Integrate mahilleb/ExpDnnWriteCommand into master

nikoma · May 14, 2016 · 658046d · 658046d
2 parents b09ba68 + 6c2d01b
commit 658046d
Show file tree

Hide file tree

Showing 10 changed files with 2,567 additions and 5 deletions.
diff --git a/Source/Readers/ExperimentalHTKMLFReader/ConfigHelper.cpp b/Source/Readers/ExperimentalHTKMLFReader/ConfigHelper.cpp
@@ -198,8 +198,16 @@ size_t ConfigHelper::GetRandomizationWindow()
 
 wstring ConfigHelper::GetRandomizer()
 {
-    // get the read method, defaults to "blockRandomize"
-    wstring randomizer(m_config(L"readMethod", L"blockRandomize"));
+    // Check (on the action) if we're writing (inputs only) or training/evaluating (inputs and outputs)
+    bool isActionWrite = wstring(m_config(L"action", L"")) == L"write";
+
+    // Get the read method, defaults to "blockRandomize".
+    wstring randomizer = m_config(L"readMethod", L"blockRandomize");
+
+    if (isActionWrite && randomizer != L"none")
+    {
+        InvalidArgument("'readMethod' must be 'none' for write action.");
+    }
 
     if (randomizer == L"blockRandomize" && GetRandomizationWindow() == randomizeNone)
     {

diff --git a/Source/Readers/ExperimentalHTKMLFReader/HTKMLFReader.cpp b/Source/Readers/ExperimentalHTKMLFReader/HTKMLFReader.cpp
@@ -27,9 +27,9 @@ std::vector<IDataDeserializerPtr> CreateDeserializers(const ConfigParameters& re
     ConfigHelper config(readerConfig);
 
     config.GetDataNamesFromConfig(featureNames, labelNames, notused, notused);
-    if (featureNames.size() < 1 || labelNames.size() < 1)
+    if (featureNames.size() < 1)
     {
-        InvalidArgument("Network needs at least 1 feature and 1 label specified.");
+        InvalidArgument("Network needs at least 1 feature specified.");
     }
 
     CorpusDescriptorPtr corpus = std::make_shared<CorpusDescriptor>();

diff --git a/Source/Readers/HTKMLFReader/HTKMLFReader.cpp b/Source/Readers/HTKMLFReader/HTKMLFReader.cpp
@@ -599,7 +599,7 @@ void HTKMLFReader<ElemType>::PrepareForTrainingOrTesting(const ConfigRecordType&
 }
 
 // Load all input and output data.
-// Note that the terms features imply be real-valued quanities and
+// Note that the terms features imply be real-valued quantities and
 // labels imply categorical quantities, irrespective of whether they
 // are inputs or targets for the network
 // TODO: lots of code dup with the other Prepare function

diff --git a/Tests/EndToEndTests/Speech/DNN/WriteCommand/run-test b/Tests/EndToEndTests/Speech/DNN/WriteCommand/run-test
@@ -31,6 +31,7 @@ if [ ! -e $OUTPUT_CURRENT ]; then
   exit 3
 fi
 
+# Check for each line that the space-separated floats match the baseline with a tolerance of 0.03 %
 OUTPUT_DIFF=$TEST_RUN_DIR/Output.ScaledLogLikelihood.diff
 awk '{FS=" "} function abs(x) {return ((x < 0.0) ? -x : x)} NR==FNR {for (i=1; i<=NF; i++) a[FNR][i]=$i;} NR!=FNR {for (i=1; i<=NF; i++) {if ((abs($i - a[FNR][i])/abs($i)) > 0.03) printf("Line %d, Field %d: Baseline = %f, Current = %f\n", NR, i, a[FNR][i], $i);}}' $OUTPUT_BASELINE $OUTPUT_CURRENT > $OUTPUT_DIFF || exit $?
-Original file line number
+Diff line change
@@ Expand Up / @@ -31,6 +31,7 @@ if [ ! -e $OUTPUT_CURRENT ]; then @@
       exit 3
     fi
+    # Check for each line that the space-separated floats match the baseline with a tolerance of 0.03 %
     OUTPUT_DIFF=$TEST_RUN_DIR/Output.ScaledLogLikelihood.diff
     awk '{FS=" "} function abs(x) {return ((x < 0.0) ? -x : x)} NR==FNR {for (i=1; i<=NF; i++) a[FNR][i]=$i;} NR!=FNR {for (i=1; i<=NF; i++) {if ((abs($i - a[FNR][i])/abs($i)) > 0.03) printf("Line %d, Field %d: Baseline = %f, Current = %f\n", NR, i, a[FNR][i], $i);}}' $OUTPUT_BASELINE $OUTPUT_CURRENT > $OUTPUT_DIFF || exit $?
@@ Expand Down @@