[mlpack-git] master: Use the correct number of feature maps in the network description (thanks Ngap wei Tham for pointing it out). (1190791)
gitdub at big.cc.gt.atl.ga.us
gitdub at big.cc.gt.atl.ga.us
Sat Oct 17 09:19:14 EDT 2015
Repository : https://github.com/mlpack/mlpack
On branch : master
Link : https://github.com/mlpack/mlpack/compare/54f77d383ddb8546c6615d0c4aca29f18758ded2...1190791f07f3e1f2080f26a5c894f90df46f5316
>---------------------------------------------------------------
commit 1190791f07f3e1f2080f26a5c894f90df46f5316
Author: Marcus Edel <marcus.edel at fu-berlin.de>
Date: Sat Oct 17 15:19:07 2015 +0200
Use the correct number of feature maps in the network description (thanks Ngap wei Tham for pointing it out).
>---------------------------------------------------------------
1190791f07f3e1f2080f26a5c894f90df46f5316
src/mlpack/tests/convolutional_network_test.cpp | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/src/mlpack/tests/convolutional_network_test.cpp b/src/mlpack/tests/convolutional_network_test.cpp
index 5a2840c..bd20116 100644
--- a/src/mlpack/tests/convolutional_network_test.cpp
+++ b/src/mlpack/tests/convolutional_network_test.cpp
@@ -71,7 +71,7 @@ void BuildVanillaNetwork()
/*
* Construct a convolutional neural network with a 28x28x1 input layer,
- * 24x24x6 convolution layer, 12x12x6 pooling layer, 8x8x12 convolution layer
+ * 24x24x8 convolution layer, 12x12x8 pooling layer, 8x8x12 convolution layer
* and a 4x4x12 pooling layer which is fully connected with the output layer.
* The network structure looks like:
*
@@ -92,6 +92,9 @@ void BuildVanillaNetwork()
BaseLayer2D<PerformanceFunction> baseLayer0;
PoolingLayer<> poolingLayer0(2);
+
+
+
ConvLayer<RMSPROP> convLayer1(8, 12, 5, 5);
BiasLayer2D<RMSPROP, ZeroInitialization> biasLayer1(12);
BaseLayer2D<PerformanceFunction> baseLayer1;
@@ -162,9 +165,10 @@ void BuildVanillaDropoutNetwork()
/*
* Construct a convolutional neural network with a 28x28x1 input layer,
- * 24x24x6 convolution layer, 12x12x6 pooling layer, 8x8x12 convolution layer,
- * 8x8x12 Dropout Layer and a 4x4x12 pooling layer which is fully connected
- * with the output layer. The network structure looks like:
+ * 24x24x4 convolution layer, 24x24x4 dropout layer, 12x12x4 pooling layer,
+ * 8x8x8 convolution layer,8x8x8 Dropout Layer and a 4x4x12 pooling layer
+ * which is fully connected with the output layer. The network structure looks
+ * like:
*
* Input Convolution Dropout Pooling Convolution, Output
* Layer Layer Layer Layer Dropout, Layer
More information about the mlpack-git
mailing list