Pipeline fix and new CNNTrain Integration

pom.xml

@@ -9,7 +9,7 @@
 
   <groupId>de.monticore.lang.monticar</groupId>
   <artifactId>cnnarch-gluon-generator</artifactId>
-  <version>0.2.8-SNAPSHOT</version>
+  <version>0.2.9-SNAPSHOT</version>
 
   <!-- == PROJECT DEPENDENCIES ============================================= -->
 
@@ -17,7 +17,7 @@
 
     <!-- .. SE-Libraries .................................................. -->
       <CNNArch.version>0.3.3-SNAPSHOT</CNNArch.version>
-      <CNNTrain.version>0.3.6-SNAPSHOT</CNNTrain.version>
+      <CNNTrain.version>0.3.7-SNAPSHOT</CNNTrain.version>
       <CNNArch2X.version>0.0.4-SNAPSHOT</CNNArch2X.version>
       <embedded-montiarc-math-opt-generator>0.1.4</embedded-montiarc-math-opt-generator>
       <EMADL2PythonWrapper.version>0.0.2-SNAPSHOT</EMADL2PythonWrapper.version>

src/main/java/de/monticore/lang/monticar/cnnarch/gluongenerator/CNNTrain2Gluon.java

@@ -151,7 +151,14 @@ public class CNNTrain2Gluon extends CNNTrainGenerator {
 
             // Generate Reward function if necessary
             if (configuration.getRlRewardFunction().isPresent()) {
-                generateRewardFunction(configuration.getRlRewardFunction().get(), Paths.get(rootProjectModelsDir));
+                if (configuration.getTrainedArchitecture().isPresent()) {
+                    generateRewardFunction(configuration.getTrainedArchitecture().get(),
+                            configuration.getRlRewardFunction().get(), Paths.get(rootProjectModelsDir));
+                } else {
+                    Log.error("No architecture model for the trained neural network but is required for " +
+                     "reinforcement learning configuration.");
+                }
+
             }
 
             ftlContext.put("trainerName", trainerName);
@@ -167,7 +174,8 @@ public class CNNTrain2Gluon extends CNNTrainGenerator {
         return fileContentMap;
     }
 
-    private void generateRewardFunction(RewardFunctionSymbol rewardFunctionSymbol, Path modelsDirPath) {
+    private void generateRewardFunction(NNArchitectureSymbol trainedArchitecture,
+        RewardFunctionSymbol rewardFunctionSymbol, Path modelsDirPath) {
         GeneratorPythonWrapperStandaloneApi pythonWrapperApi = new GeneratorPythonWrapperStandaloneApi();
 
         List<String> fullNameOfComponent = rewardFunctionSymbol.getRewardFunctionComponentName();
@@ -200,7 +208,7 @@ public class CNNTrain2Gluon extends CNNTrainGenerator {
             componentPortInformation = pythonWrapperApi.generate(emaSymbol, pythonWrapperOutputPath);
         }
         RewardFunctionParameterAdapter functionParameter = new RewardFunctionParameterAdapter(componentPortInformation);
-        new FunctionParameterChecker().check(functionParameter);
+        new FunctionParameterChecker().check(functionParameter, trainedArchitecture);
         rewardFunctionSymbol.setRewardFunctionParameter(functionParameter);
     }
 

src/main/java/de/monticore/lang/monticar/cnnarch/gluongenerator/reinforcement/FunctionParameterChecker.java

 /* (c) https://github.com/MontiCore/monticore */
 package de.monticore.lang.monticar.cnnarch.gluongenerator.reinforcement;
 
+import de.monticore.lang.monticar.cnntrain._symboltable.NNArchitectureSymbol;
 import de.se_rwth.commons.logging.Log;
 
+import java.util.List;
+
 /**
  *
  */
@@ -11,21 +14,42 @@ public class FunctionParameterChecker {
     private String inputTerminalParameterName;
     private String outputParameterName;
     private RewardFunctionParameterAdapter rewardFunctionParameter;
+    private NNArchitectureSymbol trainedArchitecture;
 
     public FunctionParameterChecker() {
     }
 
-    public void check(final RewardFunctionParameterAdapter rewardFunctionParameter) {
+    public void check(final RewardFunctionParameterAdapter rewardFunctionParameter,
+        final NNArchitectureSymbol trainedArchitecture) {
+        assert rewardFunctionParameter != null;
+        assert trainedArchitecture != null;
         this.rewardFunctionParameter = rewardFunctionParameter;
+        this.trainedArchitecture = trainedArchitecture;
+
         retrieveParameterNames();
         checkHasExactlyTwoInputs();
         checkHasExactlyOneOutput();
         checkHasStateAndTerminalInput();
-        checkInputStateDimension();
         checkInputTerminalTypeAndDimension();
+        checkStateDimensionEqualsTrainedArchitectureState();
+        checkInputStateDimension();
         checkOutputDimension();
     }
 
+    private void checkStateDimensionEqualsTrainedArchitectureState() {
+        failIfConditionFails(stateInputOfNNArchitectureIsEqualToRewardState(),
+        "State dimension of trained architecture is not equal to reward state dimensions.");
+    }
+
+    private boolean stateInputOfNNArchitectureIsEqualToRewardState() {
+        assert trainedArchitecture.getInputs().size() == 1: "Trained architecture is not a policy network.";
+        final String nnStateInputName = trainedArchitecture.getInputs().get(0);
+        final List<Integer> dimensions = trainedArchitecture.getDimensions().get(nnStateInputName);
+
+        return rewardFunctionParameter.getInputPortDimensionOfPort(inputStateParameterName).isPresent()
+            && rewardFunctionParameter.getInputPortDimensionOfPort(inputStateParameterName).get().equals(dimensions);
+    }
+
     private void checkHasExactlyTwoInputs() {
         failIfConditionFails(functionHasTwoInputs(), "Reward function must have exactly two input parameters: "
                 + "One input needs to represents the environment's state and another input needs to be a "

src/test/java/de/monticore/lang/monticar/cnnarch/gluongenerator/reinforcement/FunctionParameterCheckerTest.java

+package de.monticore.lang.monticar.cnnarch.gluongenerator.reinforcement;
+
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.Lists;
+import de.monticore.lang.monticar.cnntrain._symboltable.NNArchitectureSymbol;
+import de.monticore.lang.monticar.generator.pythonwrapper.symbolservices.data.ComponentPortInformation;
+import de.monticore.lang.monticar.generator.pythonwrapper.symbolservices.data.EmadlType;
+import de.monticore.lang.monticar.generator.pythonwrapper.symbolservices.data.PortDirection;
+import de.monticore.lang.monticar.generator.pythonwrapper.symbolservices.data.PortVariable;
+import de.se_rwth.commons.logging.Finding;
+import de.se_rwth.commons.logging.Log;
+import org.junit.Before;
+import org.junit.Test;
+
+import java.util.List;
+import java.util.Map;
+
+import static org.junit.Assert.*;
+import static org.mockito.Mockito.mock;
+import static org.mockito.Mockito.when;
+
+public class FunctionParameterCheckerTest {
+    private static final List<Integer> STATE_DIMENSIONS = Lists.newArrayList(3,2,4);
+    private static final PortVariable STATE_PORT = PortVariable.multidimensionalVariableFrom("input1", EmadlType.Q,
+            PortDirection.INPUT, STATE_DIMENSIONS);
+    private static final PortVariable TERMINAL_PORT = PortVariable.primitiveVariableFrom("input2", EmadlType.B,
+            PortDirection.INPUT);
+    private static final PortVariable OUTPUT_PORT = PortVariable.primitiveVariableFrom("output1", EmadlType.Q,
+            PortDirection.OUTPUT);
+    private static final String COMPONENT_NAME = "TestRewardComponent";
+
+    FunctionParameterChecker uut = new FunctionParameterChecker();
+
+    @Before
+    public void setup() {
+       Log.getFindings().clear();
+       Log.enableFailQuick(false);
+    }
+
+    @Test
+    public void validReward() {
+        // given
+        RewardFunctionParameterAdapter adapter = getValidRewardAdapter();
+
+        // when
+        uut.check(adapter, getValidTrainedArchitecture());
+        List<Finding> findings = Log.getFindings();
+
+        assertEquals(0, findings.stream().filter(Finding::isError).count());
+    }
+
+    @Test
+    public void invalidRewardWithOneInput() {
+        // given
+        RewardFunctionParameterAdapter adapter = getComponentWithOneInput();
+
+        // when
+        uut.check(adapter, getValidTrainedArchitecture());
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().anyMatch(Finding::isError));
+    }
+
+    @Test
+    public void invalidRewardWithTwoOutputs() {
+        // given
+        RewardFunctionParameterAdapter adapter = getComponentWithTwoOutputs();
+
+        // when
+        uut.check(adapter, getValidTrainedArchitecture());
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().anyMatch(Finding::isError));
+    }
+
+    @Test
+    public void invalidRewardWithTerminalHasQType() {
+        // given
+        RewardFunctionParameterAdapter adapter = getComponentWithTwoQInputs();
+
+        // when
+        uut.check(adapter, getValidTrainedArchitecture());
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().anyMatch(Finding::isError));
+    }
+
+    @Test
+    public void invalidRewardWithNonScalarOutput() {
+        // given
+        RewardFunctionParameterAdapter adapter = getComponentWithNonScalarOutput();
+
+        // when
+        uut.check(adapter, getValidTrainedArchitecture());
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().filter(Finding::isError).count() == 1);
+    }
+
+    @Test
+    public void invalidRewardStateUnequalToTrainedArchitectureState1() {
+        // given
+        RewardFunctionParameterAdapter adapter = getValidRewardAdapter();
+        NNArchitectureSymbol trainedArchitectureWithDifferenDimension = getTrainedArchitectureWithStateDimensions(
+            Lists.newArrayList(6));
+
+        // when
+        uut.check(adapter, trainedArchitectureWithDifferenDimension);
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().filter(Finding::isError).count() == 1);
+    }
+
+    @Test
+    public void invalidRewardStateUnequalToTrainedArchitectureState2() {
+        // given
+        RewardFunctionParameterAdapter adapter = getValidRewardAdapter();
+        NNArchitectureSymbol trainedArchitectureWithDifferenDimension = getTrainedArchitectureWithStateDimensions(
+            Lists.newArrayList(3, 8));
+
+        // when
+        uut.check(adapter, trainedArchitectureWithDifferenDimension);
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().filter(Finding::isError).count() == 1);
+    }
+
+    @Test
+    public void invalidRewardStateUnequalToTrainedArchitectureState3() {
+        // given
+        RewardFunctionParameterAdapter adapter = getValidRewardAdapter();
+        NNArchitectureSymbol trainedArchitectureWithDifferenDimension = getTrainedArchitectureWithStateDimensions(
+            Lists.newArrayList(2,4,3));
+
+        // when
+        uut.check(adapter, trainedArchitectureWithDifferenDimension);
+        List<Finding> findings = Log.getFindings();
+
+        assertTrue(findings.stream().filter(Finding::isError).count() == 1);
+    }
+
+    private RewardFunctionParameterAdapter getComponentWithNonScalarOutput() {
+        ComponentPortInformation componentPortInformation = new ComponentPortInformation(COMPONENT_NAME);
+        componentPortInformation.addAllInputs(getValidInputPortVariables());
+        List<PortVariable> outputs = Lists.newArrayList(PortVariable.multidimensionalVariableFrom(
+        "output", EmadlType.Q, PortDirection.OUTPUT, Lists.newArrayList(2,2)));
+        componentPortInformation.addAllOutputs(outputs);
+        return new RewardFunctionParameterAdapter(componentPortInformation);
+    }
+
+    private RewardFunctionParameterAdapter getComponentWithTwoQInputs() {
+        ComponentPortInformation componentPortInformation
+            = new ComponentPortInformation(COMPONENT_NAME);
+        List<PortVariable> inputs = Lists.newArrayList(STATE_PORT,
+            PortVariable.multidimensionalVariableFrom("input2", EmadlType.Q, PortDirection.INPUT,
+                Lists.newArrayList(2,3,2)));
+        componentPortInformation.addAllInputs(inputs);
+        componentPortInformation.addAllOutputs(getValidOutputPorts());
+        return new RewardFunctionParameterAdapter(componentPortInformation);
+    }
+
+    private RewardFunctionParameterAdapter getComponentWithTwoOutputs() {
+        ComponentPortInformation componentPortInformation
+            = new ComponentPortInformation(COMPONENT_NAME);
+        componentPortInformation.addAllInputs(getValidInputPortVariables());
+        List<PortVariable> outputs = getValidOutputPorts();
+        outputs.add(PortVariable.primitiveVariableFrom("output2", EmadlType.B, PortDirection.OUTPUT));
+        componentPortInformation.addAllOutputs(outputs);
+        return new RewardFunctionParameterAdapter(componentPortInformation);
+    }
+
+    private RewardFunctionParameterAdapter getComponentWithOneInput() {
+        ComponentPortInformation componentPortInformation
+            = new ComponentPortInformation(COMPONENT_NAME);
+        componentPortInformation.addAllInputs(Lists.newArrayList(STATE_PORT));
+        componentPortInformation.addAllOutputs(getValidOutputPorts());
+        return new RewardFunctionParameterAdapter(componentPortInformation);
+    }
+
+    private RewardFunctionParameterAdapter getValidRewardAdapter() {
+        ComponentPortInformation componentPortInformation
+            = new ComponentPortInformation(COMPONENT_NAME);
+        componentPortInformation.addAllInputs(getValidInputPortVariables());
+        componentPortInformation.addAllOutputs(getValidOutputPorts());
+        return new RewardFunctionParameterAdapter(componentPortInformation);
+    }
+
+    private List<PortVariable> getValidOutputPorts() {
+        return Lists.newArrayList(OUTPUT_PORT);
+    }
+
+    private List<PortVariable> getValidInputPortVariables() {
+        return Lists.newArrayList(STATE_PORT, TERMINAL_PORT);
+    }
+
+    private NNArchitectureSymbol getValidTrainedArchitecture() {
+        NNArchitectureSymbol nnArchitectureSymbol = mock(NNArchitectureSymbol.class);
+        final String stateInputName = "stateInput";
+        when(nnArchitectureSymbol.getInputs()).thenReturn(Lists.newArrayList(stateInputName));
+        when(nnArchitectureSymbol.getDimensions()).thenReturn(ImmutableMap.<String, List<Integer>>builder()
+            .put(stateInputName, STATE_DIMENSIONS)
+            .build());
+        return nnArchitectureSymbol;
+    }
+
+    private NNArchitectureSymbol getTrainedArchitectureWithStateDimensions(final List<Integer> dimensions) {
+        NNArchitectureSymbol nnArchitectureSymbol = mock(NNArchitectureSymbol.class);
+        final String stateInputName = "stateInput";
+        when(nnArchitectureSymbol.getInputs()).thenReturn(Lists.newArrayList(stateInputName));
+        when(nnArchitectureSymbol.getDimensions()).thenReturn(ImmutableMap.<String, List<Integer>>builder()
+            .put(stateInputName, dimensions)
+            .build());
+        return nnArchitectureSymbol;
+    }
+}
\ No newline at end of file

src/test/resources/target_code/CNNBufferFile.h

-/* (c) https://github.com/MontiCore/monticore */
 #ifndef CNNBUFFERFILE_H
 #define CNNBUFFERFILE_H
 

src/test/resources/target_code/CNNCreator_Alexnet.py

-# (c) https://github.com/MontiCore/monticore  
 import mxnet as mx
 import logging
 import os

src/test/resources/target_code/CNNCreator_CifarClassifierNetwork.py

-# (c) https://github.com/MontiCore/monticore  
 import mxnet as mx
 import logging
 import os

src/test/resources/target_code/CNNCreator_VGG16.py

-# (c) https://github.com/MontiCore/monticore  
 import mxnet as mx
 import logging
 import os

src/test/resources/target_code/CNNDataLoader_Alexnet.py

-# (c) https://github.com/MontiCore/monticore  
 import os
 import h5py
 import mxnet as mx

src/test/resources/target_code/CNNDataLoader_CifarClassifierNetwork.py

-# (c) https://github.com/MontiCore/monticore  
 import os
 import h5py
 import mxnet as mx

src/test/resources/target_code/CNNDataLoader_VGG16.py

-# (c) https://github.com/MontiCore/monticore  
 import os
 import h5py
 import mxnet as mx

src/test/resources/target_code/CNNNet_Alexnet.py

-# (c) https://github.com/MontiCore/monticore  
 import mxnet as mx
 import numpy as np
 from mxnet import gluon
@@ -91,13 +90,14 @@ class Net_0(gluon.HybridBlock):
             else:
                 self.input_normalization_data_ = NoNormalization()
 
-            self.conv1_padding = Padding(padding=(0,0,0,0,2,1,2,1))
+            self.conv1_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.conv1_ = gluon.nn.Conv2D(channels=96,
                 kernel_size=(11,11),
                 strides=(4,4),
                 use_bias=True)
             # conv1_, output shape: {[96,55,55]}
 
+            self.pool1_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.pool1_ = gluon.nn.MaxPool2D(
                 pool_size=(3,3),
                 strides=(2,2))
@@ -114,6 +114,7 @@ class Net_0(gluon.HybridBlock):
                 use_bias=True)
             # conv2_1_, output shape: {[128,27,27]}
 
+            self.pool2_1_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.pool2_1_ = gluon.nn.MaxPool2D(
                 pool_size=(3,3),
                 strides=(2,2))
@@ -127,6 +128,7 @@ class Net_0(gluon.HybridBlock):
                 use_bias=True)
             # conv2_2_, output shape: {[128,27,27]}
 
+            self.pool2_2_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.pool2_2_ = gluon.nn.MaxPool2D(
                 pool_size=(3,3),
                 strides=(2,2))
@@ -162,6 +164,7 @@ class Net_0(gluon.HybridBlock):
                 use_bias=True)
             # conv5_1_, output shape: {[128,13,13]}
 
+            self.pool5_1_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.pool5_1_ = gluon.nn.MaxPool2D(
                 pool_size=(3,3),
                 strides=(2,2))
@@ -183,6 +186,7 @@ class Net_0(gluon.HybridBlock):
                 use_bias=True)
             # conv5_2_, output shape: {[128,13,13]}
 
+            self.pool5_2_padding = Padding(padding=(0,0,-1,0,0,0,0,0))
             self.pool5_2_ = gluon.nn.MaxPool2D(
                 pool_size=(3,3),
                 strides=(2,2))
@@ -217,7 +221,8 @@ class Net_0(gluon.HybridBlock):
             beta=0.75,
             knorm=2,
             nsize=5)
-        pool1_ = self.pool1_(lrn1_)
+        pool1_padding = self.pool1_padding(lrn1_)
+        pool1_ = self.pool1_(pool1_padding)
         relu1_ = self.relu1_(pool1_)
         split1_ = self.split1_(relu1_)
         get2_1_ = split1_[0]
@@ -228,7 +233,8 @@ class Net_0(gluon.HybridBlock):
             beta=0.75,
             knorm=2,
             nsize=5)
-        pool2_1_ = self.pool2_1_(lrn2_1_)
+        pool2_1_padding = self.pool2_1_padding(lrn2_1_)
+        pool2_1_ = self.pool2_1_(pool2_1_padding)
         relu2_1_ = self.relu2_1_(pool2_1_)
         get2_2_ = split1_[1]
         conv2_2_padding = self.conv2_2_padding(get2_2_)
@@ -238,7 +244,8 @@ class Net_0(gluon.HybridBlock):
             beta=0.75,
             knorm=2,
             nsize=5)
-        pool2_2_ = self.pool2_2_(lrn2_2_)
+        pool2_2_padding = self.pool2_2_padding(lrn2_2_)
+        pool2_2_ = self.pool2_2_(pool2_2_padding)
         relu2_2_ = self.relu2_2_(pool2_2_)
         concatenate3_ = self.concatenate3_(relu2_1_, relu2_2_)
         conv3_padding = self.conv3_padding(concatenate3_)
@@ -251,7 +258,8 @@ class Net_0(gluon.HybridBlock):
         relu4_1_ = self.relu4_1_(conv4_1_)
         conv5_1_padding = self.conv5_1_padding(relu4_1_)
         conv5_1_ = self.conv5_1_(conv5_1_padding)
-        pool5_1_ = self.pool5_1_(conv5_1_)
+        pool5_1_padding = self.pool5_1_padding(conv5_1_)
+        pool5_1_ = self.pool5_1_(pool5_1_padding)
         relu5_1_ = self.relu5_1_(pool5_1_)