CPU info:
    CPU Model Name: Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz
    Hardware threads: 12
    Total Memory: 33474872 kB
-------------------------------------------------------------------
+ [[ C:\CNTKTestData == '' ]]
+ [[ ! -d C:\CNTKTestData ]]
+ '[' Windows_NT == Windows_NT ']'
++ cygpath -au 'C:\CNTKTestData'
+ TEST_DATA_DIR=/cygdrive/c/CNTKTestData
+ LocalTestDir=/tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData
+ mkdir /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData
+ '[' cpu == cpu ']'
+ export CUDA_VISIBLE_DEVICES=-1
+ CUDA_VISIBLE_DEVICES=-1
+ echo Use pre-trained eval models in 'C:\CNTKTestData' for cpp eval tests.
Use pre-trained eval models in C:\CNTKTestData for cpp eval tests.
+ cp /cygdrive/c/CNTKTestData/PreTrainedModels/EvalModels/01_OneHidden.model /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData/01_OneHidden.model
+ cp /cygdrive/c/CNTKTestData/PreTrainedModels/EvalModels/resnet20_cifar10_python.dnn /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData/resnet20.dnn
+ cp /cygdrive/c/CNTKTestData/PreTrainedModels/EvalModels/atis.dnn /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData/atis.dnn
+ cp /cygdrive/c/repos/ThirdCNTK/Tests/EndToEndTests/../../Examples/LanguageUnderstanding/ATIS/BrainScript/query.wl /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData/query.wl
+ cp /cygdrive/c/repos/ThirdCNTK/Tests/EndToEndTests/../../Examples/LanguageUnderstanding/ATIS/BrainScript/slots.wl /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData/slots.wl
+ pushd /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData
/tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData /cygdrive/c/repos/ThirdCNTK/Tests/EndToEndTests/EvalClientTests/CNTKLibraryCPPEvalExamplesTest
+ '[' Windows_NT == Windows_NT ']'
+ /cygdrive/c/repos/ThirdCNTK/x64/release/CNTKLibraryCPPEvalExamplesTest.exe

##### Test CPPEval samples on CPU device. #####

===== Evaluate single sample using dense format.
The batch contains 1 sequences.
Sequence 0 contains 1 samples.
    sample 0: 2.784544, 2.258028, -0.253707, 2.223094, -3.174539, -1.431938, -1.481088, -3.174907, 1.350909, 0.903016.

===== Evaluate batch of samples using dense format.
The batch contains 3 sequences.
Sequence 0 contains 1 samples.
    sample 0: 2.784545, 2.258028, -0.253708, 2.223094, -3.174539, -1.431939, -1.481088, -3.174907, 1.350909, 0.903017.
Sequence 1 contains 1 samples.
    sample 0: 5.640748, 3.034741, -0.655203, 2.712542, -4.132360, -2.585585, -3.404921, -4.179915, 2.686388, 0.879486.
Sequence 2 contains 1 samples.
    sample 0: 3.997461, 4.642735, 0.845104, 2.094089, -4.255864, -1.791972, -2.881375, -4.643809, 1.214328, 0.780322.

===== Evaluate multiple requests in parallel.
thread 0 joined.
thread 1 joined.
thread 2 joined.

===== Evaluate single sequence using one-hot vector.
            BOS ---- O
              i ---- O
          would ---- O
           like ---- O
             to ---- O
           find ---- O
              a ---- O
         flight ---- O
           from ---- O
      charlotte ---- B-fromloc.city_name
             to ---- O
            las ---- B-toloc.city_name
          vegas ---- I-toloc.city_name
           that ---- O
          makes ---- O
              a ---- O
           stop ---- O
             in ---- O
            st. ---- B-stoploc.city_name
          louis ---- B-arrive_time.time_relative
            EOS ---- O


===== Evaluate batch of sequences with variable length using one-hot vector.
The number of sequences in the batch: 2
Sequence 0:
            BOS ---- O
              i ---- O
          would ---- O
           like ---- O
             to ---- O
           find ---- O
              a ---- O
         flight ---- O
           from ---- O
      charlotte ---- B-fromloc.city_name
             to ---- O
            las ---- B-toloc.city_name
          vegas ---- I-toloc.city_name
           that ---- O
          makes ---- O
              a ---- O
           stop ---- O
             in ---- O
            st. ---- B-stoploc.city_name
          louis ---- B-arrive_time.time_relative
            EOS ---- O

Sequence 1:
            BOS ---- O
        flights ---- O
           from ---- O
            new ---- B-fromloc.city_name
           york ---- I-fromloc.city_name
             to ---- O
        seattle ---- B-toloc.city_name
            EOS ---- O


===== Evaluate single sequence using sparse input.
            BOS ---- O
              i ---- O
          would ---- O
           like ---- O
             to ---- O
           find ---- O
              a ---- O
         flight ---- O
           from ---- O
      charlotte ---- B-fromloc.city_name
             to ---- O
            las ---- B-toloc.city_name
          vegas ---- I-toloc.city_name
           that ---- O
          makes ---- O
              a ---- O
           stop ---- O
             in ---- O
            st. ---- B-stoploc.city_name
          louis ---- B-arrive_time.time_relative
            EOS ---- O


##### Test MultiThreadsEvaluation CPU device. #####

##### Run evaluation on CPU device with 2 parallel evaluation thread(s). #####

##### Run evaluation using new function on CPU. #####
thread 0 joined.
thread 1 joined.

##### Run evaluation using clone function on CPU. #####
Function 'classifierOutput': Input Variables (count=1)
    name=features, kind=0
Function 'classifierOutput': Output Variables (count=1)
    name=classifierOutput, kind=1
MultiThreadsEvaluationWithClone on device=0
Evaluation result:
Iteration:0, Sample 0:
    8.719499 -7.649824 1.461357 10.811009 1.258002 -4.332583 7.601730 -16.948837 -0.582021 2.418953 ...
Iteration:0, Sample 1:
    8.720922 -7.647464 1.459087 10.812464 1.261330 -4.335119 7.599889 -16.945734 -0.579114 2.423536 ...
Iteration:0, Sample 2:
    8.720100 -7.650048 1.464657 10.805371 1.262745 -4.333430 7.598026 -16.944080 -0.584620 2.424258 ...
Evaluation result:
Iteration:0, Sample 0:
    8.719499 -7.649824 1.461357 10.811009 1.258002 -4.332583 7.601730 -16.948837 -0.582021 2.418953 ...
Iteration:0, Sample 1:
    8.720922 -7.647464 1.459087 10.812464 1.261330 -4.335119 7.599889 -16.945734 -0.579114 2.423536 ...
Iteration:0, Sample 2:
    8.720100 -7.650048 1.464657 10.805371 1.262745 -4.333430 7.598026 -16.944080 -0.584620 2.424258 ...
Evaluation result:
Iteration:1, Sample 0:
    8.722195 -7.648002 1.462350 10.806680 1.262483 -4.338805 7.599278 -16.944553 -0.582074 2.421458 ...
Iteration:1, Sample 1:
    8.721126 -7.647966 1.461311 10.808912 1.260600 -4.335733 7.599218 -16.943220 -0.586526 2.423216 ...
Iteration:1, Sample 2:
    8.721636 -7.650586 1.460604 10.809491 1.258408 -4.334564 7.597913 -16.943571 -0.585630 2.419630 ...
Evaluation result:
Iteration:1, Sample 0:
    8.722195 -7.648002 1.462350 10.806680 1.262483 -4.338805 7.599278 -16.944553 -0.582074 2.421458 ...
Iteration:1, Sample 1:
    8.721126 -7.647966 1.461311 10.808912 1.260600 -4.335733 7.599218 -16.943220 -0.586526 2.423216 ...
Iteration:1, Sample 2:
    8.721636 -7.650586 1.460604 10.809491 1.258408 -4.334564 7.597913 -16.943571 -0.585630 2.419630 ...
Evaluation result:
Iteration:2, Sample 0:
    8.718333 -7.646465 1.462744 10.808577 1.257758 -4.337018 7.599608 -16.946207 -0.582566 2.423581 ...
Iteration:2, Sample 1:
    8.717912 -7.645286 1.460469 10.811042 1.261215 -4.332682 7.599174 -16.947752 -0.583365 2.425624 ...
Iteration:2, Sample 2:
    8.721033 -7.649396 1.462294 10.806743 1.261737 -4.334637 7.599154 -16.942791 -0.578653 2.420604 ...
Evaluation result:
Iteration:2, Sample 0:
    8.718333 -7.646465 1.462744 10.808577 1.257758 -4.337018 7.599608 -16.946207 -0.582566 2.423581 ...
Iteration:2, Sample 1:
    8.717912 -7.645286 1.460469 10.811042 1.261215 -4.332682 7.599174 -16.947752 -0.583365 2.425624 ...
Iteration:2, Sample 2:
    8.721033 -7.649396 1.462294 10.806743 1.261737 -4.334637 7.599154 -16.942791 -0.578653 2.420604 ...
Evaluation result:
Iteration:3, Sample 0:
    8.721188 -7.648074 1.462249 10.810592 1.259941 -4.337050 7.599345 -16.945051 -0.579847 2.421400 ...
Iteration:3, Sample 1:
    8.717767 -7.650074 1.461809 10.807857 1.261626 -4.334464 7.604057 -16.942709 -0.579220 2.419601 ...
Iteration:3, Sample 2:
    8.721833 -7.648919 1.460830 10.811456 1.260108 -4.334238 7.596704 -16.946079 -0.579708 2.423071 ...
thread 0 joined.
Evaluation result:
Iteration:3, Sample 0:
    8.721188 -7.648074 1.462249 10.810592 1.259941 -4.337050 7.599345 -16.945051 -0.579847 2.421400 ...
Iteration:3, Sample 1:
    8.717767 -7.650074 1.461809 10.807857 1.261626 -4.334464 7.604057 -16.942709 -0.579220 2.419601 ...
Iteration:3, Sample 2:
    8.721833 -7.648919 1.460830 10.811456 1.260108 -4.334238 7.596704 -16.946079 -0.579708 2.423071 ...
thread 1 joined.

##### Run evaluation using pre-trained model on CPU. #####
Function '': Input Variables (count=2)
    name=features, kind=0
    name=labels, kind=0
Function '': Output Variables (count=3)
    name=ce, kind=1
    name=errs, kind=1
    name=out.z, kind=1
MultiThreadsEvaluationWithLoadModel on device=0
Evaluation result:
Iteration:0, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:0, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:0, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
Evaluation result:
Iteration:1, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:1, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:1, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
Evaluation result:
Iteration:2, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:2, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:2, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 Evaluation result:
-7.863690 12.338904 -0.816265 -2.759349 3.292670 Iteration:0, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:0, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 1.272151 
11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:0, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
Evaluation result:
Iteration:3, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:3, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:3, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 Evaluation result:
-7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
Iteration:1, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:1, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:1, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
thread 0 joined.
Evaluation result:
Iteration:2, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:2, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:2, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
Evaluation result:
Iteration:3, Sample 0:
Output:-1.631962 -7.887448 1.684969 8.685357 -7.478977 9.775093 -6.652484 0.383906 2.626894 -2.976902 
Iteration:3, Sample 1:
Output:-2.957949 -7.711860 -2.918236 5.793887 -8.211493 11.805773 -2.283456 -2.504362 3.462196 0.227575 
Iteration:3, Sample 2:
Output:-4.195490 -8.739225 -3.749012 6.490619 -7.863690 12.338904 -0.816265 -2.759349 3.292670 1.272151 
thread 1 joined.

===== Evaluate intermediate layer =====
The batch contains 1 sequences.
Sequence 0 contains 1 samples.
    sample 0: 0.674033, 0.000000, 0.109044, 0.397623, 0.440187, 0.000000, 0.042737, 0.018471, 0.016952, 0.005611, 0.393881, 0.001275, 0.294192, 0.023059, 0.852816, 0.519126, 0.304926, 0.003931, 0.061081, 0.200880, 0.593306, 0.056079, 0.011282, 0.315629, 0.134917, 0.096884, 0.000000, 0.350360, 0.000000, 0.015231, 0.003045, 0.402462, 0.047899, 0.625825, 0.000000, 0.000000, 0.000000, 0.151889, 0.185796, 0.000000, 0.023398, 0.043338, 0.123514, 0.000000, 0.000000, 0.000000, 0.001660, 0.029734, 0.208211, 0.265516, 0.011518, 0.056297, 0.225230, 0.000000, 0.000000, 0.452441, 0.171762, 0.509325, 0.328891, 0.244234, 0.011638, 0.026650, 0.496360, 0.000000.

===== Evaluate combined outputs =====
The batch contains 1 sequences.
Sequence 0 contains 1 samples.
    sample 0: 2.784544, 2.258028, -0.253707, 2.223094, -3.174539, -1.431938, -1.481088, -3.174907, 1.350909, 0.903016.
The batch contains 1 sequences.
Sequence 0 contains 1 samples.
    sample 0: 0.674033, 0.000000, 0.109044, 0.397623, 0.440187, 0.000000, 0.042737, 0.018471, 0.016952, 0.005611, 0.393881, 0.001275, 0.294192, 0.023059, 0.852816, 0.519126, 0.304926, 0.003931, 0.061081, 0.200880, 0.593306, 0.056079, 0.011282, 0.315629, 0.134917, 0.096884, 0.000000, 0.350360, 0.000000, 0.015231, 0.003045, 0.402462, 0.047899, 0.625825, 0.000000, 0.000000, 0.000000, 0.151889, 0.185796, 0.000000, 0.023398, 0.043338, 0.123514, 0.000000, 0.000000, 0.000000, 0.001660, 0.029734, 0.208211, 0.265516, 0.011518, 0.056297, 0.225230, 0.000000, 0.000000, 0.452441, 0.171762, 0.509325, 0.328891, 0.244234, 0.011638, 0.026650, 0.496360, 0.000000.
Evaluation complete.
+ ExitCode=0
+ popd
/cygdrive/c/repos/ThirdCNTK/Tests/EndToEndTests/EvalClientTests/CNTKLibraryCPPEvalExamplesTest
+ rm -rf /tmp/cntk-test-20170907134534.169127/EvalClientTests_CNTKLibraryCPPEvalExamplesTest@release_cpu/TestData
+ exit 0