Skip to content
GitLab
Menu
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
Main Repositories
otb
Commits
c277879e
Commit
c277879e
authored
Sep 08, 2017
by
Cédric Traizet
Browse files
Neuron type changed to Logistic
parent
f3436d08
Changes
3
Hide whitespace changes
Inline
Side-by-side
include/AutoencoderModel.h
View file @
c277879e
...
...
@@ -36,6 +36,7 @@ public:
typedef
typename
Superclass
::
ConfidenceListSampleType
ConfidenceListSampleType
;
/// Neural network related typedefs
//typedef shark::Autoencoder<NeuronType,shark::LinearNeuron> OutAutoencoderType;
typedef
shark
::
Autoencoder
<
NeuronType
,
shark
::
LinearNeuron
>
OutAutoencoderType
;
typedef
shark
::
Autoencoder
<
NeuronType
,
NeuronType
>
AutoencoderType
;
typedef
shark
::
FFNet
<
NeuronType
,
shark
::
LinearNeuron
>
NetworkType
;
...
...
include/DimensionalityReductionModelFactory.txx
View file @
c277879e
...
...
@@ -46,7 +46,7 @@ using TiedAutoencoderModelFactory = AutoencoderModelFactoryBase<TInputValue, TTa
*/
template <class TInputValue, class TTargetValue>
using AutoencoderModelFactory = AutoencoderModelFactoryBase<TInputValue, TTargetValue, shark::
Tanh
Neuron> ;
using AutoencoderModelFactory = AutoencoderModelFactoryBase<TInputValue, TTargetValue, shark::
Logistic
Neuron> ;
template <class TInputValue, class TTargetValue>
...
...
include/cbLearningApplicationBaseDR.h
View file @
c277879e
...
...
@@ -103,7 +103,7 @@ public:
#ifdef OTB_USE_SHARK
// typedef shark::Autoencoder< shark::TanhNeuron, shark::LinearNeuron> AutoencoderType;
typedef
shark
::
Tanh
Neuron
NeuronType
;
typedef
shark
::
Logistic
Neuron
NeuronType
;
typedef
otb
::
AutoencoderModel
<
InputValueType
,
NeuronType
>
AutoencoderModelType
;
/*
// typedef shark::TiedAutoencoder< shark::TanhNeuron, shark::LinearNeuron> TiedAutoencoderType;
...
...
Write
Preview
Supports
Markdown
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