
166 deletions
+32
-166
src/main/resources/templates/caffe2/elements/Flatten.ftl
src/main/resources/templates/caffe2/elements/Flatten.ftl
+1
-2
src/main/resources/templates/caffe2/elements/FullyConnected.ftl
...in/resources/templates/caffe2/elements/FullyConnected.ftl
+1
-4
src/main/resources/templates/caffe2/elements/GlobalPooling.ftl
...ain/resources/templates/caffe2/elements/GlobalPooling.ftl
+6
-5
src/main/resources/templates/caffe2/elements/Lrn.ftl
src/main/resources/templates/caffe2/elements/Lrn.ftl
+7
-6
src/test/resources/target_code/CNNCreator_Alexnet.py
src/test/resources/target_code/CNNCreator_Alexnet.py
+11
-48
src/test/resources/target_code/CNNCreator_CifarClassifierNetwork.py
...esources/target_code/CNNCreator_CifarClassifierNetwork.py
+1
-97
src/test/resources/target_code/CNNCreator_LeNet.py
src/test/resources/target_code/CNNCreator_LeNet.py
+5
-4
No files found.
src/main/resources/templates/caffe2/elements/Flatten.ftl
View file @
708625a4
${element.name} = mx.symbol.Flatten(data=${element.inputs[0]},
name="${element.name}")
\ No newline at end of file
${element.name} = model.net.Flatten(${element.inputs[0]}, "${element.name}")
\ No newline at end of file
src/main/resources/templates/caffe2/elements/FullyConnected.ftl
View file @
708625a4
...
...
@@ -4,13 +4,10 @@
<#assign inputChannels = element.element.inputTypes[0].channels?c>
<#assign inputHeight = element.element.inputTypes[0].height>
<#assign inputWidth = element.element.inputTypes[0].width>
<#if flatten>
<#-- TODO: check how to adapt CNNArchLang flatten #${element.name} = mx.symbol.flatten(data=${input}) -->
</#if>
<#--flatten is not needed since the fc layer applies it automatically-->
<#if inputLayerType?matches("FullyConnected") || (inputHeight == 1 && inputWidth == 1)>
${element.name} = brew.fc(model, ${input}, '${element.name}', dim_in=${inputChannels}, dim_out=${element.units?c})
<#else>
${element.name} = brew.fc(model, ${input}, '${element.name}', dim_in=${inputChannels} * ${inputHeight} * ${inputWidth}, dim_out=${element.units?c})
</#if>
<#-- TODO: check how to adapt CNNArchLang argument no_bias=${element.noBias?string("True","False")} -->
<#include "OutputShape.ftl">
\ No newline at end of file
src/main/resources/templates/caffe2/elements/GlobalPooling.ftl
View file @
708625a4
${element.name} = mx.symbol.Pooling(data=${element.inputs[0]},
global_pool=True,
kernel=(1,1),
pool_type="${element.poolType}",
name="${element.name}")
<#assign input = element.inputs[0]>
<#if element.poolType == "max">
${element.name} = brew.max_pool(model, ${input}, '${element.name}', global_pooling=True)
<#elseif element.poolType == "avg">
${element.name} = brew.average_pool(model, ${input}, '${element.name}', global_pooling=True)
</#if>
<#include "OutputShape.ftl">
\ No newline at end of file
src/main/resources/templates/caffe2/elements/Lrn.ftl
View file @
708625a4
${element.name} = mx.symbol.LRN(data=${element.inputs[0]},
alpha=${element.alpha?c},
beta=${element.beta?c},
knorm=${element.knorm?c},
nsize=${element.nsize?c},
name="${element.name}")
<#assign input = element.inputs[0]>
<#if !element.knorm?string?contains(".")>
<#assign bias = element.knorm?string["0.0"]>
<#else>
<#assign bias = element.knorm?c>
</#if>
${element.name} = brew.lrn(model, ${input}, '${element.name}', size=${element.nsize?c}, alpha=${element.alpha?c}, beta=${element.beta?c}, bias=${bias})
src/test/resources/target_code/CNNCreator_Alexnet.py
View file @
708625a4
...
...
@@ -64,80 +64,43 @@ class CNNCreator_Alexnet:
data
=
data
# data, output shape: {[3,224,224]}
conv1_
=
brew
.
conv
(
model
,
data
,
'conv1_'
,
dim_in
=
3
,
dim_out
=
96
,
kernel
=
11
,
stride
=
4
)
conv1_
=
brew
.
conv
(
model
,
data
,
'conv1_'
,
dim_in
=
3
,
dim_out
=
96
,
kernel
=
11
,
stride
=
4
)
# conv1_, output shape: {[96,55,55]}
lrn1_
=
mx
.
symbol
.
LRN
(
data
=
conv1_
,
alpha
=
0.0001
,
beta
=
0.75
,
knorm
=
2
,
nsize
=
5
,
name
=
"lrn1_"
)
lrn1_
=
brew
.
lrn
(
model
,
conv1_
,
'lrn1_'
,
size
=
5
,
alpha
=
0.0001
,
beta
=
0.75
,
bias
=
2.0
)
pool1_
=
brew
.
max_pool
(
model
,
lrn1_
,
'pool1_'
,
kernel
=
3
,
stride
=
2
)
# pool1_, output shape: {[96,27,27]}
relu1_
=
brew
.
relu
(
model
,
pool1_
,
pool1_
)
split1_
=
mx
.
symbol
.
split
(
data
=
relu1_
,
num_outputs
=
2
,
axis
=
1
,
name
=
"split1_"
)
# split1_, output shape: {[48,27,27][48,27,27]}
get2_1_
=
split1_
[
0
]
conv2_1_
=
brew
.
conv
(
model
,
get2_1_
,
'conv2_1_'
,
dim_in
=
48
,
dim_out
=
128
,
kernel
=
5
,
stride
=
1
)
conv2_1_
=
brew
.
conv
(
model
,
get2_1_
,
'conv2_1_'
,
dim_in
=
48
,
dim_out
=
128
,
kernel
=
5
,
stride
=
1
,
pad
=
1
)
# conv2_1_, output shape: {[128,27,27]}
lrn2_1_
=
mx
.
symbol
.
LRN
(
data
=
conv2_1_
,
alpha
=
0.0001
,
beta
=
0.75
,
knorm
=
2
,
nsize
=
5
,
name
=
"lrn2_1_"
)
lrn2_1_
=
brew
.
lrn
(
model
,
conv2_1_
,
'lrn2_1_'
,
size
=
5
,
alpha
=
0.0001
,
beta
=
0.75
,
bias
=
2.0
)
pool2_1_
=
brew
.
max_pool
(
model
,
lrn2_1_
,
'pool2_1_'
,
kernel
=
3
,
stride
=
2
)
# pool2_1_, output shape: {[128,13,13]}
relu2_1_
=
brew
.
relu
(
model
,
pool2_1_
,
pool2_1_
)
get2_2_
=
split1_
[
1
]
conv2_2_
=
brew
.
conv
(
model
,
get2_2_
,
'conv2_2_'
,
dim_in
=
48
,
dim_out
=
128
,
kernel
=
5
,
stride
=
1
)
conv2_2_
=
brew
.
conv
(
model
,
get2_2_
,
'conv2_2_'
,
dim_in
=
48
,
dim_out
=
128
,
kernel
=
5
,
stride
=
1
,
pad
=
1
)
# conv2_2_, output shape: {[128,27,27]}
lrn2_2_
=
mx
.
symbol
.
LRN
(
data
=
conv2_2_
,
alpha
=
0.0001
,
beta
=
0.75
,
knorm
=
2
,
nsize
=
5
,
name
=
"lrn2_2_"
)
lrn2_2_
=
brew
.
lrn
(
model
,
conv2_2_
,
'lrn2_2_'
,
size
=
5
,
alpha
=
0.0001
,
beta
=
0.75
,
bias
=
2.0
)
pool2_2_
=
brew
.
max_pool
(
model
,
lrn2_2_
,
'pool2_2_'
,
kernel
=
3
,
stride
=
2
)
# pool2_2_, output shape: {[128,13,13]}
relu2_2_
=
brew
.
relu
(
model
,
pool2_2_
,
pool2_2_
)
concatenate3_
=
mx
.
symbol
.
concat
(
relu2_1_
,
relu2_2_
,
dim
=
1
,
name
=
"concatenate3_"
)
# concatenate3_, output shape: {[256,13,13]}
conv3_
=
brew
.
conv
(
model
,
concatenate3_
,
'conv3_'
,
dim_in
=
256
,
dim_out
=
384
,
kernel
=
3
,
stride
=
1
)
conv3_
=
brew
.
conv
(
model
,
concatenate3_
,
'conv3_'
,
dim_in
=
256
,
dim_out
=
384
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv3_, output shape: {[384,13,13]}
relu3_
=
brew
.
relu
(
model
,
conv3_
,
conv3_
)
split3_
=
mx
.
symbol
.
split
(
data
=
relu3_
,
num_outputs
=
2
,
axis
=
1
,
name
=
"split3_"
)
# split3_, output shape: {[192,13,13][192,13,13]}
get4_1_
=
split3_
[
0
]
conv4_1_
=
brew
.
conv
(
model
,
get4_1_
,
'conv4_1_'
,
dim_in
=
192
,
dim_out
=
192
,
kernel
=
3
,
stride
=
1
)
conv4_1_
=
brew
.
conv
(
model
,
get4_1_
,
'conv4_1_'
,
dim_in
=
192
,
dim_out
=
192
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv4_1_, output shape: {[192,13,13]}
relu4_1_
=
brew
.
relu
(
model
,
conv4_1_
,
conv4_1_
)
conv5_1_
=
brew
.
conv
(
model
,
relu4_1_
,
'conv5_1_'
,
dim_in
=
192
,
dim_out
=
128
,
kernel
=
3
,
stride
=
1
)
conv5_1_
=
brew
.
conv
(
model
,
relu4_1_
,
'conv5_1_'
,
dim_in
=
192
,
dim_out
=
128
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv5_1_, output shape: {[128,13,13]}
pool5_1_
=
brew
.
max_pool
(
model
,
conv5_1_
,
'pool5_1_'
,
kernel
=
3
,
stride
=
2
)
# pool5_1_, output shape: {[128,6,6]}
relu5_1_
=
brew
.
relu
(
model
,
pool5_1_
,
pool5_1_
)
get4_2_
=
split3_
[
1
]
conv4_2_
=
brew
.
conv
(
model
,
get4_2_
,
'conv4_2_'
,
dim_in
=
192
,
dim_out
=
192
,
kernel
=
3
,
stride
=
1
)
conv4_2_
=
brew
.
conv
(
model
,
get4_2_
,
'conv4_2_'
,
dim_in
=
192
,
dim_out
=
192
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv4_2_, output shape: {[192,13,13]}
relu4_2_
=
brew
.
relu
(
model
,
conv4_2_
,
conv4_2_
)
conv5_2_
=
brew
.
conv
(
model
,
relu4_2_
,
'conv5_2_'
,
dim_in
=
192
,
dim_out
=
128
,
kernel
=
3
,
stride
=
1
)
conv5_2_
=
brew
.
conv
(
model
,
relu4_2_
,
'conv5_2_'
,
dim_in
=
192
,
dim_out
=
128
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv5_2_, output shape: {[128,13,13]}
pool5_2_
=
brew
.
max_pool
(
model
,
conv5_2_
,
'pool5_2_'
,
kernel
=
3
,
stride
=
2
)
# pool5_2_, output shape: {[128,6,6]}
relu5_2_
=
brew
.
relu
(
model
,
pool5_2_
,
pool5_2_
)
concatenate6_
=
mx
.
symbol
.
concat
(
relu5_1_
,
relu5_2_
,
dim
=
1
,
name
=
"concatenate6_"
)
# concatenate6_, output shape: {[256,6,6]}
fc6_
=
brew
.
fc
(
model
,
concatenate6_
,
'fc6_'
,
dim_in
=
256
*
6
*
6
,
dim_out
=
4096
)
# fc6_, output shape: {[4096,1,1]}
relu6_
=
brew
.
relu
(
model
,
fc6_
,
fc6_
)
...
...
src/test/resources/target_code/CNNCreator_CifarClassifierNetwork.py
View file @
708625a4
...
...
@@ -66,169 +66,73 @@ class CNNCreator_CifarClassifierNetwork:
# data, output shape: {[3,32,32]}
conv2_1_
=
brew
.
conv
(
model
,
data
,
'conv2_1_'
,
dim_in
=
3
,
dim_out
=
8
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv2_1_, output shape: {[8,32,32]}
batchnorm2_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv2_1_
,
fix_gamma
=
True
,
name
=
"batchnorm2_1_"
)
relu2_1_
=
brew
.
relu
(
model
,
batchnorm2_1_
,
batchnorm2_1_
)
conv3_1_
=
brew
.
conv
(
model
,
relu2_1_
,
'conv3_1_'
,
dim_in
=
8
,
dim_out
=
8
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv3_1_, output shape: {[8,32,32]}
batchnorm3_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv3_1_
,
fix_gamma
=
True
,
name
=
"batchnorm3_1_"
)
conv2_2_
=
brew
.
conv
(
model
,
data
,
'conv2_2_'
,
dim_in
=
3
,
dim_out
=
8
,
kernel
=
1
,
stride
=
1
,
pad
=
1
)
# conv2_2_, output shape: {[8,32,32]}
batchnorm2_2_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv2_2_
,
fix_gamma
=
True
,
name
=
"batchnorm2_2_"
)
add4_
=
batchnorm3_1_
+
batchnorm2_2_
# add4_, output shape: {[8,32,32]}
relu4_
=
brew
.
relu
(
model
,
add4_
,
add4_
)
conv5_1_
=
brew
.
conv
(
model
,
relu4_
,
'conv5_1_'
,
dim_in
=
8
,
dim_out
=
16
,
kernel
=
3
,
stride
=
2
,
pad
=
1
)
# conv5_1_, output shape: {[16,16,16]}
batchnorm5_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv5_1_
,
fix_gamma
=
True
,
name
=
"batchnorm5_1_"
)
relu5_1_
=
brew
.
relu
(
model
,
batchnorm5_1_
,
batchnorm5_1_
)
conv6_1_
=
brew
.
conv
(
model
,
relu5_1_
,
'conv6_1_'
,
dim_in
=
16
,
dim_out
=
16
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv6_1_, output shape: {[16,16,16]}
batchnorm6_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv6_1_
,
fix_gamma
=
True
,
name
=
"batchnorm6_1_"
)
conv5_2_
=
brew
.
conv
(
model
,
relu4_
,
'conv5_2_'
,
dim_in
=
8
,
dim_out
=
16
,
kernel
=
1
,
stride
=
2
,
pad
=
1
)
# conv5_2_, output shape: {[16,16,16]}
batchnorm5_2_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv5_2_
,
fix_gamma
=
True
,
name
=
"batchnorm5_2_"
)
add7_
=
batchnorm6_1_
+
batchnorm5_2_
# add7_, output shape: {[16,16,16]}
relu7_
=
brew
.
relu
(
model
,
add7_
,
add7_
)
conv8_1_
=
brew
.
conv
(
model
,
relu7_
,
'conv8_1_'
,
dim_in
=
16
,
dim_out
=
16
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv8_1_, output shape: {[16,16,16]}
batchnorm8_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv8_1_
,
fix_gamma
=
True
,
name
=
"batchnorm8_1_"
)
relu8_1_
=
brew
.
relu
(
model
,
batchnorm8_1_
,
batchnorm8_1_
)
conv9_1_
=
brew
.
conv
(
model
,
relu8_1_
,
'conv9_1_'
,
dim_in
=
16
,
dim_out
=
16
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv9_1_, output shape: {[16,16,16]}
batchnorm9_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv9_1_
,
fix_gamma
=
True
,
name
=
"batchnorm9_1_"
)
add10_
=
batchnorm9_1_
+
relu7_
# add10_, output shape: {[16,16,16]}
relu10_
=
brew
.
relu
(
model
,
add10_
,
add10_
)
conv11_1_
=
brew
.
conv
(
model
,
relu10_
,
'conv11_1_'
,
dim_in
=
16
,
dim_out
=
16
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv11_1_, output shape: {[16,16,16]}
batchnorm11_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv11_1_
,
fix_gamma
=
True
,
name
=
"batchnorm11_1_"
)
relu11_1_
=
brew
.
relu
(
model
,
batchnorm11_1_
,
batchnorm11_1_
)
conv12_1_
=
brew
.
conv
(
model
,
relu11_1_
,
'conv12_1_'
,
dim_in
=
16
,
dim_out
=
16
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv12_1_, output shape: {[16,16,16]}
batchnorm12_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv12_1_
,
fix_gamma
=
True
,
name
=
"batchnorm12_1_"
)
add13_
=
batchnorm12_1_
+
relu10_
# add13_, output shape: {[16,16,16]}
relu13_
=
brew
.
relu
(
model
,
add13_
,
add13_
)
conv14_1_
=
brew
.
conv
(
model
,
relu13_
,
'conv14_1_'
,
dim_in
=
16
,
dim_out
=
32
,
kernel
=
3
,
stride
=
2
,
pad
=
1
)
# conv14_1_, output shape: {[32,8,8]}
batchnorm14_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv14_1_
,
fix_gamma
=
True
,
name
=
"batchnorm14_1_"
)
relu14_1_
=
brew
.
relu
(
model
,
batchnorm14_1_
,
batchnorm14_1_
)
conv15_1_
=
brew
.
conv
(
model
,
relu14_1_
,
'conv15_1_'
,
dim_in
=
32
,
dim_out
=
32
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv15_1_, output shape: {[32,8,8]}
batchnorm15_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv15_1_
,
fix_gamma
=
True
,
name
=
"batchnorm15_1_"
)
conv14_2_
=
brew
.
conv
(
model
,
relu13_
,
'conv14_2_'
,
dim_in
=
16
,
dim_out
=
32
,
kernel
=
1
,
stride
=
2
,
pad
=
1
)
# conv14_2_, output shape: {[32,8,8]}
batchnorm14_2_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv14_2_
,
fix_gamma
=
True
,
name
=
"batchnorm14_2_"
)
add16_
=
batchnorm15_1_
+
batchnorm14_2_
# add16_, output shape: {[32,8,8]}
relu16_
=
brew
.
relu
(
model
,
add16_
,
add16_
)
conv17_1_
=
brew
.
conv
(
model
,
relu16_
,
'conv17_1_'
,
dim_in
=
32
,
dim_out
=
32
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv17_1_, output shape: {[32,8,8]}
batchnorm17_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv17_1_
,
fix_gamma
=
True
,
name
=
"batchnorm17_1_"
)
relu17_1_
=
brew
.
relu
(
model
,
batchnorm17_1_
,
batchnorm17_1_
)
conv18_1_
=
brew
.
conv
(
model
,
relu17_1_
,
'conv18_1_'
,
dim_in
=
32
,
dim_out
=
32
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv18_1_, output shape: {[32,8,8]}
batchnorm18_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv18_1_
,
fix_gamma
=
True
,
name
=
"batchnorm18_1_"
)
add19_
=
batchnorm18_1_
+
relu16_
# add19_, output shape: {[32,8,8]}
relu19_
=
brew
.
relu
(
model
,
add19_
,
add19_
)
conv20_1_
=
brew
.
conv
(
model
,
relu19_
,
'conv20_1_'
,
dim_in
=
32
,
dim_out
=
32
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv20_1_, output shape: {[32,8,8]}
batchnorm20_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv20_1_
,
fix_gamma
=
True
,
name
=
"batchnorm20_1_"
)
relu20_1_
=
brew
.
relu
(
model
,
batchnorm20_1_
,
batchnorm20_1_
)
conv21_1_
=
brew
.
conv
(
model
,
relu20_1_
,
'conv21_1_'
,
dim_in
=
32
,
dim_out
=
32
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv21_1_, output shape: {[32,8,8]}
batchnorm21_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv21_1_
,
fix_gamma
=
True
,
name
=
"batchnorm21_1_"
)
add22_
=
batchnorm21_1_
+
relu19_
# add22_, output shape: {[32,8,8]}
relu22_
=
brew
.
relu
(
model
,
add22_
,
add22_
)
conv23_1_
=
brew
.
conv
(
model
,
relu22_
,
'conv23_1_'
,
dim_in
=
32
,
dim_out
=
64
,
kernel
=
3
,
stride
=
2
,
pad
=
1
)
# conv23_1_, output shape: {[64,4,4]}
batchnorm23_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv23_1_
,
fix_gamma
=
True
,
name
=
"batchnorm23_1_"
)
relu23_1_
=
brew
.
relu
(
model
,
batchnorm23_1_
,
batchnorm23_1_
)
conv24_1_
=
brew
.
conv
(
model
,
relu23_1_
,
'conv24_1_'
,
dim_in
=
64
,
dim_out
=
64
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv24_1_, output shape: {[64,4,4]}
batchnorm24_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv24_1_
,
fix_gamma
=
True
,
name
=
"batchnorm24_1_"
)
conv23_2_
=
brew
.
conv
(
model
,
relu22_
,
'conv23_2_'
,
dim_in
=
32
,
dim_out
=
64
,
kernel
=
1
,
stride
=
2
,
pad
=
1
)
# conv23_2_, output shape: {[64,4,4]}
batchnorm23_2_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv23_2_
,
fix_gamma
=
True
,
name
=
"batchnorm23_2_"
)
add25_
=
batchnorm24_1_
+
batchnorm23_2_
# add25_, output shape: {[64,4,4]}
relu25_
=
brew
.
relu
(
model
,
add25_
,
add25_
)
conv26_1_
=
brew
.
conv
(
model
,
relu25_
,
'conv26_1_'
,
dim_in
=
64
,
dim_out
=
64
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv26_1_, output shape: {[64,4,4]}
batchnorm26_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv26_1_
,
fix_gamma
=
True
,
name
=
"batchnorm26_1_"
)
relu26_1_
=
brew
.
relu
(
model
,
batchnorm26_1_
,
batchnorm26_1_
)
conv27_1_
=
brew
.
conv
(
model
,
relu26_1_
,
'conv27_1_'
,
dim_in
=
64
,
dim_out
=
64
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv27_1_, output shape: {[64,4,4]}
batchnorm27_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv27_1_
,
fix_gamma
=
True
,
name
=
"batchnorm27_1_"
)
add28_
=
batchnorm27_1_
+
relu25_
# add28_, output shape: {[64,4,4]}
relu28_
=
brew
.
relu
(
model
,
add28_
,
add28_
)
conv29_1_
=
brew
.
conv
(
model
,
relu28_
,
'conv29_1_'
,
dim_in
=
64
,
dim_out
=
64
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv29_1_, output shape: {[64,4,4]}
batchnorm29_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv29_1_
,
fix_gamma
=
True
,
name
=
"batchnorm29_1_"
)
relu29_1_
=
brew
.
relu
(
model
,
batchnorm29_1_
,
batchnorm29_1_
)
conv30_1_
=
brew
.
conv
(
model
,
relu29_1_
,
'conv30_1_'
,
dim_in
=
64
,
dim_out
=
64
,
kernel
=
3
,
stride
=
1
,
pad
=
1
)
# conv30_1_, output shape: {[64,4,4]}
batchnorm30_1_
=
mx
.
symbol
.
BatchNorm
(
data
=
conv30_1_
,
fix_gamma
=
True
,
name
=
"batchnorm30_1_"
)
add31_
=
batchnorm30_1_
+
relu28_
# add31_, output shape: {[64,4,4]}
relu31_
=
brew
.
relu
(
model
,
add31_
,
add31_
)
globalpooling31_
=
mx
.
symbol
.
Pooling
(
data
=
relu31_
,
global_pool
=
True
,
kernel
=
(
1
,
1
),
pool_type
=
"avg"
,
name
=
"globalpooling31_"
)
globalpooling31_
=
brew
.
average_pool
(
model
,
relu31_
,
'globalpooling31_'
,
global_pooling
=
True
)
# globalpooling31_, output shape: {[64,1,1]}
fc31_
=
brew
.
fc
(
model
,
globalpooling31_
,
'fc31_'
,
dim_in
=
64
,
dim_out
=
128
)
# fc31_, output shape: {[128,1,1]}
...
...
src/test/resources/target_code/CNNCreator_LeNet.py
View file @
708625a4
...
...
@@ -7,6 +7,7 @@ import logging
import
os
import
sys
import
lmdb
class
CNNCreator_LeNet
:
module
=
None
...
...
@@ -58,7 +59,7 @@ class CNNCreator_LeNet:
return
data
,
label
,
dataset_size
def
create_model
(
self
,
model
,
data
,
device_opts
):
def
create_model
(
self
,
model
,
data
,
device_opts
,
is_test
):
with
core
.
DeviceScope
(
device_opts
):
image
=
data
...
...
@@ -135,7 +136,7 @@ class CNNCreator_LeNet:
# == Training model ==
train_model
=
model_helper
.
ModelHelper
(
name
=
"train_net"
,
arg_scope
=
arg_scope
)
data
,
label
,
train_dataset_size
=
self
.
add_input
(
train_model
,
batch_size
=
batch_size
,
db
=
os
.
path
.
join
(
self
.
_data_dir_
,
'train_lmdb'
),
db_type
=
'lmdb'
,
device_opts
=
device_opts
)
predictions
=
self
.
create_model
(
train_model
,
data
,
device_opts
=
device_opts
)
predictions
=
self
.
create_model
(
train_model
,
data
,
device_opts
=
device_opts
,
is_test
=
False
)
self
.
add_training_operators
(
train_model
,
predictions
,
label
,
device_opts
,
opt_type
,
base_learning_rate
,
policy
,
stepsize
,
epsilon
,
beta1
,
beta2
,
gamma
,
momentum
)
self
.
add_accuracy
(
train_model
,
predictions
,
label
,
device_opts
,
eval_metric
)
with
core
.
DeviceScope
(
device_opts
):
...
...
@@ -158,7 +159,7 @@ class CNNCreator_LeNet:
# == Testing model. ==
test_model
=
model_helper
.
ModelHelper
(
name
=
"test_net"
,
arg_scope
=
arg_scope
,
init_params
=
False
)
data
,
label
,
test_dataset_size
=
self
.
add_input
(
test_model
,
batch_size
=
batch_size
,
db
=
os
.
path
.
join
(
self
.
_data_dir_
,
'test_lmdb'
),
db_type
=
'lmdb'
,
device_opts
=
device_opts
)
predictions
=
self
.
create_model
(
test_model
,
data
,
device_opts
=
device_opts
)
predictions
=
self
.
create_model
(
test_model
,
data
,
device_opts
=
device_opts
,
is_test
=
True
)
self
.
add_accuracy
(
test_model
,
predictions
,
label
,
device_opts
,
eval_metric
)
workspace
.
RunNetOnce
(
test_model
.
param_init_net
)
workspace
.
CreateNet
(
test_model
.
net
,
overwrite
=
True
)
...
...
@@ -176,7 +177,7 @@ class CNNCreator_LeNet:
# == Deployment model. ==
# We simply need the main AddModel part.
deploy_model
=
model_helper
.
ModelHelper
(
name
=
"deploy_net"
,
arg_scope
=
arg_scope
,
init_params
=
False
)
self
.
create_model
(
deploy_model
,
"data"
,
device_opts
)
self
.
create_model
(
deploy_model
,
"data"
,
device_opts
,
is_test
=
True
)
print
(
"Saving deploy model"
)
self
.
save_net
(
self
.
_init_net_
,
self
.
_predict_net_
,
deploy_model
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment