annotate testdata/evaluation/outputs/piano-b5a8836dd2a4-flatten-0.05.txt @ 237:5ec1da7ffd58 norm

More rms levels

Yeti 0.9.9+
1.0
make -C constant-q-cpp -f Makefile.linux libcq.a
make[1]: Entering directory '/home/cannam/code/silvet/constant-q-cpp'
make[1]: 'libcq.a' is up to date.
make[1]: Leaving directory '/home/cannam/code/silvet/constant-q-cpp'
make -C flattendynamics -f Makefile flattendynamics.so
make[1]: Entering directory '/home/cannam/code/silvet/flattendynamics'
g++ -DLADSPA -fpic -g   -c -o flattendynamics-ladspa.o flattendynamics-ladspa.cpp
g++ flattendynamics-ladspa.o -DLADSPA -fpic -g -shared -o flattendynamics.so
make[1]: Leaving directory '/home/cannam/code/silvet/flattendynamics'
g++ -Wall -O3 -fopenmp -ffast-math -msse -msse2 -mfpmath=sse -ftree-vectorize -fPIC -I../vamp-plugin-sdk/ -DUSE_PTHREADS -I. -I../vamp-plugin-sdk -Iconstant-q-cpp -Ibqvec/src -Wall -O3 -fopenmp -ffast-math -msse -msse2 -mfpmath=sse -ftree-vectorize -fPIC -I../vamp-plugin-sdk/ -DUSE_PTHREADS   -c -o src/Silvet.o src/Silvet.cpp
g++ -Wall -O3 -fopenmp -ffast-math -msse -msse2 -mfpmath=sse -ftree-vectorize -fPIC -I../vamp-plugin-sdk/ -DUSE_PTHREADS -I. -I../vamp-plugin-sdk -Iconstant-q-cpp -Ibqvec/src -Wall -O3 -fopenmp -ffast-math -msse -msse2 -mfpmath=sse -ftree-vectorize -fPIC -I../vamp-plugin-sdk/ -DUSE_PTHREADS   -c -o src/libmain.o src/libmain.cpp
g++ -o silvet.so src/Silvet.o src/EM.o src/Instruments.o src/libmain.o bqvec/src/Allocators.o constant-q-cpp/libcq.a ../vamp-plugin-sdk/libvamp-sdk.a constant-q-cpp/libcq.a ../vamp-plugin-sdk/libvamp-sdk.a   -lgomp -shared -Wl,-Bsymbolic -Wl,-z,defs -Wl,--version-script=vamp-plugin.map -lpthread

Input files are:
/home/cannam/Music/piano_small_dataset/MAPS_MUS-bach_846_AkPnBcht.wav
/home/cannam/Music/piano_small_dataset/31.wav
/home/cannam/Music/piano_small_dataset/MAPS_MUS-scn15_7_SptkBGAm.wav
/home/cannam/Music/piano_small_dataset/mz_333_1MINp_align.wav
/home/cannam/Music/piano_small_dataset/MAPS_MUS-chpn_op7_1_ENSTDkAm.wav

Evaluating for file /home/cannam/Music/piano_small_dataset/MAPS_MUS-bach_846_AkPnBcht.wav...

For file MAPS_MUS-bach_846_AkPnBcht, instrument 1, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 97.4, recall 77.8, accuracy 76.3, F 86.5  <-- main piano preset for MAPS_MUS-bach_846_AkPnBcht (norm = no)

Validating against ground truth at 100 ms:
precision 97.4, recall 77.8, accuracy 76.3, F 86.5

Validating against ground truth at 150 ms:
precision 98.3, recall 78.5, accuracy 77.4, F 87.3


For file MAPS_MUS-bach_846_AkPnBcht, instrument 1, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 95, recall 77.8, accuracy 74.8, F 85.6  <-- main piano preset for MAPS_MUS-bach_846_AkPnBcht (norm = yes)

Validating against ground truth at 100 ms:
precision 97.5, recall 79.8, accuracy 78.2, F 87.8

Validating against ground truth at 150 ms:
precision 97.5, recall 79.8, accuracy 78.2, F 87.8


For file MAPS_MUS-bach_846_AkPnBcht, instrument 0, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 98.2, recall 75.8, accuracy 74.8, F 85.6  <-- main generic preset for MAPS_MUS-bach_846_AkPnBcht (norm = no)

Validating against ground truth at 100 ms:
precision 99.1, recall 76.5, accuracy 76, F 86.3

Validating against ground truth at 150 ms:
precision 99.1, recall 76.5, accuracy 76, F 86.3


For file MAPS_MUS-bach_846_AkPnBcht, instrument 0, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 86.8, recall 71.1, accuracy 64.2, F 78.2  <-- main generic preset for MAPS_MUS-bach_846_AkPnBcht (norm = yes)

Validating against ground truth at 100 ms:
precision 92.6, recall 75.8, accuracy 71.5, F 83.3

Validating against ground truth at 150 ms:
precision 93.4, recall 76.5, accuracy 72.6, F 84.1


Evaluating for file /home/cannam/Music/piano_small_dataset/31.wav...

For file 31, instrument 1, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 54, recall 38.8, accuracy 29.1, F 45.1  <-- main piano preset for 31 (norm = no)

Validating against ground truth at 100 ms:
precision 75, recall 53.9, accuracy 45.7, F 62.7

Validating against ground truth at 150 ms:
precision 80, recall 57.5, accuracy 50.3, F 66.9


For file 31, instrument 1, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 60.6, recall 43.1, accuracy 33.7, F 50.4  <-- main piano preset for 31 (norm = yes)

Validating against ground truth at 100 ms:
precision 76.7, recall 54.6, accuracy 46.9, F 63.8

Validating against ground truth at 150 ms:
precision 81.8, recall 58.2, accuracy 51.5, F 68


For file 31, instrument 0, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 52.6, recall 42.4, accuracy 30.7, F 47  <-- main generic preset for 31 (norm = no)

Validating against ground truth at 100 ms:
precision 66, recall 53.2, accuracy 41.8, F 58.9

Validating against ground truth at 150 ms:
precision 72.3, recall 58.2, accuracy 47.6, F 64.5


For file 31, instrument 0, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 57.4, recall 44.6, accuracy 33.5, F 50.2  <-- main generic preset for 31 (norm = yes)

Validating against ground truth at 100 ms:
precision 71.2, recall 55.3, accuracy 45.2, F 62.3

Validating against ground truth at 150 ms:
precision 79.6, recall 61.8, accuracy 53.4, F 69.6


Evaluating for file /home/cannam/Music/piano_small_dataset/MAPS_MUS-scn15_7_SptkBGAm.wav...

For file MAPS_MUS-scn15_7_SptkBGAm, instrument 1, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 71.6, recall 76, accuracy 58.4, F 73.7  <-- main piano preset for MAPS_MUS-scn15_7_SptkBGAm (norm = no)

Validating against ground truth at 100 ms:
precision 77.3, recall 82, accuracy 66.1, F 79.6

Validating against ground truth at 150 ms:
precision 77.3, recall 82, accuracy 66.1, F 79.6


For file MAPS_MUS-scn15_7_SptkBGAm, instrument 1, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 65.2, recall 77, accuracy 54.6, F 70.6  <-- main piano preset for MAPS_MUS-scn15_7_SptkBGAm (norm = yes)

Validating against ground truth at 100 ms:
precision 67.7, recall 80, accuracy 57.9, F 73.3

Validating against ground truth at 150 ms:
precision 70.3, recall 83, accuracy 61.4, F 76.1


For file MAPS_MUS-scn15_7_SptkBGAm, instrument 0, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 61.2, recall 71, accuracy 48.9, F 65.7  <-- main generic preset for MAPS_MUS-scn15_7_SptkBGAm (norm = no)

Validating against ground truth at 100 ms:
precision 67.2, recall 78, accuracy 56.5, F 72.2

Validating against ground truth at 150 ms:
precision 69.8, recall 81, accuracy 60, F 75


For file MAPS_MUS-scn15_7_SptkBGAm, instrument 0, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 58.7, recall 77, accuracy 50, F 66.6  <-- main generic preset for MAPS_MUS-scn15_7_SptkBGAm (norm = yes)

Validating against ground truth at 100 ms:
precision 62.5, recall 82, accuracy 55, F 70.9

Validating against ground truth at 150 ms:
precision 67.1, recall 88, accuracy 61.5, F 76.1


Evaluating for file /home/cannam/Music/piano_small_dataset/mz_333_1MINp_align.wav...

For file mz_333_1MINp_align, instrument 1, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 1 from file
Taking default sample rate of 8000Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 8000
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 1ch at 8000Hz

Extracting and writing features... 6%
Extracting and writing features... 13%
Extracting and writing features... 20%
Extracting and writing features... 27%
Extracting and writing features... 34%
Extracting and writing features... 41%
Extracting and writing features... 47%
Extracting and writing features... 54%
Extracting and writing features... 61%
Extracting and writing features... 68%
Extracting and writing features... 75%
Extracting and writing features... 82%
Extracting and writing features... 88%
Extracting and writing features... 95%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 62.2, recall 69.9, accuracy 49, F 65.8  <-- main piano preset for mz_333_1MINp_align (norm = no)

Validating against ground truth at 100 ms:
precision 72, recall 81, accuracy 61.6, F 76.3

Validating against ground truth at 150 ms:
precision 74.4, recall 83.6, accuracy 64.9, F 78.7


For file mz_333_1MINp_align, instrument 1, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 1 from file
Taking default sample rate of 8000Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 8000
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 1ch at 8000Hz

Extracting and writing features... 6%
Extracting and writing features... 13%
Extracting and writing features... 20%
Extracting and writing features... 27%
Extracting and writing features... 34%
Extracting and writing features... 41%
Extracting and writing features... 47%
Extracting and writing features... 54%
Extracting and writing features... 61%
Extracting and writing features... 68%
Extracting and writing features... 75%
Extracting and writing features... 82%
Extracting and writing features... 88%
Extracting and writing features... 95%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 64, recall 68.6, accuracy 49.5, F 66.2  <-- main piano preset for mz_333_1MINp_align (norm = yes)

Validating against ground truth at 100 ms:
precision 73.7, recall 79, accuracy 61.7, F 76.3

Validating against ground truth at 150 ms:
precision 76.2, recall 81.6, accuracy 65.1, F 78.8


For file mz_333_1MINp_align, instrument 0, norm no...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 1 from file
Taking default sample rate of 8000Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 8000
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 1ch at 8000Hz

Extracting and writing features... 6%
Extracting and writing features... 13%
Extracting and writing features... 20%
Extracting and writing features... 27%
Extracting and writing features... 34%
Extracting and writing features... 41%
Extracting and writing features... 47%
Extracting and writing features... 54%
Extracting and writing features... 61%
Extracting and writing features... 68%
Extracting and writing features... 75%
Extracting and writing features... 82%
Extracting and writing features... 88%
Extracting and writing features... 95%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 66, recall 68.6, accuracy 50.7, F 67.3  <-- main generic preset for mz_333_1MINp_align (norm = no)

Validating against ground truth at 100 ms:
precision 74.8, recall 77.7, accuracy 61.6, F 76.2

Validating against ground truth at 150 ms:
precision 78.6, recall 81.6, accuracy 66.8, F 80.1


For file mz_333_1MINp_align, instrument 0, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 1 from file
Taking default sample rate of 8000Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 8000
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 1ch at 8000Hz

Extracting and writing features... 6%
Extracting and writing features... 13%
Extracting and writing features... 20%
Extracting and writing features... 27%
Extracting and writing features... 34%
Extracting and writing features... 41%
Extracting and writing features... 47%
Extracting and writing features... 54%
Extracting and writing features... 61%
Extracting and writing features... 68%
Extracting and writing features... 75%
Extracting and writing features... 82%
Extracting and writing features... 88%
Extracting and writing features... 95%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 62.5, recall 63.3, accuracy 45.9, F 62.9  <-- main generic preset for mz_333_1MINp_align (norm = yes)

Validating against ground truth at 100 ms:
precision 76.1, recall 77.1, accuracy 62.1, F 76.6

Validating against ground truth at 150 ms:
precision 78.7, recall 79.7, accuracy 65.5, F 79.2


Evaluating for file /home/cannam/Music/piano_small_dataset/MAPS_MUS-chpn_op7_1_ENSTDkAm.wav...

For file MAPS_MUS-chpn_op7_1_ENSTDkAm, instrument 1, norm no...
sox WARN dither: dither clipped 94 samples; decrease volume?
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 42.1, recall 25.4, accuracy 18.8, F 31.7  <-- main piano preset for MAPS_MUS-chpn_op7_1_ENSTDkAm (norm = no)

Validating against ground truth at 100 ms:
precision 67.8, recall 40.9, accuracy 34.3, F 51.1

Validating against ground truth at 150 ms:
precision 74.2, recall 44.8, accuracy 38.8, F 55.9


For file MAPS_MUS-chpn_op7_1_ENSTDkAm, instrument 1, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="1"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 39.1, recall 26.8, accuracy 18.9, F 31.8  <-- main piano preset for MAPS_MUS-chpn_op7_1_ENSTDkAm (norm = yes)

Validating against ground truth at 100 ms:
precision 65.9, recall 45.2, accuracy 36.6, F 53.6

Validating against ground truth at 150 ms:
precision 71.6, recall 49.1, accuracy 41.1, F 58.2


For file MAPS_MUS-chpn_op7_1_ENSTDkAm, instrument 0, norm no...
sox WARN dither: dither clipped 89 samples; decrease volume?
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 36.6, recall 23.6, accuracy 16.7, F 28.7  <-- main generic preset for MAPS_MUS-chpn_op7_1_ENSTDkAm (norm = no)

Validating against ground truth at 100 ms:
precision 61.2, recall 39.5, accuracy 31.6, F 48

Validating against ground truth at 150 ms:
precision 66.1, recall 42.7, accuracy 35, F 51.9


For file MAPS_MUS-chpn_op7_1_ENSTDkAm, instrument 0, norm yes...
force -> 
one-file -> /tmp/4813
Have audio source: "/tmp/4813.wav"

Determining default rate and channel count from first input file... Done
File or URL "/tmp/4813.wav" opened successfully
Taking default channel count of 2 from file
Taking default sample rate of 44100Hz from file
(Note: Default may be overridden by transforms)
Duplicate statement encountered on import in ImportFailOnDuplicates mode [with triple <( <http://vamp-plugins.org/rdf/plugins/silvet#library> <http://purl.org/ontology/vamp/available_plugin> <http://vamp-plugins.org/rdf/plugins/silvet#silvet> )>]
PluginRDFIndexer::pullURL: Document at file:///home/cannam/code/silvet/silvet2.n3 duplicates triples found in earlier loaded document -- skipping it
RDFTransformFactory: NOTE: Transform is: 
<transform
    id="vamp:silvet:silvet:"
    pluginVersion=""
    program=""
    stepSize="1024"
    blockSize="1024"
    windowType="hanning"
    startTime="0.000000000"
    duration="0.000000000"
    sampleRate="0">
  <parameter name="finetune" value="0"/>
  <parameter name="instrument" value="0"/>
  <parameter name="mode" value="1"/>
</transform>

NOTE: Transform does not specify a sample rate, using default rate of 44100
NOTE: Loaded and initialised plugin for transform "vamp:silvet:silvet:" with plugin step size 1024 and block size 1024 (adapter step and block size 16384)
Extracting features for: "/tmp/4813.wav"
Audio file "/tmp/4813.wav": 2ch at 44100Hz

Extracting and writing features... 1%
Extracting and writing features... 2%
Extracting and writing features... 3%
Extracting and writing features... 5%
Extracting and writing features... 6%
Extracting and writing features... 7%
Extracting and writing features... 8%
Extracting and writing features... 10%
Extracting and writing features... 11%
Extracting and writing features... 12%
Extracting and writing features... 13%
Extracting and writing features... 14%
Extracting and writing features... 16%
Extracting and writing features... 17%
Extracting and writing features... 18%
Extracting and writing features... 19%
Extracting and writing features... 21%
Extracting and writing features... 22%
Extracting and writing features... 23%
Extracting and writing features... 24%
Extracting and writing features... 26%
Extracting and writing features... 27%
Extracting and writing features... 28%
Extracting and writing features... 29%
Extracting and writing features... 31%
Extracting and writing features... 32%
Extracting and writing features... 33%
Extracting and writing features... 34%
Extracting and writing features... 36%
Extracting and writing features... 37%
Extracting and writing features... 38%
Extracting and writing features... 39%
Extracting and writing features... 40%
Extracting and writing features... 42%
Extracting and writing features... 43%
Extracting and writing features... 44%
Extracting and writing features... 45%
Extracting and writing features... 47%
Extracting and writing features... 48%
Extracting and writing features... 49%
Extracting and writing features... 50%
Extracting and writing features... 52%
Extracting and writing features... 53%
Extracting and writing features... 54%
Extracting and writing features... 55%
Extracting and writing features... 57%
Extracting and writing features... 58%
Extracting and writing features... 59%
Extracting and writing features... 60%
Extracting and writing features... 62%
Extracting and writing features... 63%
Extracting and writing features... 64%
Extracting and writing features... 65%
Extracting and writing features... 66%
Extracting and writing features... 68%
Extracting and writing features... 69%
Extracting and writing features... 70%
Extracting and writing features... 71%
Extracting and writing features... 73%
Extracting and writing features... 74%
Extracting and writing features... 75%
Extracting and writing features... 76%
Extracting and writing features... 78%
Extracting and writing features... 79%
Extracting and writing features... 80%
Extracting and writing features... 81%
Extracting and writing features... 83%
Extracting and writing features... 84%
Extracting and writing features... 85%
Extracting and writing features... 86%
Extracting and writing features... 88%
Extracting and writing features... 89%
Extracting and writing features... 90%
Extracting and writing features... 91%
Extracting and writing features... 92%
Extracting and writing features... 94%
Extracting and writing features... 95%
Extracting and writing features... 96%
Extracting and writing features... 97%
Extracting and writing features... 99%
Extracting and writing features... Done


Validating against ground truth at 50 ms:
precision 35.3, recall 26.5, accuracy 17.8, F 30.3  <-- main generic preset for MAPS_MUS-chpn_op7_1_ENSTDkAm (norm = yes)

Validating against ground truth at 100 ms:
precision 60.8, recall 45.5, accuracy 35.2, F 52.1

Validating against ground truth at 150 ms:
precision 66.5, recall 49.8, accuracy 39.8, F 56.9


real	37m47.601s
user	47m47.226s
sys	1m53.113s