Merge branch 'master' into alrezni/examples_text

Conflicts: CNTK.sln
allenyao0702 · Apr 18, 2016 · 22b7f50 · 22b7f50
2 parents 95a3888 + 4c9f918
commit 22b7f50
Show file tree

Hide file tree

Showing 174 changed files with 183,663 additions and 2,092 deletions.
diff --git a/.gitattributes b/.gitattributes
@@ -36,6 +36,7 @@ configure text eol=lf
 generate_build_info text eol=lf
 run-test text eol=lf
 run-test-common text eol=lf
+run-timit-test-common text eol=lf
 make_binary_drop_linux text eol=lf
 
 Makefile text

diff --git a/.gitignore b/.gitignore
@@ -150,6 +150,10 @@ GeneratedArtifacts/
 _Pvt_Extensions/
 ModelManifest.xml
 
+# Python
+*.pyc
+__pychache__/
+
 # =========================
 # Windows detritus
 # =========================

diff --git a/CNTK.sln b/CNTK.sln
@@ -453,20 +453,6 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "GPU", "GPU", "{2A1F0FB0-230
 		Tests\EndToEndTests\LM\RNNLM\GPU\rnnlm.cntk = Tests\EndToEndTests\LM\RNNLM\GPU\rnnlm.cntk
 	EndProjectSection
 EndProject
-Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "SLU", "SLU", "{BFBC6BE1-C33E-4A80-B8F3-A33410EC00FC}"
-	ProjectSection(SolutionItems) = preProject
-		Tests\EndToEndTests\SLU\atis.dev.IOB.simple = Tests\EndToEndTests\SLU\atis.dev.IOB.simple
-		Tests\EndToEndTests\SLU\atis.test.apos.pred.pos.head.IOB.simple = Tests\EndToEndTests\SLU\atis.test.apos.pred.pos.head.IOB.simple
-		Tests\EndToEndTests\SLU\atis.train.apos.pred.pos.head.IOB.simple = Tests\EndToEndTests\SLU\atis.train.apos.pred.pos.head.IOB.simple
-		Tests\EndToEndTests\SLU\globals.cntk = Tests\EndToEndTests\SLU\globals.cntk
-		Tests\EndToEndTests\SLU\input.txt = Tests\EndToEndTests\SLU\input.txt
-		Tests\EndToEndTests\SLU\inputmap.txt = Tests\EndToEndTests\SLU\inputmap.txt
-		Tests\EndToEndTests\SLU\lstmNDL.txt = Tests\EndToEndTests\SLU\lstmNDL.txt
-		Tests\EndToEndTests\SLU\README.txt = Tests\EndToEndTests\SLU\README.txt
-		Tests\EndToEndTests\SLU\rnnlu.cntk = Tests\EndToEndTests\SLU\rnnlu.cntk
-		Tests\EndToEndTests\SLU\rnnlu.ndl.cntk = Tests\EndToEndTests\SLU\rnnlu.ndl.cntk
-	EndProjectSection
-EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "MNIST", "MNIST", "{FA33A61E-95C7-4049-8111-22058CE361A3}"
 	ProjectSection(SolutionItems) = preProject
 		Examples\Image\MNIST\README.md = Examples\Image\MNIST\README.md
@@ -509,7 +495,7 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "CIFAR-10", "CIFAR-10", "{77
 		Examples\Image\Miscellaneous\CIFAR-10\CifarConverter.py = Examples\Image\Miscellaneous\CIFAR-10\CifarConverter.py
 		Examples\Image\Miscellaneous\CIFAR-10\labelsmap.txt = Examples\Image\Miscellaneous\CIFAR-10\labelsmap.txt
 		Examples\Image\Miscellaneous\CIFAR-10\Macros.ndl = Examples\Image\Miscellaneous\CIFAR-10\Macros.ndl
-		Examples\Image\Miscellaneous\CIFAR-10\README.md = Examples\Image\Miscellaneous\CIFAR-10\README.md
+		Examples\Image\Miscellaneous\CIFAR-10\readme.txt = Examples\Image\Miscellaneous\CIFAR-10\readme.txt
 	EndProjectSection
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "ImageNet", "ImageNet", "{EF710C5A-E616-442A-889D-C997D39AF2E1}"
@@ -666,6 +652,7 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Config", "Config", "{850008
 	ProjectSection(SolutionItems) = preProject
 		Examples\Text\PennTreebank\Config\rnn.cntk = Examples\Text\PennTreebank\Config\rnn.cntk
 		Examples\Text\PennTreebank\Config\S2SAutoEncoder.cntk = Examples\Text\PennTreebank\Config\S2SAutoEncoder.cntk
+		Examples\Text\PennTreebank\Config\S2SLib.bs = Examples\Text\PennTreebank\Config\S2SLib.bs
 	EndProjectSection
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "SLU", "SLU", "{E6DC3B7D-303D-4A54-B040-D8DCF8C56E17}"
@@ -900,6 +887,10 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "NetworkTests", "Tests\UnitT
 		{EAD17188-072C-4726-B840-A769C36DAD1B} = {EAD17188-072C-4726-B840-A769C36DAD1B}
 	EndProjectSection
 EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Text", "Text", "{8656B71D-E24C-4AC2-8BE4-C07B415A3E15}"
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "SequenceClassification", "SequenceClassification", "{E53E63A0-FAA9-4416-9AD1-08A8FB87FEE1}"
+EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Miscellaneous", "Miscellaneous", "{8629430A-821E-43BA-AEC5-8B2CF31A2A7A}"
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "CIFAR-10", "CIFAR-10", "{0141526B-F257-4574-8CBE-99634726FFCE}"
@@ -949,6 +940,37 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "SLU", "SLU", "{B900D033-DC3
 		Tests\EndToEndTests\Examples\Text\Miscellaneous\SLU\testcases.yml = Tests\EndToEndTests\Examples\Text\Miscellaneous\SLU\testcases.yml
 	EndProjectSection
 EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Config", "Config", "{EC780385-7580-4D15-914B-1D878A295CBC}"
+	ProjectSection(SolutionItems) = preProject
+		Tests\EndToEndTests\Text\SequenceClassification\Config\seqcla.cntk = Tests\EndToEndTests\Text\SequenceClassification\Config\seqcla.cntk
+	EndProjectSection
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Data", "Data", "{D11F76CC-DB6D-4CB4-B3B7-AB139DE2F5FA}"
+	ProjectSection(SolutionItems) = preProject
+		Tests\EndToEndTests\Text\SequenceClassification\Data\embeddingmatrix.txt = Tests\EndToEndTests\Text\SequenceClassification\Data\embeddingmatrix.txt
+		Tests\EndToEndTests\Text\SequenceClassification\Data\Train.txt = Tests\EndToEndTests\Text\SequenceClassification\Data\Train.txt
+	EndProjectSection
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "SLU", "SLU", "{181664AC-4C95-4798-A923-09B879215B33}"
+	ProjectSection(SolutionItems) = preProject
+		Tests\EndToEndTests\Text\SLU\atis.dev.IOB.simple = Tests\EndToEndTests\Text\SLU\atis.dev.IOB.simple
+		Tests\EndToEndTests\Text\SLU\atis.test.apos.pred.pos.head.IOB.simple = Tests\EndToEndTests\Text\SLU\atis.test.apos.pred.pos.head.IOB.simple
+		Tests\EndToEndTests\Text\SLU\atis.train.apos.pred.pos.head.IOB.simple = Tests\EndToEndTests\Text\SLU\atis.train.apos.pred.pos.head.IOB.simple
+		Tests\EndToEndTests\Text\SLU\baseline.linux.cpu.txt = Tests\EndToEndTests\Text\SLU\baseline.linux.cpu.txt
+		Tests\EndToEndTests\Text\SLU\baseline.linux.gpu.txt = Tests\EndToEndTests\Text\SLU\baseline.linux.gpu.txt
+		Tests\EndToEndTests\Text\SLU\baseline.windows.cpu.txt = Tests\EndToEndTests\Text\SLU\baseline.windows.cpu.txt
+		Tests\EndToEndTests\Text\SLU\baseline.windows.gpu.txt = Tests\EndToEndTests\Text\SLU\baseline.windows.gpu.txt
+		Tests\EndToEndTests\Text\SLU\globals.cntk = Tests\EndToEndTests\Text\SLU\globals.cntk
+		Tests\EndToEndTests\Text\SLU\input.txt = Tests\EndToEndTests\Text\SLU\input.txt
+		Tests\EndToEndTests\Text\SLU\inputmap.txt = Tests\EndToEndTests\Text\SLU\inputmap.txt
+		Tests\EndToEndTests\Text\SLU\lstm.ndl = Tests\EndToEndTests\Text\SLU\lstm.ndl
+		Tests\EndToEndTests\Text\SLU\output.txt = Tests\EndToEndTests\Text\SLU\output.txt
+		Tests\EndToEndTests\Text\SLU\rnnlu.cntk = Tests\EndToEndTests\Text\SLU\rnnlu.cntk
+		Tests\EndToEndTests\Text\SLU\rnnlu.ndl.cntk = Tests\EndToEndTests\Text\SLU\rnnlu.ndl.cntk
+		Tests\EndToEndTests\Text\SLU\run-test = Tests\EndToEndTests\Text\SLU\run-test
+		Tests\EndToEndTests\Text\SLU\testcases.yml = Tests\EndToEndTests\Text\SLU\testcases.yml
+	EndProjectSection
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug_CpuOnly|x64 = Debug_CpuOnly|x64
@@ -1234,7 +1256,6 @@ Global
 		{811924DE-2F12-4EA0-BE58-E57BEF3B74D1} = {3BF59CCE-D245-420A-9F17-73CE61E284C2}
 		{96012801-5187-4FAF-A54E-BF4B73C855F8} = {811924DE-2F12-4EA0-BE58-E57BEF3B74D1}
 		{2A1F0FB0-2304-4F35-87B3-66230C6E58F0} = {811924DE-2F12-4EA0-BE58-E57BEF3B74D1}
-		{BFBC6BE1-C33E-4A80-B8F3-A33410EC00FC} = {6E565B48-1923-49CE-9787-9BBB9D96F4C5}
 		{FA33A61E-95C7-4049-8111-22058CE361A3} = {9BDFA4BE-790E-408F-915B-5979BB5078C6}
 		{F99E1E80-50D8-421C-AD94-8ED0DF08C355} = {9BDFA4BE-790E-408F-915B-5979BB5078C6}
 		{ED57E827-B28F-4BEE-BFB7-398EF8D83357} = {FA33A61E-95C7-4049-8111-22058CE361A3}
@@ -1290,6 +1311,8 @@ Global
 		{48C2A9DE-FB2C-4724-9ADC-744216D79BCF} = {08A05A9A-4E45-42D5-83FA-719E99C04A30}
 		{2B1046A1-0140-43B7-B3DC-CF7DEEE1009E} = {8071EF60-30F7-4A77-81AA-ADCA0E18B1E3}
 		{CDA96AA3-3252-4978-A0BF-2ACD670823CB} = {6F19321A-65E7-4829-B00C-3886CD6C6EDE}
+		{8656B71D-E24C-4AC2-8BE4-C07B415A3E15} = {6E565B48-1923-49CE-9787-9BBB9D96F4C5}
+		{E53E63A0-FAA9-4416-9AD1-08A8FB87FEE1} = {8656B71D-E24C-4AC2-8BE4-C07B415A3E15}
 		{8629430A-821E-43BA-AEC5-8B2CF31A2A7A} = {FC7E7EC7-6E6A-4518-81C6-DA60451C657A}
 		{0141526B-F257-4574-8CBE-99634726FFCE} = {8629430A-821E-43BA-AEC5-8B2CF31A2A7A}
 		{58286327-6742-44C4-A34E-D2583419E55E} = {0141526B-F257-4574-8CBE-99634726FFCE}
@@ -1298,5 +1321,8 @@ Global
 		{2BFE4D88-6F32-4701-887A-1DE3D7626DBB} = {0141526B-F257-4574-8CBE-99634726FFCE}
 		{CCB0CD89-DE53-4104-94D3-041D46FC8885} = {439BE0E0-FABE-403D-BF2C-A41FB8A60616}
 		{B900D033-DC37-45F1-AE52-F35584FD3024} = {CCB0CD89-DE53-4104-94D3-041D46FC8885}
+		{EC780385-7580-4D15-914B-1D878A295CBC} = {E53E63A0-FAA9-4416-9AD1-08A8FB87FEE1}
+		{D11F76CC-DB6D-4CB4-B3B7-AB139DE2F5FA} = {E53E63A0-FAA9-4416-9AD1-08A8FB87FEE1}
+		{181664AC-4C95-4798-A923-09B879215B33} = {8656B71D-E24C-4AC2-8BE4-C07B415A3E15}
 	EndGlobalSection
 EndGlobal
diff --git a/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_AdaptLearnRate.cntk b/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_AdaptLearnRate.cntk
@@ -1,12 +1,14 @@
-stderr=$ExpDir$\TrainAdaptLR\log\log
+# If set to true, always initialize the network on CPU, making initialization consistent across CPU and GPU targets (for testing).
+initOnCPUOnly=true 
+
 command=TIMIT_TrainAdaptLR
 
 precision=float
 
 TIMIT_TrainAdaptLR=[
     action=train
 
-    modelPath=$ExpDir$\TrainAdaptLR\model\cntkSpeech.dnn
+    modelPath=$ExpDir$/TrainAdaptLR/model/cntkSpeech.dnn
 
     # deviceId=-1 for CPU, >=0 for GPU devices 
     deviceId=$DeviceNumber$
@@ -23,7 +25,7 @@ TIMIT_TrainAdaptLR=[
         uniformInit=true
         needPrior=true
     ]
-    
+
     SGD=[
         epochSize=0
         minibatchSize=128
@@ -51,47 +53,42 @@ TIMIT_TrainAdaptLR=[
         clippingThresholdPerSample=1#INF
 
     ]
-       
+
     # Parameter values for the reader
     reader=[
-      # reader to use
-      readerType=HTKMLFReader
-#      readMethod=blockRandomize
-      readMethod=rollingWindow
-      miniBatchMode=Partial
-      randomize=Auto
-      verbosity=1   
-      features=[
-	dim=792	
-     	scpFile=$ScpDir$\TIMIT.train.scp.fbank.fullpath
-      ]
+        # reader to use
+        readerType=HTKMLFReader
+        readMethod=blockRandomize
+        miniBatchMode=Partial
+        randomize=Auto
+        verbosity=0
+        features=[
+            dim=792
+            scpFile=$ScpDir$/TIMIT.train.scp.fbank.fullpath.rnn
+        ]
 
-      labels=[
-	mlfFile=$MlfDir$\TIMIT.train.align_cistate.mlf.cntk
-        labelDim=183
-	labelMappingFile=$MlfDir$\TIMIT.statelist
-      ]
+        labels=[
+            mlfFile=$MlfDir$/TIMIT.train.align_cistate.mlf.cntk
+            labelDim=183
+            labelMappingFile=$MlfDir$/TIMIT.statelist
+        ]
     ]
 
     cvReader=[
-      # reader to use
-      readerType=HTKMLFReader
-#      readMethod=blockRandomize
-      readMethod=rollingWindow
-      miniBatchMode=Partial
-      randomize=Auto
-      verbosity=1   
-      features=[
-	dim=792
-	scpFile=$ScpDir$\TIMIT.dev.scp.fbank.fullpath    
-      ]
+        readerType=HTKMLFReader
+        readMethod=blockRandomize
+        miniBatchMode=Partial
+        randomize=Auto
+        verbosity=0
+        features=[
+            dim=792
+            scpFile=$ScpDir$/TIMIT.dev.scp.fbank.fullpath.rnn
+        ]
 
-      labels=[
-	mlfFile=$MlfDir$\TIMIT.dev.align_cistate.mlf.cntk
-        labelDim=183	
-	labelMappingFile=$MlfDir$\TIMIT.statelist
-      ]
+        labels=[
+            mlfFile=$MlfDir$/TIMIT.dev.align_cistate.mlf.cntk
+            labelDim=183
+            labelMappingFile=$MlfDir$/TIMIT.statelist
+        ]
     ]
-
-]
-
+]
diff --git a/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_CrossValidateSimpleNetwork.cntk b/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_CrossValidateSimpleNetwork.cntk
@@ -1,4 +1,6 @@
-stderr=$ExpDir$\CrossValidateSimpleNetwork\log\log
+# If set to true, always initialize the network on CPU, making initialization consistent across CPU and GPU targets (for testing).
+initOnCPUOnly=true
+
 command=TIMIT_CVSimple
 
 precision=float
@@ -10,33 +12,31 @@ precision=float
 TIMIT_CVSimple=[
     action=cv
 
-    modelPath=$ExpDir$\TrainSimpleNetwork\model\cntkSpeech.dnn
+    modelPath=$ExpDir$/TrainSimpleNetwork/model/cntkSpeech.dnn
 
     # deviceId=-1 for CPU, >=0 for GPU devices 
     deviceId=$DeviceNumber$
 
     traceLevel=1
     crossValidationInterval=0:2:25 # evaluate from model 0 to model 10, every 2 models (0,2,4, etc)
-     # Parameter values for the reader
+    # Parameter values for the reader
     reader=[
-      # reader to use
-      readerType=HTKMLFReader
-#     readMethod=blockRandomize
-      readMethod=rollingWindow
-
-      miniBatchMode=Partial
-      randomize=None
-      verbosity=1   
-
-      features=[
-	  dim=792
-	  scpFile=$ScpDir$\TIMIT.dev.scp.fbank.fullpath
-      ]
-
-      labels=[
-	mlfFile=$MlfDir$\TIMIT.dev.align_cistate.mlf.cntk
-        labelDim=183
-	labelMappingFile=$MlfDir$\TIMIT.statelist
-      ]
+        # reader to use
+        readerType=HTKMLFReader
+        miniBatchMode=Partial
+        readMethod=rollingWindow
+        randomize=None
+        verbosity=0
+
+        features=[
+            dim=792
+            scpFile=$ScpDir$/TIMIT.dev.scp.fbank.fullpath
+        ]
+
+        labels=[
+            mlfFile=$MlfDir$/TIMIT.dev.align_cistate.mlf.cntk
+            labelDim=183
+            labelMappingFile=$MlfDir$/TIMIT.statelist
+        ]
     ]
-]
+]
diff --git a/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_EvalSimpleNetwork.cntk b/Examples/Speech/Miscellaneous/TIMIT/config/TIMIT_EvalSimpleNetwork.cntk
@@ -1,4 +1,6 @@
-stderr=$ExpDir$\EvalSimpleNetwork\log\log
+# If set to true, always initialize the network on CPU, making initialization consistent across CPU and GPU targets (for testing).
+initOnCPUOnly=true
+
 command=TIMIT_EvalSimple
 
 precision=float
@@ -10,7 +12,7 @@ precision=float
 TIMIT_EvalSimple=[
     action=eval
 
-    modelPath=$ExpDir$\TrainSimpleNetwork\model\cntkSpeech.dnn
+    modelPath=$ExpDir$/TrainSimpleNetwork/model/cntkSpeech.dnn
 
     # deviceId=-1 for CPU, >=0 for GPU devices 
     deviceId=$DeviceNumber$
@@ -19,24 +21,22 @@ TIMIT_EvalSimple=[
 
      # Parameter values for the reader
     reader=[
-      # reader to use
-      readerType=HTKMLFReader
-#     readMethod=blockRandomize
-      readMethod=rollingWindow
-
-      miniBatchMode=Partial
-      randomize=None
-      verbosity=1   
-
-      features=[
-	  dim=792
-	  scpFile=$ScpDir$\TIMIT.dev.scp.fbank.fullpath
-      ]
-
-      labels=[
-	mlfFile=$MlfDir$\TIMIT.dev.align_cistate.mlf.cntk
-        labelDim=183
-	labelMappingFile=$MlfDir$\TIMIT.statelist
-      ]
+        # reader to use
+        readerType=HTKMLFReader
+        miniBatchMode=Partial
+        readMethod=rollingWindow
+        randomize=None
+        verbosity=0
+
+        features=[
+            dim=792
+            scpFile=$ScpDir$/TIMIT.dev.scp.fbank.fullpath
+        ]
+
+        labels=[
+            mlfFile=$MlfDir$/TIMIT.dev.align_cistate.mlf.cntk
+            labelDim=183
+            labelMappingFile=$MlfDir$/TIMIT.statelist
+        ]
     ]
-]
+]