adjusted tests

src/main/java/de/monticore/lang/monticar/emadl/generator/EMADLGenerator.java

@@ -16,8 +16,12 @@ import de.monticore.lang.monticar.cnnarch.generator.CNNTrainGenerator;
 import de.monticore.lang.monticar.cnnarch.generator.DataPathConfigParser;
 import de.monticore.lang.monticar.cnnarch.gluongenerator.CNNTrain2Gluon;
 import de.monticore.lang.monticar.cnnarch.gluongenerator.annotations.ArchitectureAdapter;
+import de.monticore.lang.monticar.cnnarch.gluongenerator.preprocessing.PreprocessingComponentParameterAdapter;
+import de.monticore.lang.monticar.cnnarch.gluongenerator.preprocessing.PreprocessingPortChecker;
 import de.monticore.lang.monticar.cnntrain._cocos.CNNTrainCocos;
 import de.monticore.lang.monticar.cnntrain._symboltable.ConfigurationSymbol;
+import de.monticore.lang.monticar.cnntrain._symboltable.LearningMethod;
+import de.monticore.lang.monticar.cnntrain._symboltable.PreprocessingComponentSymbol;
 import de.monticore.lang.monticar.emadl._cocos.DataPathCocos;
 import de.monticore.lang.monticar.emadl._cocos.EMADLCocos;
 import de.monticore.lang.monticar.emadl.tagging.dltag.DataPathSymbol;
@@ -30,6 +34,7 @@ import de.monticore.lang.monticar.generator.pythonwrapper.GeneratorPythonWrapper
 import de.monticore.lang.monticar.generator.cpp.converter.TypeConverter;
 import de.monticore.lang.monticar.generator.pythonwrapper.GeneratorPythonWrapperFactory;
 import de.monticore.lang.monticar.generator.pythonwrapper.GeneratorPythonWrapperStandaloneApi;
+import de.monticore.lang.monticar.generator.pythonwrapper.symbolservices.data.ComponentPortInformation;
 import de.monticore.lang.tagging._symboltable.TagSymbol;
 import de.monticore.lang.tagging._symboltable.TaggingResolver;
 import de.monticore.symboltable.Scope;
@@ -621,7 +626,6 @@ public class EMADLGenerator {
                     }
                     discriminator.get().setComponentName(fullDiscriminatorName);
                     configuration.setDiscriminatorNetwork(new ArchitectureAdapter(fullDiscriminatorName, discriminator.get()));
-                    //CNNTrainCocos.checkCriticCocos(configuration);
                 }
 
                 // Resolve QNetwork if present
@@ -643,11 +647,16 @@ public class EMADLGenerator {
                     }
                     qnetwork.get().setComponentName(fullQNetworkName);
                     configuration.setQNetwork(new ArchitectureAdapter(fullQNetworkName, qnetwork.get()));
-                    //CNNTrainCocos.checkCriticCocos(configuration);
                 }
 
+                if (configuration.getLearningMethod() == LearningMethod.GAN)
+                    CNNTrainCocos.checkGANCocos(configuration);
+
                 if (configuration.hasPreprocessor()) {
-                    String fullPreprocessorName = configuration.getPreprocessingName().get();
+                    PreprocessingComponentSymbol preprocessingSymbol = configuration.getPreprocessingComponent().get();
+                    List<String> fullNameOfComponent = preprocessingSymbol.getPreprocessingComponentName();
+                    String fullPreprocessorName = String.join(".", fullNameOfComponent);
+
                     int indexOfFirstNameCharacter = fullPreprocessorName.lastIndexOf('.') + 1;
                     fullPreprocessorName = fullPreprocessorName.substring(0, indexOfFirstNameCharacter)
                             + fullPreprocessorName.substring(indexOfFirstNameCharacter, indexOfFirstNameCharacter + 1).toUpperCase()
@@ -671,7 +680,11 @@ public class EMADLGenerator {
                     }
 
                     String targetPath = getGenerationTargetPath();
-                    pythonWrapper.generateAndTryBuilding(processor_instance, targetPath + "/pythonWrapper", targetPath);
+                    ComponentPortInformation componentPortInformation;
+                    componentPortInformation = pythonWrapper.generateAndTryBuilding(processor_instance, targetPath + "/pythonWrapper", targetPath);
+                    PreprocessingComponentParameterAdapter componentParameter = new PreprocessingComponentParameterAdapter(componentPortInformation);
+                    PreprocessingPortChecker.check(componentParameter);
+                    preprocessingSymbol.setPreprocessingComponentParameter(componentParameter);
                 }
 
                 cnnTrainGenerator.setInstanceName(componentInstance.getFullName().replaceAll("\\.", "_"));

src/main/java/de/monticore/lang/monticar/emadl/generator/reinforcementlearning/RewardFunctionCppGenerator.java

@@ -22,7 +22,7 @@ public class RewardFunctionCppGenerator implements RewardFunctionSourceGenerator
                 .<EMAComponentInstanceSymbol>resolve(rootModel, EMAComponentInstanceSymbol.KIND);
 
         if (!instanceSymbol.isPresent()) {
-            Log.error("Generation of reward function is not possible: Cannot resolve component instance "
+            Log.error("Generation of component is not possible: Cannot resolve component instance "
                     + rootModel);
         }
 
@@ -40,7 +40,7 @@ public class RewardFunctionCppGenerator implements RewardFunctionSourceGenerator
         try {
             generator.generate(componentInstanceSymbol, taggingResolver);
         } catch (IOException e) {
-            Log.error("Generation of reward function is not possible: " + e.getMessage());
+            Log.error("Generation of rd function is not possible: " + e.getMessage());
         }
 
     }

src/test/resources/target_code/gluon/CNNCreator_mnist_mnistClassifier_net.py

@@ -58,3 +58,17 @@ class CNNCreator_mnist_mnistClassifier_net:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (1,28,28,)
+        input_domains = (int,0.0,255.0,)
+        inputs["image_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (10,1,1,)
+        output_domains = (float,0.0,1.0,)
+        outputs["predictions_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/CNNDataLoader_mnist_mnistClassifier_net.py

@@ -4,7 +4,6 @@ import mxnet as mx
 import logging
 import sys
 import numpy as np
-import cv2
 import importlib
 from mxnet import nd
 
@@ -78,6 +77,7 @@ class CNNDataLoader_mnist_mnistClassifier_net:
         train_label = {}
         data_mean = {}
         data_std = {}
+        train_images = {}
 
         shape_output = self.preprocess_data(instance, inp, 0, train_h5)
         train_len = len(train_h5[self._input_names_[0]])
@@ -140,6 +140,7 @@ class CNNDataLoader_mnist_mnistClassifier_net:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        test_images = {}
         if 'images' in test_h5:
             test_images = test_h5['images']
 
@@ -151,103 +152,7 @@ class CNNDataLoader_mnist_mnistClassifier_net:
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:
-            data = data_h5[input_name][0]
-            attr = getattr(input_wrapper, input_name)
-            if (type(data)) == np.ndarray:
-                data = np.asfortranarray(data).astype(attr.dtype)
-            else:
-                data = type(attr)(data)
-            setattr(input_wrapper, input_name, data)
-        for output_name in self._output_names_:
-            data = data_h5[output_name][0]
-            attr = getattr(input_wrapper, output_name)
-            if (type(data)) == np.ndarray:
-                data = np.asfortranarray(data).astype(attr.dtype)
-            else:
-                data = type(attr)(data)
-            setattr(input_wrapper, output_name, data)
-        return instance_wrapper.execute(input_wrapper)
-
-    def load_preprocessed_data(self, batch_size, preproc_lib):
-        train_h5, test_h5 = self.load_h5_files()
-
-        wrapper = importlib.import_module(preproc_lib)
-        instance = getattr(wrapper, preproc_lib)()
-        instance.init()
-        lib_head, _sep, tail = preproc_lib.rpartition('_')
-        inp = getattr(wrapper, lib_head + "_input")()
-
-        train_data = {}
-        train_label = {}
-        data_mean = {}
-        data_std = {}
-
-        shape_output = self.preprocess_data(instance, inp, 0, train_h5)
-        train_len = len(train_h5[self._input_names_[0]])
-
-        for input_name in self._input_names_:
-            if type(getattr(shape_output, input_name + "_out")) == np.ndarray:
-                cur_shape = (train_len,) + getattr(shape_output, input_name + "_out").shape
-            else:
-                cur_shape = (train_len, 1)
-            train_data[input_name] = mx.nd.zeros(cur_shape)
-        for output_name in self._output_names_:
-            if type(getattr(shape_output, output_name + "_out")) == nd.array:
-                cur_shape = (train_len,) + getattr(shape_output, output_name + "_out").shape
-            else:
-                cur_shape = (train_len, 1)
-            train_label[output_name] = mx.nd.zeros(cur_shape)
-
-        for i in range(train_len):
-            output = self.preprocess_data(instance, inp, i, train_h5)
-            for input_name in self._input_names_:
-                train_data[input_name][i] = getattr(output, input_name + "_out")
-            for output_name in self._output_names_:
-                train_label[output_name][i] = getattr(shape_output, output_name + "_out")
-
-        for input_name in self._input_names_:
-            data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        train_iter = mx.io.NDArrayIter(data=train_data,
-                                       label=train_label,
-                                       batch_size=batch_size)
-
-        test_data = {}
-        test_label = {}
-
-        shape_output = self.preprocess_data(instance, inp, 0, test_h5)
-        test_len = len(test_h5[self._input_names_[0]])
-
-        for input_name in self._input_names_:
-            if type(getattr(shape_output, input_name + "_out")) == np.ndarray:
-                cur_shape = (test_len,) + getattr(shape_output, input_name + "_out").shape
-            else:
-                cur_shape = (test_len, 1)
-            test_data[input_name] = mx.nd.zeros(cur_shape)
-        for output_name in self._output_names_:
-            if type(getattr(shape_output, output_name + "_out")) == nd.array:
-                cur_shape = (test_len,) + getattr(shape_output, output_name + "_out").shape
-            else:
-                cur_shape = (test_len, 1)
-            test_label[output_name] = mx.nd.zeros(cur_shape)
-
-        for i in range(test_len):
-            output = self.preprocess_data(instance, inp, i, test_h5)
-            for input_name in self._input_names_:
-                test_data[input_name][i] = getattr(output, input_name + "_out")
-            for output_name in self._output_names_:
-                test_label[output_name][i] = getattr(shape_output, output_name + "_out")
-
-        test_iter = mx.io.NDArrayIter(data=test_data,
-                                       label=test_label,
-                                       batch_size=batch_size)
-
-        return train_iter, test_iter, data_mean, data_std
-
-    def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
-        for input_name in self._input_names_:
-            data = data_h5[input_name][0]
+            data = data_h5[input_name][index]
             attr = getattr(input_wrapper, input_name)
             if (type(data)) == np.ndarray:
                 data = np.asfortranarray(data).astype(attr.dtype)
@@ -255,7 +160,7 @@ class CNNDataLoader_mnist_mnistClassifier_net:
                 data = type(attr)(data)
             setattr(input_wrapper, input_name, data)
         for output_name in self._output_names_:
-            data = data_h5[output_name][0]
+            data = data_h5[output_name][index]
             attr = getattr(input_wrapper, output_name)
             if (type(data)) == np.ndarray:
                 data = np.asfortranarray(data).astype(attr.dtype)

src/test/resources/target_code/gluon/CNNNet_mnist_mnistClassifier_net.py

@@ -148,16 +148,3 @@ class Net_0(gluon.HybridBlock):
 
         return predictions_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (1,28,28)
-        input_domains = (int,0.0,255.0)
-        inputs["image_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (10,1,1)
-        output_domains = (float,0.0,1.0)
-        outputs["predictions_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/CNNTrainer_mnist_mnistClassifier_net.py

@@ -21,6 +21,7 @@ if __name__ == "__main__":
         batch_size=64,
         num_epoch=11,
         context='gpu',
+        preprocessing=False,
         eval_metric='accuracy',
         eval_metric_params={
         },

src/test/resources/target_code/gluon/reinforcementModel/cartpole/CNNCreator_cartpole_master_dqn.py

@@ -58,3 +58,17 @@ class CNNCreator_cartpole_master_dqn:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (4,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (2,1,1,)
+        output_domains = (float,float('-inf'),float('inf'),)
+        outputs["qvalues_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/cartpole/CNNNet_cartpole_master_dqn.py

@@ -123,17 +123,3 @@ class Net_0(gluon.HybridBlock):
 
         return qvalues_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (4)
-        input_domains = (float,float('-inf'),float('inf'))
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (2,1,1)
-        output_domains = (float,float('-inf'),float('inf'))
-        outputs["qvalues_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/reinforcementModel/mountaincar/CNNCreator_mountaincar_master_actor.py

@@ -58,3 +58,17 @@ class CNNCreator_mountaincar_master_actor:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (2,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (1,1,1,)
+        output_domains = (float,-1.0,1.0,)
+        outputs["action_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/mountaincar/CNNNet_mountaincar_master_actor.py

@@ -125,16 +125,3 @@ class Net_0(gluon.HybridBlock):
 
         return action_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (2)
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (1,1,1)
-        output_domains = (float,-1.0,1.0)
-        outputs["action_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/reinforcementModel/mountaincar/reinforcement_learning/CNNCreator_mountaincar_agent_mountaincarCritic.py

@@ -58,3 +58,20 @@ class CNNCreator_mountaincar_agent_mountaincarCritic:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (2,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        input_dimensions = (1,)
+        input_domains = (float,-1.0,1.0,)
+        inputs["action_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (1,1,1,)
+        output_domains = (float,float('-inf'),float('inf'),)
+        outputs["qvalues_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/mountaincar/reinforcement_learning/CNNNet_mountaincar_agent_mountaincarCritic.py

@@ -136,20 +136,3 @@ class Net_0(gluon.HybridBlock):
 
         return qvalues_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (2)
-        input_domains = (float,float('-inf'),float('inf'))
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        input_dimensions = (1)
-        input_domains = (float,-1.0,1.0)
-        inputs["action_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (1,1,1)
-        output_domains = (float,float('-inf'),float('inf'))
-        outputs["qvalues_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs/CNNCreator_torcs_agent_torcsAgent_dqn.py

@@ -58,3 +58,17 @@ class CNNCreator_torcs_agent_torcsAgent_dqn:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (5,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (30,1,1,)
+        output_domains = (float,float('-inf'),float('inf'),)
+        outputs["qvalues_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs/CNNNet_torcs_agent_torcsAgent_dqn.py

@@ -123,16 +123,3 @@ class Net_0(gluon.HybridBlock):
 
         return qvalues_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (5)
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (30,1,1)
-        output_domains = (float,float('-inf'),float('inf'))
-        outputs["qvalues_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs_td3/CNNCreator_torcs_agent_torcsAgent_actor.py

@@ -58,3 +58,17 @@ class CNNCreator_torcs_agent_torcsAgent_actor:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (29,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (3,1,1,)
+        output_domains = (float,-1.0,1.0,)
+        outputs["commands_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs_td3/CNNNet_torcs_agent_torcsAgent_actor.py

@@ -125,16 +125,3 @@ class Net_0(gluon.HybridBlock):
 
         return commands_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (29)
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (3,1,1)
-        output_domains = (float,-1.0,1.0)
-        outputs["commands_"] = output_domains + (output_dimensions,)
-        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs_td3/reinforcement_learning/CNNCreator_torcs_agent_network_torcsCritic.py

@@ -58,3 +58,20 @@ class CNNCreator_torcs_agent_network_torcsCritic:
 
         for i, network in self.networks.items():
             network.export(self._model_dir_ + self._model_prefix_ + "_" + str(i), epoch=0)
+
+    def getInputs(self):
+        inputs = {}
+        input_dimensions = (29,)
+        input_domains = (float,0,1,)
+        inputs["state_"] = input_domains + (input_dimensions,)
+        input_dimensions = (3,)
+        input_domains = (float,-1.0,1.0,)
+        inputs["action_"] = input_domains + (input_dimensions,)
+        return inputs
+
+    def getOutputs(self):
+        outputs = {}
+        output_dimensions = (1,1,1,)
+        output_domains = (float,float('-inf'),float('inf'),)
+        outputs["qvalues_"] = output_domains + (output_dimensions,)
+        return outputs

src/test/resources/target_code/gluon/reinforcementModel/torcs_td3/reinforcement_learning/CNNNet_torcs_agent_network_torcsCritic.py

@@ -132,19 +132,3 @@ class Net_0(gluon.HybridBlock):
 
         return qvalues_
 
-    def getInputs(self):
-        inputs = {}
-        input_dimensions = (29)
-        input_domains = (float,0,1)
-        inputs["state_"] = input_domains + (input_dimensions,)
-        input_dimensions = (3)
-        input_domains = (float,-1.0,1.0)
-        inputs["action_"] = input_domains + (input_dimensions,)
-        return inputs
-
-    def getOutputs(self):
-        outputs = {}
-        output_dimensions = (1,1,1)
-        output_domains = (float,float('-inf'),float('inf'))
-        outputs["qvalues_"] = output_domains + (output_dimensions,)
-        return outputs

train.log

 Epoch[0] Train-accuracy=0.100000
-Epoch[0] Time cost=0.049
-Epoch[0] Validation-accuracy=0.200000
-Epoch[1] Train-accuracy=0.100000
-Epoch[1] Time cost=0.051
+Epoch[0] Time cost=0.076
+Epoch[0] Validation-accuracy=0.500000
+Epoch[1] Train-accuracy=0.500000
+Epoch[1] Time cost=0.061
 Epoch[1] Validation-accuracy=0.300000
 Epoch[2] Train-accuracy=0.600000
-Epoch[2] Time cost=0.049
-Epoch[2] Validation-accuracy=0.200000
-Epoch[3] Train-accuracy=0.700000
-Epoch[3] Time cost=0.045
-Epoch[3] Validation-accuracy=0.100000
-Epoch[4] Train-accuracy=0.500000
-Epoch[4] Time cost=0.069
+Epoch[2] Time cost=0.096
+Epoch[2] Validation-accuracy=0.300000
+Epoch[3] Train-accuracy=0.500000
+Epoch[3] Time cost=0.076
+Epoch[3] Validation-accuracy=0.200000
+Epoch[4] Train-accuracy=0.600000
+Epoch[4] Time cost=0.048
 Saved checkpoint to "model/instanceTestCifar.CifarNetwork/model-0005.params"
 Epoch[4] Validation-accuracy=0.200000
-Epoch[5] Train-accuracy=0.500000
-Epoch[5] Time cost=0.055
+Epoch[5] Train-accuracy=0.400000
+Epoch[5] Time cost=0.070
 Epoch[5] Validation-accuracy=0.200000
-Epoch[6] Train-accuracy=0.500000
-Epoch[6] Time cost=0.068
-Epoch[6] Validation-accuracy=0.200000
-Epoch[7] Train-accuracy=0.400000
-Epoch[7] Time cost=0.076
-Epoch[7] Validation-accuracy=0.200000
+Epoch[6] Train-accuracy=0.400000
+Epoch[6] Time cost=0.062
+Epoch[6] Validation-accuracy=0.100000
+Epoch[7] Train-accuracy=0.500000
+Epoch[7] Time cost=0.046
+Epoch[7] Validation-accuracy=0.100000
 Epoch[8] Train-accuracy=0.400000
-Epoch[8] Time cost=0.051
-Epoch[8] Validation-accuracy=0.200000
+Epoch[8] Time cost=0.061
+Epoch[8] Validation-accuracy=0.100000
 Epoch[9] Train-accuracy=0.400000
-Epoch[9] Time cost=0.052
+Epoch[9] Time cost=0.066
 Saved checkpoint to "model/instanceTestCifar.CifarNetwork/model-0010.params"
 Epoch[9] Validation-accuracy=0.100000