Merge pull request deeplearning4j#1492 from deeplearning4j/mw_bn_quirk

Fixed test error by setting nOut for bn.
vovietanh · May 2, 2016 · 36804c6 · 36804c6
2 parents bb723e8 + 14f3805
commit 36804c6
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 4 deletions.
diff --git a/deeplearning4j-core/src/test/java/org/deeplearning4j/nn/graph/TestCompGraphCNN.java b/deeplearning4j-core/src/test/java/org/deeplearning4j/nn/graph/TestCompGraphCNN.java
@@ -203,7 +203,6 @@ public void testCNNComputationGraphKernelTooLarge() {
     }
 
     @Test
-    @Ignore
     public void testCNNComputationGraphSingleOutFeatureMap() {
         int imageWidth = 23;
         int imageHeight = 23;
@@ -234,7 +233,7 @@ public void testCNNComputationGraphSingleOutFeatureMap() {
                         .build(), "input")
                 .addLayer("pool1", new SubsamplingLayer.Builder()
                         .poolingType(SubsamplingLayer.PoolingType.MAX)
-                        .kernelSize(imageHeight - kernelHeight + 1, 1)
+                        .kernelSize(imageHeight - kernelHeight, 1)
                         .stride(1, 1)
                         .build(), "conv1")
                 .addLayer("output", new OutputLayer.Builder()

diff --git a/deeplearning4j-core/src/test/java/org/deeplearning4j/nn/multilayer/MultiLayerTest.java b/deeplearning4j-core/src/test/java/org/deeplearning4j/nn/multilayer/MultiLayerTest.java
@@ -139,7 +139,7 @@ public void testBatchNorm() {
                 .list()
                 .layer(0, new DenseLayer.Builder().nIn(4).nOut(3).weightInit(WeightInit.XAVIER).activation("tanh").build())
                 .layer(1, new DenseLayer.Builder().nIn(3).nOut(2).weightInit(WeightInit.XAVIER).activation("tanh").build())
-                .layer(2, new BatchNormalization.Builder().build())
+                .layer(2, new BatchNormalization.Builder().nOut(2).build())
                 .layer(3, new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT)
                         .weightInit(WeightInit.XAVIER)
                         .activation("softmax")
@@ -650,7 +650,7 @@ public void testDataSetScoreCNN(){
                 .learningRate(1.0)
                 .seed(12345L)
                 .list()
-                .layer(0, new ConvolutionLayer.Builder(2,2).nOut(3).build())
+                .layer(0, new ConvolutionLayer.Builder(2,2).nOut(1).build())
                 .layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).activation("softmax").nOut(2).build())
                 .cnnInputSize(3,3,2)
                 .pretrain(false).backprop(true).build();