To check out this repository please hg clone the following URL, or open the URL using EasyMercurial or your preferred Mercurial client.
root / Vamp.ipynb @ 9:1171de1838d7
History | View | Annotate | Download (74.2 KB)
| 1 |
{
|
|---|---|
| 2 |
"cells": [ |
| 3 |
{
|
| 4 |
"cell_type": "markdown", |
| 5 |
"metadata": {},
|
| 6 |
"source": [ |
| 7 |
"# Using Vamp plugins from Python\n", |
| 8 |
"This notebook illustrates processing an audio file using a Vamp plugin, showing the results in a simple plot, and saving to a .csv file. This could be useful when integrating with analysis software written in Python, or for a batch process. (Note that it is also possible to run Vamp plugins in batch using the [Sonic Annotator](http://vamp-plugins.org/sonic-annotator) command-line program.)" |
| 9 |
] |
| 10 |
}, |
| 11 |
{
|
| 12 |
"cell_type": "markdown", |
| 13 |
"metadata": {},
|
| 14 |
"source": [ |
| 15 |
"### Setup\n", |
| 16 |
"\n", |
| 17 |
"First we import some necessary modules.\n", |
| 18 |
"\n", |
| 19 |
"The `vamp` module loads and runs Vamp plugins. `librosa` is an audio analysis module from LabROSA at Columbia University. We are using it here only to load audio files, though it can also carry out some analysis functions. `matplotlib` is the usual plotting library." |
| 20 |
] |
| 21 |
}, |
| 22 |
{
|
| 23 |
"cell_type": "code", |
| 24 |
"execution_count": 1, |
| 25 |
"metadata": {
|
| 26 |
"collapsed": false |
| 27 |
}, |
| 28 |
"outputs": [ |
| 29 |
{
|
| 30 |
"name": "stderr", |
| 31 |
"output_type": "stream", |
| 32 |
"text": [ |
| 33 |
"/usr/lib/python2.7/site-packages/librosa/core/audio.py:33: UserWarning: Could not import scikits.samplerate. Falling back to scipy.signal\n", |
| 34 |
" warnings.warn('Could not import scikits.samplerate. '\n"
|
| 35 |
] |
| 36 |
} |
| 37 |
], |
| 38 |
"source": [ |
| 39 |
"import vamp\n", |
| 40 |
"import librosa\n", |
| 41 |
"import matplotlib.pyplot as plt\n", |
| 42 |
"%matplotlib inline" |
| 43 |
] |
| 44 |
}, |
| 45 |
{
|
| 46 |
"cell_type": "markdown", |
| 47 |
"metadata": {},
|
| 48 |
"source": [ |
| 49 |
"### Getting started with the Vamp module\n", |
| 50 |
"\n", |
| 51 |
"List the plugins that are installed. The strings that are returned here are referred to in the module documentation as _plugin keys_ -- each one consists of the name of the library file that contains the plugin, then a colon, then the identifier for the plugin itself. So a set of plugins with the same text before the colon (such as `qm-vamp-plugins:`) were all distributed in the same plugin library file.\n", |
| 52 |
"\n", |
| 53 |
"You can find plugin descriptions and downloads at http://vamp-plugins.org/download.html." |
| 54 |
] |
| 55 |
}, |
| 56 |
{
|
| 57 |
"cell_type": "code", |
| 58 |
"execution_count": 2, |
| 59 |
"metadata": {
|
| 60 |
"collapsed": false |
| 61 |
}, |
| 62 |
"outputs": [ |
| 63 |
{
|
| 64 |
"data": {
|
| 65 |
"text/plain": [ |
| 66 |
"['bbc-vamp-plugins:bbc-energy',\n", |
| 67 |
" 'bbc-vamp-plugins:bbc-intensity',\n", |
| 68 |
" 'bbc-vamp-plugins:bbc-peaks',\n", |
| 69 |
" 'bbc-vamp-plugins:bbc-rhythm',\n", |
| 70 |
" 'bbc-vamp-plugins:bbc-spectral-contrast',\n", |
| 71 |
" 'bbc-vamp-plugins:bbc-spectral-flux',\n", |
| 72 |
" 'bbc-vamp-plugins:bbc-speechmusic-segmenter',\n", |
| 73 |
" 'cepstral-pitchtracker:cepstral-pitchtracker',\n", |
| 74 |
" 'chp:constrainedharmonicpeak',\n", |
| 75 |
" 'cqvamp:cqchromavamp',\n", |
| 76 |
" 'cqvamp:cqvamp',\n", |
| 77 |
" 'cqvamp:cqvampmidi',\n", |
| 78 |
" 'match-vamp-plugin:match',\n", |
| 79 |
" 'nnls-chroma:chordino',\n", |
| 80 |
" 'nnls-chroma:nnls-chroma',\n", |
| 81 |
" 'nnls-chroma:tuning',\n", |
| 82 |
" 'pyin:localcandidatepyin',\n", |
| 83 |
" 'pyin:pyin',\n", |
| 84 |
" 'pyin:yin',\n", |
| 85 |
" 'pyin:yinfc',\n", |
| 86 |
" 'qm-vamp-plugins:qm-adaptivespectrogram',\n", |
| 87 |
" 'qm-vamp-plugins:qm-barbeattracker',\n", |
| 88 |
" 'qm-vamp-plugins:qm-chromagram',\n", |
| 89 |
" 'qm-vamp-plugins:qm-constantq',\n", |
| 90 |
" 'qm-vamp-plugins:qm-dwt',\n", |
| 91 |
" 'qm-vamp-plugins:qm-keydetector',\n", |
| 92 |
" 'qm-vamp-plugins:qm-mfcc',\n", |
| 93 |
" 'qm-vamp-plugins:qm-onsetdetector',\n", |
| 94 |
" 'qm-vamp-plugins:qm-segmenter',\n", |
| 95 |
" 'qm-vamp-plugins:qm-similarity',\n", |
| 96 |
" 'qm-vamp-plugins:qm-tempotracker',\n", |
| 97 |
" 'qm-vamp-plugins:qm-tonalchange',\n", |
| 98 |
" 'qm-vamp-plugins:qm-transcription',\n", |
| 99 |
" 'segmentino:segmentino',\n", |
| 100 |
" 'silvet:silvet',\n", |
| 101 |
" 'simple-cepstrum:simple-cepstrum',\n", |
| 102 |
" 'tempogram:tempogram',\n", |
| 103 |
" 'vamp-aubio:aubionotes',\n", |
| 104 |
" 'vamp-aubio:aubioonset',\n", |
| 105 |
" 'vamp-aubio:aubiopitch',\n", |
| 106 |
" 'vamp-aubio:aubiosilence',\n", |
| 107 |
" 'vamp-aubio:aubiotempo',\n", |
| 108 |
" 'vamp-example-plugins:amplitudefollower',\n", |
| 109 |
" 'vamp-example-plugins:fixedtempo',\n", |
| 110 |
" 'vamp-example-plugins:percussiononsets',\n", |
| 111 |
" 'vamp-example-plugins:powerspectrum',\n", |
| 112 |
" 'vamp-example-plugins:spectralcentroid',\n", |
| 113 |
" 'vamp-example-plugins:zerocrossing',\n", |
| 114 |
" 'vamp-libxtract:amdf',\n", |
| 115 |
" 'vamp-libxtract:asdf',\n", |
| 116 |
" 'vamp-libxtract:autocorrelation',\n", |
| 117 |
" 'vamp-libxtract:average_deviation',\n", |
| 118 |
" 'vamp-libxtract:bark_coefficients',\n", |
| 119 |
" 'vamp-libxtract:crest',\n", |
| 120 |
" 'vamp-libxtract:dct',\n", |
| 121 |
" 'vamp-libxtract:f0',\n", |
| 122 |
" 'vamp-libxtract:failsafe_f0',\n", |
| 123 |
" 'vamp-libxtract:flatness',\n", |
| 124 |
" 'vamp-libxtract:harmonic_spectrum',\n", |
| 125 |
" 'vamp-libxtract:highest_value',\n", |
| 126 |
" 'vamp-libxtract:irregularity_j',\n", |
| 127 |
" 'vamp-libxtract:irregularity_k',\n", |
| 128 |
" 'vamp-libxtract:kurtosis',\n", |
| 129 |
" 'vamp-libxtract:loudness',\n", |
| 130 |
" 'vamp-libxtract:lowest_value',\n", |
| 131 |
" 'vamp-libxtract:mean',\n", |
| 132 |
" 'vamp-libxtract:mfcc',\n", |
| 133 |
" 'vamp-libxtract:noisiness',\n", |
| 134 |
" 'vamp-libxtract:nonzero_count',\n", |
| 135 |
" 'vamp-libxtract:odd_even_ratio',\n", |
| 136 |
" 'vamp-libxtract:peak_spectrum',\n", |
| 137 |
" 'vamp-libxtract:rms_amplitude',\n", |
| 138 |
" 'vamp-libxtract:rolloff',\n", |
| 139 |
" 'vamp-libxtract:sharpness',\n", |
| 140 |
" 'vamp-libxtract:skewness',\n", |
| 141 |
" 'vamp-libxtract:smoothness',\n", |
| 142 |
" 'vamp-libxtract:spectral_centroid',\n", |
| 143 |
" 'vamp-libxtract:spectral_inharmonicity',\n", |
| 144 |
" 'vamp-libxtract:spectral_kurtosis',\n", |
| 145 |
" 'vamp-libxtract:spectral_skewness',\n", |
| 146 |
" 'vamp-libxtract:spectral_slope',\n", |
| 147 |
" 'vamp-libxtract:spectral_standard_deviation',\n", |
| 148 |
" 'vamp-libxtract:spectral_variance',\n", |
| 149 |
" 'vamp-libxtract:spectrum',\n", |
| 150 |
" 'vamp-libxtract:spread',\n", |
| 151 |
" 'vamp-libxtract:standard_deviation',\n", |
| 152 |
" 'vamp-libxtract:sum',\n", |
| 153 |
" 'vamp-libxtract:tonality',\n", |
| 154 |
" 'vamp-libxtract:tristimulus_1',\n", |
| 155 |
" 'vamp-libxtract:tristimulus_2',\n", |
| 156 |
" 'vamp-libxtract:tristimulus_3',\n", |
| 157 |
" 'vamp-libxtract:variance',\n", |
| 158 |
" 'vamp-libxtract:zcr',\n", |
| 159 |
" 'vamp-rubberband:rubberband',\n", |
| 160 |
" 'vamp-test-plugin:vamp-test-plugin',\n", |
| 161 |
" 'vamp-test-plugin:vamp-test-plugin-freq']" |
| 162 |
] |
| 163 |
}, |
| 164 |
"execution_count": 2, |
| 165 |
"metadata": {},
|
| 166 |
"output_type": "execute_result" |
| 167 |
} |
| 168 |
], |
| 169 |
"source": [ |
| 170 |
"vamp.list_plugins()" |
| 171 |
] |
| 172 |
}, |
| 173 |
{
|
| 174 |
"cell_type": "markdown", |
| 175 |
"metadata": {},
|
| 176 |
"source": [ |
| 177 |
"We'll be using the `librosa` module's `load` function to load the audio file. IPython will show documentation about a function if you just give its name with a \"?\" at the end." |
| 178 |
] |
| 179 |
}, |
| 180 |
{
|
| 181 |
"cell_type": "code", |
| 182 |
"execution_count": 3, |
| 183 |
"metadata": {
|
| 184 |
"collapsed": true |
| 185 |
}, |
| 186 |
"outputs": [], |
| 187 |
"source": [ |
| 188 |
"librosa.load?" |
| 189 |
] |
| 190 |
}, |
| 191 |
{
|
| 192 |
"cell_type": "markdown", |
| 193 |
"metadata": {},
|
| 194 |
"source": [ |
| 195 |
"And the main high-level Vamp module function to apply a plugin is called `collect`, because it runs a plugin and collects the results into a suitable structure rather than returning them individually." |
| 196 |
] |
| 197 |
}, |
| 198 |
{
|
| 199 |
"cell_type": "code", |
| 200 |
"execution_count": 4, |
| 201 |
"metadata": {
|
| 202 |
"collapsed": true |
| 203 |
}, |
| 204 |
"outputs": [], |
| 205 |
"source": [ |
| 206 |
"vamp.collect?" |
| 207 |
] |
| 208 |
}, |
| 209 |
{
|
| 210 |
"cell_type": "markdown", |
| 211 |
"metadata": {},
|
| 212 |
"source": [ |
| 213 |
"### Extracting some chroma features\n", |
| 214 |
"\n", |
| 215 |
"Load our simplest test audio file and assign the sample data to `data` and the sampling rate to `rate`." |
| 216 |
] |
| 217 |
}, |
| 218 |
{
|
| 219 |
"cell_type": "code", |
| 220 |
"execution_count": 5, |
| 221 |
"metadata": {
|
| 222 |
"collapsed": false |
| 223 |
}, |
| 224 |
"outputs": [], |
| 225 |
"source": [ |
| 226 |
"data, rate = librosa.load(\"data/piano-scale.wav\")" |
| 227 |
] |
| 228 |
}, |
| 229 |
{
|
| 230 |
"cell_type": "markdown", |
| 231 |
"metadata": {},
|
| 232 |
"source": [ |
| 233 |
"`librosa` defaults to mixing audio down to mono and resampling it to 22050 Hz. (The original file here was 44.1kHz.)" |
| 234 |
] |
| 235 |
}, |
| 236 |
{
|
| 237 |
"cell_type": "code", |
| 238 |
"execution_count": 6, |
| 239 |
"metadata": {
|
| 240 |
"collapsed": false |
| 241 |
}, |
| 242 |
"outputs": [ |
| 243 |
{
|
| 244 |
"data": {
|
| 245 |
"text/plain": [ |
| 246 |
"22050" |
| 247 |
] |
| 248 |
}, |
| 249 |
"execution_count": 6, |
| 250 |
"metadata": {},
|
| 251 |
"output_type": "execute_result" |
| 252 |
} |
| 253 |
], |
| 254 |
"source": [ |
| 255 |
"rate" |
| 256 |
] |
| 257 |
}, |
| 258 |
{
|
| 259 |
"cell_type": "markdown", |
| 260 |
"metadata": {},
|
| 261 |
"source": [ |
| 262 |
"Run the `nnls-chroma` Chromagram plugin with some predefined parameters that make the output better suited to this type of sung performance." |
| 263 |
] |
| 264 |
}, |
| 265 |
{
|
| 266 |
"cell_type": "code", |
| 267 |
"execution_count": 7, |
| 268 |
"metadata": {
|
| 269 |
"collapsed": true |
| 270 |
}, |
| 271 |
"outputs": [], |
| 272 |
"source": [ |
| 273 |
"plugin_params = { \"tuningmode\": 1, \"s\": 0.9, \"chromanormalize\": 3 }\n",
|
| 274 |
"out = vamp.collect(data, rate,\n", |
| 275 |
" \"nnls-chroma:nnls-chroma\",\n", |
| 276 |
" output = \"chroma\",\n", |
| 277 |
" parameters = plugin_params,\n", |
| 278 |
" process_timestamp_method = vamp.vampyhost.SHIFT_DATA)" |
| 279 |
] |
| 280 |
}, |
| 281 |
{
|
| 282 |
"cell_type": "markdown", |
| 283 |
"metadata": {},
|
| 284 |
"source": [ |
| 285 |
"Because the output is grid-like, it comes back in a dictionary element labelled `matrix`. (Other types of features might appear in elements keyed `list` or `vector`.)" |
| 286 |
] |
| 287 |
}, |
| 288 |
{
|
| 289 |
"cell_type": "code", |
| 290 |
"execution_count": 8, |
| 291 |
"metadata": {
|
| 292 |
"collapsed": false |
| 293 |
}, |
| 294 |
"outputs": [ |
| 295 |
{
|
| 296 |
"data": {
|
| 297 |
"text/plain": [ |
| 298 |
"{'matrix': ( 0.092879819,\n",
|
| 299 |
" array([[ 0.00000000e+00, 3.95574346e-02, 1.29732716e-05,\n", |
| 300 |
" 9.80210781e-01, 9.58022848e-03, 0.00000000e+00,\n", |
| 301 |
" 0.00000000e+00, 1.64232314e-01, 9.96426120e-02,\n", |
| 302 |
" 0.00000000e+00, 2.50873379e-02, 0.00000000e+00],\n", |
| 303 |
" [ 0.00000000e+00, 3.14951129e-02, 1.80668838e-04,\n", |
| 304 |
" 9.78162169e-01, 3.25743221e-02, 0.00000000e+00,\n", |
| 305 |
" 2.29330850e-03, 1.62046552e-01, 1.21343270e-01,\n", |
| 306 |
" 0.00000000e+00, 1.25381378e-02, 0.00000000e+00],\n", |
| 307 |
" [ 0.00000000e+00, 3.00429221e-02, 1.06590232e-04,\n", |
| 308 |
" 9.80653524e-01, 1.40791936e-02, 0.00000000e+00,\n", |
| 309 |
" 9.71607305e-03, 1.61771417e-01, 1.04309380e-01,\n", |
| 310 |
" 0.00000000e+00, 8.54655821e-03, 0.00000000e+00],\n", |
| 311 |
" [ 5.58154285e-02, 2.38421746e-02, 2.34732070e-04,\n", |
| 312 |
" 9.85957980e-01, 0.00000000e+00, 8.80511070e-04,\n", |
| 313 |
" 1.73822697e-02, 1.46616176e-01, 2.19904333e-02,\n", |
| 314 |
" 4.21529301e-02, 1.19695384e-02, 0.00000000e+00],\n", |
| 315 |
" [ 1.04891837e-01, 0.00000000e+00, 0.00000000e+00,\n", |
| 316 |
" 8.22632074e-01, 0.00000000e+00, 5.40932834e-01,\n", |
| 317 |
" 2.50056237e-02, 9.16116759e-02, 1.97594035e-02,\n", |
| 318 |
" 1.00487731e-01, 3.59659968e-03, 1.21216271e-02],\n", |
| 319 |
" [ 4.19154540e-02, 0.00000000e+00, 0.00000000e+00,\n", |
| 320 |
" 5.32641709e-01, 0.00000000e+00, 8.34550500e-01,\n", |
| 321 |
" 1.78163908e-02, 4.51259725e-02, 3.18069607e-02,\n", |
| 322 |
" 1.09734260e-01, 5.05780652e-02, 9.80062131e-03],\n", |
| 323 |
" [ 8.45797267e-03, 0.00000000e+00, 0.00000000e+00,\n", |
| 324 |
" 3.46328110e-01, 1.50650961e-03, 9.27628219e-01,\n", |
| 325 |
" 7.37146754e-03, 2.01032832e-02, 2.88057886e-02,\n", |
| 326 |
" 1.09431997e-01, 7.88086504e-02, 3.81295895e-03],\n", |
| 327 |
" [ 7.56919500e-04, 0.00000000e+00, 0.00000000e+00,\n", |
| 328 |
" 1.79450840e-01, 7.06915976e-04, 9.73997831e-01,\n", |
| 329 |
" 1.11817913e-02, 1.11172069e-02, 1.42024225e-02,\n", |
| 330 |
" 1.05667293e-01, 8.66513774e-02, 0.00000000e+00],\n", |
| 331 |
" [ 1.66557627e-04, 0.00000000e+00, 0.00000000e+00,\n", |
| 332 |
" 5.85122816e-02, 0.00000000e+00, 9.89142358e-01,\n", |
| 333 |
" 0.00000000e+00, 1.83676016e-02, 1.94070525e-02,\n", |
| 334 |
" 1.07398190e-01, 7.69759417e-02, 0.00000000e+00],\n", |
| 335 |
" [ 1.33603578e-04, 7.56053627e-03, 9.44652930e-02,\n", |
| 336 |
" 0.00000000e+00, 0.00000000e+00, 8.86209607e-01,\n", |
| 337 |
" 0.00000000e+00, 4.42017883e-01, 3.05218417e-02,\n", |
| 338 |
" 6.33440092e-02, 0.00000000e+00, 7.29914904e-02],\n", |
| 339 |
" [ 1.31346369e-02, 6.74642762e-03, 6.19773120e-02,\n", |
| 340 |
" 0.00000000e+00, 0.00000000e+00, 5.67794800e-01,\n", |
| 341 |
" 0.00000000e+00, 8.15741003e-01, 2.10058969e-02,\n", |
| 342 |
" 8.59899446e-03, 2.03802008e-02, 8.47698301e-02],\n", |
| 343 |
" [ 4.31743301e-02, 6.34776545e-04, 4.03778553e-02,\n", |
| 344 |
" 0.00000000e+00, 0.00000000e+00, 3.56203496e-01,\n", |
| 345 |
" 0.00000000e+00, 9.28523600e-01, 1.56203127e-02,\n", |
| 346 |
" 0.00000000e+00, 2.54802778e-02, 8.10867995e-02],\n", |
| 347 |
" [ 7.33419284e-02, 6.10208313e-04, 3.63619663e-02,\n", |
| 348 |
" 0.00000000e+00, 0.00000000e+00, 1.90394580e-01,\n", |
| 349 |
" 0.00000000e+00, 9.74134982e-01, 0.00000000e+00,\n", |
| 350 |
" 0.00000000e+00, 3.36330049e-02, 8.35358649e-02],\n", |
| 351 |
" [ 8.68176147e-02, 4.59924020e-04, 4.55667339e-02,\n", |
| 352 |
" 0.00000000e+00, 0.00000000e+00, 5.53724468e-02,\n", |
| 353 |
" 0.00000000e+00, 9.90521610e-01, 0.00000000e+00,\n", |
| 354 |
" 0.00000000e+00, 2.28140894e-02, 7.52758607e-02],\n", |
| 355 |
" [ 7.16657490e-02, 4.01280704e-04, 3.66930082e-03,\n", |
| 356 |
" 1.17143862e-01, 0.00000000e+00, 5.73444937e-04,\n", |
| 357 |
" 1.10340081e-02, 9.86149490e-01, 8.01642761e-02,\n", |
| 358 |
" 0.00000000e+00, 0.00000000e+00, 4.57016900e-02],\n", |
| 359 |
" [ 1.75292432e-01, 2.99866330e-02, 2.26163003e-03,\n", |
| 360 |
" 2.27569327e-01, 1.22354610e-03, 5.50737930e-03,\n", |
| 361 |
" 1.99322514e-02, 7.56762803e-01, 5.85586727e-01,\n", |
| 362 |
" 0.00000000e+00, 0.00000000e+00, 2.34449338e-02],\n", |
| 363 |
" [ 2.28524566e-01, 3.58712338e-02, 1.71243236e-03,\n", |
| 364 |
" 1.92382738e-01, 2.56250240e-03, 1.83521246e-03,\n", |
| 365 |
" 1.90234948e-02, 4.48429465e-01, 8.41433167e-01,\n", |
| 366 |
" 0.00000000e+00, 0.00000000e+00, 2.25367188e-03],\n", |
| 367 |
" [ 2.01807752e-01, 3.38590629e-02, 1.47551857e-03,\n", |
| 368 |
" 1.39506012e-01, 2.78139906e-03, 0.00000000e+00,\n", |
| 369 |
" 1.72728170e-02, 2.58494407e-01, 9.33561802e-01,\n", |
| 370 |
" 0.00000000e+00, 0.00000000e+00, 0.00000000e+00],\n", |
| 371 |
" [ 1.54486775e-01, 7.73785859e-02, 1.31765706e-03,\n", |
| 372 |
" 1.13231480e-01, 2.59730266e-03, 0.00000000e+00,\n", |
| 373 |
" 1.56198768e-02, 1.29941836e-01, 9.69632685e-01,\n", |
| 374 |
" 0.00000000e+00, 0.00000000e+00, 0.00000000e+00],\n", |
| 375 |
" [ 1.27307221e-01, 1.46335676e-01, 7.25547271e-03,\n", |
| 376 |
" 7.30697215e-02, 1.78271858e-03, 1.15589900e-02,\n", |
| 377 |
" 1.46873416e-02, 4.01094183e-02, 9.77254152e-01,\n", |
| 378 |
" 0.00000000e+00, 0.00000000e+00, 0.00000000e+00],\n", |
| 379 |
" [ 0.00000000e+00, 6.90020099e-02, 1.04619361e-01,\n", |
| 380 |
" 2.25574570e-03, 1.59145482e-02, 8.51853862e-02,\n", |
| 381 |
" 1.19112581e-02, 3.24970335e-02, 8.37207258e-01,\n", |
| 382 |
" 2.33193263e-02, 5.23565650e-01, 0.00000000e+00],\n", |
| 383 |
" [ 0.00000000e+00, 1.16285548e-01, 8.28386694e-02,\n", |
| 384 |
" 4.62941220e-03, 4.11567837e-02, 5.65895475e-02,\n", |
| 385 |
" 8.86768941e-03, 3.56909935e-03, 4.53278303e-01,\n", |
| 386 |
" 5.48035046e-03, 8.76992106e-01, 0.00000000e+00],\n", |
| 387 |
" [ 0.00000000e+00, 9.20006111e-02, 8.02344009e-02,\n", |
| 388 |
" 8.05004500e-03, 3.36742140e-02, 5.60967848e-02,\n", |
| 389 |
" 7.82551430e-03, 0.00000000e+00, 2.42856041e-01,\n", |
| 390 |
" 6.69736741e-03, 9.60035205e-01, 0.00000000e+00],\n", |
| 391 |
" [ 0.00000000e+00, 7.55143464e-02, 8.95384848e-02,\n", |
| 392 |
" 3.87140363e-02, 3.20630074e-02, 5.86400703e-02,\n", |
| 393 |
" 6.61307480e-03, 0.00000000e+00, 1.47289306e-01,\n", |
| 394 |
" 4.46502026e-03, 9.79059339e-01, 0.00000000e+00],\n", |
| 395 |
" [ 0.00000000e+00, 4.65285294e-02, 9.54503864e-02,\n", |
| 396 |
" 7.55635425e-02, 2.02768799e-02, 6.72976673e-02,\n", |
| 397 |
" 6.64060982e-03, 0.00000000e+00, 7.32876062e-02,\n", |
| 398 |
" 2.12864913e-02, 9.86005127e-01, 0.00000000e+00],\n", |
| 399 |
" [ 2.27480859e-01, 1.47993211e-04, 4.33240309e-02,\n", |
| 400 |
" 4.05451544e-02, 5.41272797e-02, 3.53963580e-03,\n", |
| 401 |
" 1.43123539e-02, 2.27174103e-01, 1.35128628e-02,\n", |
| 402 |
" 4.26806025e-02, 9.42322791e-01, 0.00000000e+00],\n", |
| 403 |
" [ 7.76776791e-01, 0.00000000e+00, 0.00000000e+00,\n", |
| 404 |
" 1.39830142e-01, 5.90621531e-02, 1.34550324e-02,\n", |
| 405 |
" 3.04677729e-02, 1.83764741e-01, 1.57451839e-03,\n", |
| 406 |
" 1.49140116e-02, 5.81655264e-01, 1.22662177e-02],\n", |
| 407 |
" [ 9.20188725e-01, 0.00000000e+00, 0.00000000e+00,\n", |
| 408 |
" 1.31064311e-01, 5.43982014e-02, 1.02829868e-02,\n", |
| 409 |
" 3.28366496e-02, 1.60479471e-01, 5.82212256e-03,\n", |
| 410 |
" 0.00000000e+00, 3.25354815e-01, 1.69819314e-02],\n", |
| 411 |
" [ 9.54825997e-01, 0.00000000e+00, 0.00000000e+00,\n", |
| 412 |
" 9.08428580e-02, 5.47444783e-02, 6.06109276e-02,\n", |
| 413 |
" 3.60330939e-02, 1.57885581e-01, 8.70869216e-03,\n", |
| 414 |
" 0.00000000e+00, 2.16832295e-01, 8.11457075e-03],\n", |
| 415 |
" [ 9.67904449e-01, 0.00000000e+00, 0.00000000e+00,\n", |
| 416 |
" 5.66124730e-02, 5.64976931e-02, 1.21210732e-01,\n", |
| 417 |
" 2.68668495e-02, 1.64355710e-01, 8.75006244e-03,\n", |
| 418 |
" 0.00000000e+00, 1.18906766e-01, 1.10401316e-02],\n", |
| 419 |
" [ 9.10301507e-01, 0.00000000e+00, 3.58769506e-01,\n", |
| 420 |
" 1.06141996e-02, 4.18055505e-02, 1.46602556e-01,\n", |
| 421 |
" 3.75781134e-02, 9.09660459e-02, 4.86972230e-03,\n", |
| 422 |
" 9.57466066e-02, 1.99975353e-02, 2.24707532e-03],\n", |
| 423 |
" [ 5.32060623e-01, 0.00000000e+00, 8.38650227e-01,\n", |
| 424 |
" 9.16879624e-03, 2.60610599e-04, 3.36099602e-02,\n", |
| 425 |
" 3.72139812e-02, 2.78077256e-02, 5.88112622e-02,\n", |
| 426 |
" 8.20663497e-02, 3.43208760e-03, 0.00000000e+00],\n", |
| 427 |
" [ 2.87455708e-01, 4.98069590e-03, 9.52399194e-01,\n", |
| 428 |
" 6.48918748e-03, 1.46152312e-02, 1.27553497e-03,\n", |
| 429 |
" 3.50150578e-02, 3.32775638e-02, 6.14331104e-02,\n", |
| 430 |
" 6.25745505e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 431 |
" [ 1.61070168e-01, 2.89101563e-02, 9.81492460e-01,\n", |
| 432 |
" 6.82534557e-03, 3.21710594e-02, 0.00000000e+00,\n", |
| 433 |
" 3.05393171e-02, 2.94240173e-02, 2.76064165e-02,\n", |
| 434 |
" 7.77955055e-02, 1.41078206e-02, 0.00000000e+00],\n", |
| 435 |
" [ 8.16927776e-02, 1.41722215e-02, 9.86824512e-01,\n", |
| 436 |
" 5.50024724e-03, 4.24346775e-02, 0.00000000e+00,\n", |
| 437 |
" 3.15050595e-02, 3.23357806e-02, 0.00000000e+00,\n", |
| 438 |
" 1.10492751e-01, 5.67878187e-02, 0.00000000e+00],\n", |
| 439 |
" [ 3.24949436e-02, 7.84328731e-04, 9.87073660e-01,\n", |
| 440 |
" 2.14368664e-02, 8.19184929e-02, 0.00000000e+00,\n", |
| 441 |
" 4.47093956e-02, 4.51755077e-02, 0.00000000e+00,\n", |
| 442 |
" 7.68498033e-02, 8.66795480e-02, 0.00000000e+00],\n", |
| 443 |
" [ 4.58201068e-03, 5.83841931e-04, 7.21634507e-01,\n", |
| 444 |
" 6.54176593e-01, 6.88196346e-03, 1.98839908e-03,\n", |
| 445 |
" 3.12678590e-02, 4.32215557e-02, 2.30717994e-02,\n", |
| 446 |
" 0.00000000e+00, 2.02596381e-01, 8.24658498e-02],\n", |
| 447 |
" [ 0.00000000e+00, 1.26990154e-02, 2.43063256e-01,\n", |
| 448 |
" 9.57038760e-01, 3.64562906e-02, 4.62111691e-03,\n", |
| 449 |
" 0.00000000e+00, 2.28635464e-02, 2.43536346e-02,\n", |
| 450 |
" 0.00000000e+00, 1.47804186e-01, 2.28763055e-02],\n", |
| 451 |
" [ 0.00000000e+00, 3.60645913e-02, 9.64465439e-02,\n", |
| 452 |
" 9.83903885e-01, 7.15166628e-02, 2.05014599e-03,\n", |
| 453 |
" 0.00000000e+00, 1.82101205e-02, 3.92813012e-02,\n", |
| 454 |
" 1.10990729e-03, 1.14122562e-01, 3.62179056e-02],\n", |
| 455 |
" [ 0.00000000e+00, 3.63094285e-02, 4.21216004e-02,\n", |
| 456 |
" 9.86869931e-01, 2.13347878e-02, 1.17978174e-02,\n", |
| 457 |
" 0.00000000e+00, 1.84751991e-02, 3.91156822e-02,\n", |
| 458 |
" 0.00000000e+00, 1.19885042e-01, 7.84666091e-02],\n", |
| 459 |
" [ 0.00000000e+00, 3.17818634e-02, 1.20548327e-02,\n", |
| 460 |
" 9.88725364e-01, 1.00220600e-02, 4.33316268e-02,\n", |
| 461 |
" 0.00000000e+00, 1.82445534e-02, 3.88606228e-02,\n", |
| 462 |
" 0.00000000e+00, 9.95126739e-02, 8.68492201e-02],\n", |
| 463 |
" [ 1.20896734e-01, 4.24718149e-02, 3.63281532e-03,\n", |
| 464 |
" 8.90641093e-01, 2.25664694e-02, 4.28505957e-01,\n", |
| 465 |
" 1.07771400e-02, 3.10042053e-02, 3.72265317e-02,\n", |
| 466 |
" 7.50589697e-03, 6.06563613e-02, 0.00000000e+00],\n", |
| 467 |
" [ 1.61590315e-02, 0.00000000e+00, 2.05814978e-03,\n", |
| 468 |
" 5.34187019e-01, 5.10551874e-03, 8.44328225e-01,\n", |
| 469 |
" 2.61573698e-02, 0.00000000e+00, 0.00000000e+00,\n", |
| 470 |
" 5.78178698e-03, 2.39303317e-02, 1.31363133e-02],\n", |
| 471 |
" [ 0.00000000e+00, 2.69280165e-03, 9.71267698e-04,\n", |
| 472 |
" 3.30787838e-01, 6.21950440e-03, 9.42233920e-01,\n", |
| 473 |
" 2.94584725e-02, 0.00000000e+00, 0.00000000e+00,\n", |
| 474 |
" 5.73373958e-03, 4.27455939e-02, 0.00000000e+00],\n", |
| 475 |
" [ 2.47827508e-02, 4.29236740e-02, 0.00000000e+00,\n", |
| 476 |
" 1.78738758e-01, 6.27625687e-03, 9.80933607e-01,\n", |
| 477 |
" 2.33737361e-02, 0.00000000e+00, 0.00000000e+00,\n", |
| 478 |
" 7.23603368e-03, 5.22218719e-02, 0.00000000e+00],\n", |
| 479 |
" [ 5.14810570e-02, 8.37553367e-02, 0.00000000e+00,\n", |
| 480 |
" 8.09028223e-02, 8.36077798e-03, 9.89670217e-01,\n", |
| 481 |
" 1.91887822e-02, 0.00000000e+00, 0.00000000e+00,\n", |
| 482 |
" 7.49138277e-03, 6.20334819e-02, 0.00000000e+00],\n", |
| 483 |
" [ 3.32303753e-05, 8.98099467e-02, 7.88206458e-02,\n", |
| 484 |
" 6.78930879e-02, 1.03781344e-02, 9.46214378e-01,\n", |
| 485 |
" 1.99007969e-02, 2.77829796e-01, 0.00000000e+00,\n", |
| 486 |
" 5.27049974e-03, 8.98295045e-02, 1.37303854e-04],\n", |
| 487 |
" [ 4.44915071e-02, 1.76926572e-02, 8.55404064e-02,\n", |
| 488 |
" 3.43059041e-02, 1.02791190e-02, 6.12779975e-01,\n", |
| 489 |
" 1.08479448e-02, 7.82902002e-01, 2.35577822e-02,\n", |
| 490 |
" 0.00000000e+00, 0.00000000e+00, 4.15841729e-04],\n", |
| 491 |
" [ 8.49419683e-02, 1.20955601e-03, 1.09671973e-01,\n", |
| 492 |
" 1.21201193e-02, 9.66064632e-03, 3.11394960e-01,\n", |
| 493 |
" 1.18757421e-02, 9.39238966e-01, 3.51763368e-02,\n", |
| 494 |
" 0.00000000e+00, 0.00000000e+00, 4.83505777e-04],\n", |
| 495 |
" [ 9.73264351e-02, 8.18368455e-04, 1.63447946e-01,\n", |
| 496 |
" 3.29327881e-02, 0.00000000e+00, 1.07415654e-01,\n", |
| 497 |
" 1.59726590e-02, 9.74627972e-01, 3.21203768e-02,\n", |
| 498 |
" 0.00000000e+00, 0.00000000e+00, 1.54338195e-03],\n", |
| 499 |
" [ 1.01416051e-01, 1.04169792e-03, 1.80728644e-01,\n", |
| 500 |
" 6.06901050e-02, 0.00000000e+00, 6.61162585e-02,\n", |
| 501 |
" 2.47565545e-02, 9.73594368e-01, 2.22180188e-02,\n", |
| 502 |
" 0.00000000e+00, 0.00000000e+00, 1.90866261e-03],\n", |
| 503 |
" [ 1.10513330e-01, 1.16068090e-03, 1.73820123e-01,\n", |
| 504 |
" 1.02041930e-01, 0.00000000e+00, 2.92204432e-02,\n", |
| 505 |
" 2.34890543e-02, 9.72198844e-01, 1.90163553e-02,\n", |
| 506 |
" 1.48797734e-02, 0.00000000e+00, 4.90254548e-04],\n", |
| 507 |
" [ 3.55627201e-02, 1.81428045e-02, 4.17622877e-03,\n", |
| 508 |
" 2.48133853e-01, 6.25082552e-02, 0.00000000e+00,\n", |
| 509 |
" 1.42965894e-02, 7.92297900e-01, 5.51682591e-01,\n", |
| 510 |
" 2.48422138e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 511 |
" [ 5.95075870e-03, 5.97717762e-02, 3.42534087e-03,\n", |
| 512 |
" 2.44145840e-01, 6.32875264e-02, 0.00000000e+00,\n", |
| 513 |
" 5.36254235e-02, 2.65350431e-01, 9.26052630e-01,\n", |
| 514 |
" 4.36774455e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 515 |
" [ 0.00000000e+00, 9.64460075e-02, 4.26064106e-03,\n", |
| 516 |
" 2.43948385e-01, 1.03570849e-01, 0.00000000e+00,\n", |
| 517 |
" 5.81620783e-02, 8.93463269e-02, 9.52694476e-01,\n", |
| 518 |
" 3.80766317e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 519 |
" [ 0.00000000e+00, 1.12178475e-01, 3.88786709e-03,\n", |
| 520 |
" 2.46120870e-01, 1.31447807e-01, 0.00000000e+00,\n", |
| 521 |
" 5.56226894e-02, 4.11828794e-02, 9.50674713e-01,\n", |
| 522 |
" 3.12177110e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 523 |
" [ 0.00000000e+00, 1.28379866e-01, 4.15798742e-03,\n", |
| 524 |
" 2.42848128e-01, 1.54101759e-01, 0.00000000e+00,\n", |
| 525 |
" 5.40410578e-02, 2.66808942e-02, 9.47005868e-01,\n", |
| 526 |
" 1.80636272e-02, 0.00000000e+00, 0.00000000e+00],\n", |
| 527 |
" [ 2.53865309e-03, 1.91127621e-02, 2.02243449e-03,\n", |
| 528 |
" 1.12406276e-01, 2.00758558e-02, 1.71211556e-01,\n", |
| 529 |
" 1.11278228e-01, 2.78214272e-02, 8.43058944e-01,\n", |
| 530 |
" 3.59242298e-02, 4.81743515e-01, 0.00000000e+00],\n", |
| 531 |
" [ 3.64949671e-03, 4.81741881e-04, 1.33294996e-03,\n", |
| 532 |
" 1.66589487e-02, 8.12750459e-02, 5.23330793e-02,\n", |
| 533 |
" 1.93934049e-02, 7.19395373e-03, 4.53242451e-01,\n", |
| 534 |
" 2.10740734e-02, 8.83749068e-01, 5.52243367e-02],\n", |
| 535 |
" [ 3.93255353e-02, 1.05348146e-02, 5.73153608e-04,\n", |
| 536 |
" 9.43983123e-02, 1.47002060e-02, 9.49143842e-02,\n", |
| 537 |
" 1.09301947e-01, 0.00000000e+00, 1.52132377e-01,\n", |
| 538 |
" 3.77451703e-02, 9.71437335e-01, 0.00000000e+00],\n", |
| 539 |
" [ 5.13472557e-02, 3.31028714e-03, 3.92159214e-04,\n", |
| 540 |
" 1.16105087e-01, 1.48322443e-02, 1.23555198e-01,\n", |
| 541 |
" 1.31526083e-01, 0.00000000e+00, 6.29847571e-02,\n", |
| 542 |
" 3.36713605e-02, 9.72449243e-01, 1.81256123e-02],\n", |
| 543 |
" [ 4.89317700e-02, 0.00000000e+00, 2.96047510e-04,\n", |
| 544 |
" 1.21519633e-01, 1.54881012e-02, 1.36466950e-01,\n", |
| 545 |
" 1.60353258e-01, 0.00000000e+00, 5.08026592e-02,\n", |
| 546 |
" 3.07973381e-02, 9.66688573e-01, 1.56879723e-02],\n", |
| 547 |
" [ 1.98805168e-01, 0.00000000e+00, 5.65945404e-04,\n", |
| 548 |
" 1.64412394e-01, 1.19373398e-02, 4.63520288e-02,\n", |
| 549 |
" 1.70583352e-01, 4.07661637e-03, 4.17408086e-02,\n", |
| 550 |
" 8.87884125e-02, 9.44411874e-01, 2.23336332e-02],\n", |
| 551 |
" [ 6.47660553e-01, 1.09090870e-02, 1.12898178e-01,\n", |
| 552 |
" 3.67569447e-01, 2.99617252e-03, 6.21701553e-02,\n", |
| 553 |
" 1.54504150e-01, 4.67437133e-02, 1.10933185e-01,\n", |
| 554 |
" 7.35432431e-02, 6.20417595e-01, 0.00000000e+00],\n", |
| 555 |
" [ 8.65435898e-01, 1.29718129e-02, 1.31817251e-01,\n", |
| 556 |
" 4.10883605e-01, 2.92400713e-03, 3.68153490e-02,\n", |
| 557 |
" 1.44890234e-01, 4.59817313e-02, 6.56576604e-02,\n", |
| 558 |
" 7.75373355e-02, 1.72791988e-01, 0.00000000e+00],\n", |
| 559 |
" [ 8.88324201e-01, 6.67957403e-03, 1.39935628e-01,\n", |
| 560 |
" 4.00488734e-01, 4.18466097e-03, 2.89282724e-02,\n", |
| 561 |
" 1.33017287e-01, 3.70216854e-02, 4.46694382e-02,\n", |
| 562 |
" 9.21769366e-02, 2.12607980e-02, 0.00000000e+00],\n", |
| 563 |
" [ 9.02807713e-01, 2.10447935e-04, 1.41207904e-01,\n", |
| 564 |
" 3.53729814e-01, 3.70743335e-03, 2.84916237e-02,\n", |
| 565 |
" 1.24700516e-01, 3.85591500e-02, 7.32387602e-02,\n", |
| 566 |
" 1.29023820e-01, 0.00000000e+00, 0.00000000e+00],\n", |
| 567 |
" [ 9.03710365e-01, 7.44168297e-04, 1.43547714e-01,\n", |
| 568 |
" 3.72946084e-01, 2.09493097e-03, 0.00000000e+00,\n", |
| 569 |
" 8.42517391e-02, 3.97068709e-02, 2.67486330e-02,\n", |
| 570 |
" 1.19236149e-01, 0.00000000e+00, 0.00000000e+00],\n", |
| 571 |
" [ 6.47389770e-01, 9.62956576e-04, 6.64771974e-01,\n", |
| 572 |
" 2.39137374e-03, 4.67590615e-02, 3.20941329e-01,\n", |
| 573 |
" 0.00000000e+00, 4.35641073e-02, 7.85760134e-02,\n", |
| 574 |
" 8.59864429e-03, 0.00000000e+00, 1.60069823e-01],\n", |
| 575 |
" [ 3.28709215e-01, 1.69933238e-03, 8.70308340e-01,\n", |
| 576 |
" 4.05057380e-03, 1.12228401e-01, 3.07389766e-01,\n", |
| 577 |
" 0.00000000e+00, 9.21808649e-03, 4.08464074e-02,\n", |
| 578 |
" 2.30031274e-02, 7.12022707e-02, 1.41627774e-01],\n", |
| 579 |
" [ 5.96006438e-02, 4.15985996e-04, 9.20822084e-01,\n", |
| 580 |
" 4.98715788e-03, 1.42810524e-01, 2.99190283e-01,\n", |
| 581 |
" 0.00000000e+00, 2.82171019e-03, 9.67504531e-02,\n", |
| 582 |
" 2.13448349e-02, 6.86788633e-02, 1.55108571e-01],\n", |
| 583 |
" [ 1.00534863e-03, 4.87674290e-04, 9.16018307e-01,\n", |
| 584 |
" 4.97340411e-03, 1.85771078e-01, 3.13747913e-01,\n", |
| 585 |
" 9.55010357e-04, 5.11498714e-04, 9.01460797e-02,\n", |
| 586 |
" 1.34017579e-02, 4.05923054e-02, 1.34093180e-01],\n", |
| 587 |
" [ 0.00000000e+00, 0.00000000e+00, 9.05534029e-01,\n", |
| 588 |
" 5.09170676e-03, 1.82564944e-01, 3.44701409e-01,\n", |
| 589 |
" 8.97256471e-03, 2.26824824e-03, 1.00266904e-01,\n", |
| 590 |
" 1.87462308e-02, 2.89424807e-02, 1.28471538e-01],\n", |
| 591 |
" [ 2.77297825e-01, 6.03795843e-03, 8.73157024e-01,\n", |
| 592 |
" 1.08850159e-01, 1.63998351e-01, 1.86085239e-01,\n", |
| 593 |
" 1.12378791e-01, 3.68778827e-03, 1.07245937e-01,\n", |
| 594 |
" 3.08599211e-02, 2.12714560e-02, 2.48486638e-01],\n", |
| 595 |
" [ 1.69244453e-01, 4.37403657e-02, 3.03969860e-01,\n", |
| 596 |
" 8.75151455e-01, 7.77170341e-03, 2.06874907e-01,\n", |
| 597 |
" 2.50959158e-01, 0.00000000e+00, 8.39735847e-03,\n", |
| 598 |
" 7.22065493e-02, 8.75575293e-04, 5.66987647e-03],\n", |
| 599 |
" [ 1.40741259e-01, 2.77895574e-02, 1.73567645e-02,\n", |
| 600 |
" 9.07734573e-01, 7.42862932e-03, 2.24477738e-01,\n", |
| 601 |
" 3.04128051e-01, 5.42865787e-03, 5.90750622e-03,\n", |
| 602 |
" 1.04962960e-01, 1.62259471e-02, 2.91900449e-02],\n", |
| 603 |
" [ 1.27348348e-01, 1.07598603e-02, 1.18422986e-03,\n", |
| 604 |
" 8.94889832e-01, 7.23825302e-03, 2.36309320e-01,\n", |
| 605 |
" 3.41708928e-01, 1.28864544e-02, 0.00000000e+00,\n", |
| 606 |
" 9.47451070e-02, 9.87819675e-03, 3.06219123e-02],\n", |
| 607 |
" [ 1.17779538e-01, 0.00000000e+00, 1.24025333e-03,\n", |
| 608 |
" 8.85621727e-01, 7.06024608e-03, 2.27433771e-01,\n", |
| 609 |
" 3.75163913e-01, 1.33218318e-02, 0.00000000e+00,\n", |
| 610 |
" 8.89331475e-02, 1.81943830e-02, 2.93087736e-02],\n", |
| 611 |
" [ 1.02612011e-01, 0.00000000e+00, 1.19107720e-02,\n", |
| 612 |
" 8.53048503e-01, 7.52635021e-03, 2.57968783e-01,\n", |
| 613 |
" 4.22296256e-01, 1.49089722e-02, 0.00000000e+00,\n", |
| 614 |
" 1.20436154e-01, 2.86021344e-02, 3.39591093e-02],\n", |
| 615 |
" [ 2.23645344e-01, 7.00941384e-02, 2.90339235e-02,\n", |
| 616 |
" 8.11006844e-01, 1.22231124e-02, 1.77608401e-01,\n", |
| 617 |
" 4.94134247e-01, 6.94465777e-03, 0.00000000e+00,\n", |
| 618 |
" 8.01459849e-02, 2.53690537e-02, 5.93009964e-02],\n", |
| 619 |
" [ 3.20195317e-01, 0.00000000e+00, 5.79862818e-02,\n", |
| 620 |
" 8.01172554e-01, 1.55903110e-02, 1.03361912e-01,\n", |
| 621 |
" 4.87446874e-01, 1.80881284e-03, 0.00000000e+00,\n", |
| 622 |
" 0.00000000e+00, 3.16866152e-02, 5.19289337e-02]], dtype=float32))}" |
| 623 |
] |
| 624 |
}, |
| 625 |
"execution_count": 8, |
| 626 |
"metadata": {},
|
| 627 |
"output_type": "execute_result" |
| 628 |
} |
| 629 |
], |
| 630 |
"source": [ |
| 631 |
"out" |
| 632 |
] |
| 633 |
}, |
| 634 |
{
|
| 635 |
"cell_type": "markdown", |
| 636 |
"metadata": {},
|
| 637 |
"source": [ |
| 638 |
"### Plotting the results\n", |
| 639 |
"\n", |
| 640 |
"The `matrix` dictionary element contains a tuple of step time (the time in seconds from one chroma feature to the next), and the chroma features themselves as a 2d NumPy array." |
| 641 |
] |
| 642 |
}, |
| 643 |
{
|
| 644 |
"cell_type": "code", |
| 645 |
"execution_count": 9, |
| 646 |
"metadata": {
|
| 647 |
"collapsed": false |
| 648 |
}, |
| 649 |
"outputs": [], |
| 650 |
"source": [ |
| 651 |
"step, chroma = out[\"matrix\"]" |
| 652 |
] |
| 653 |
}, |
| 654 |
{
|
| 655 |
"cell_type": "code", |
| 656 |
"execution_count": 10, |
| 657 |
"metadata": {
|
| 658 |
"collapsed": false |
| 659 |
}, |
| 660 |
"outputs": [ |
| 661 |
{
|
| 662 |
"data": {
|
| 663 |
"text/plain": [ |
| 664 |
" 0.092879819" |
| 665 |
] |
| 666 |
}, |
| 667 |
"execution_count": 10, |
| 668 |
"metadata": {},
|
| 669 |
"output_type": "execute_result" |
| 670 |
} |
| 671 |
], |
| 672 |
"source": [ |
| 673 |
"step" |
| 674 |
] |
| 675 |
}, |
| 676 |
{
|
| 677 |
"cell_type": "markdown", |
| 678 |
"metadata": {},
|
| 679 |
"source": [ |
| 680 |
"As an aside, we may find it useful later to have the step time in samples rather than seconds. Multiplying by the sample rate gets this, with some rounding error, but the module also contains a dedicated function to get the result exactly." |
| 681 |
] |
| 682 |
}, |
| 683 |
{
|
| 684 |
"cell_type": "code", |
| 685 |
"execution_count": 11, |
| 686 |
"metadata": {
|
| 687 |
"collapsed": false |
| 688 |
}, |
| 689 |
"outputs": [ |
| 690 |
{
|
| 691 |
"data": {
|
| 692 |
"text/plain": [ |
| 693 |
"2048.00000895" |
| 694 |
] |
| 695 |
}, |
| 696 |
"execution_count": 11, |
| 697 |
"metadata": {},
|
| 698 |
"output_type": "execute_result" |
| 699 |
} |
| 700 |
], |
| 701 |
"source": [ |
| 702 |
"float(step) * rate" |
| 703 |
] |
| 704 |
}, |
| 705 |
{
|
| 706 |
"cell_type": "code", |
| 707 |
"execution_count": 12, |
| 708 |
"metadata": {
|
| 709 |
"collapsed": false |
| 710 |
}, |
| 711 |
"outputs": [ |
| 712 |
{
|
| 713 |
"data": {
|
| 714 |
"text/plain": [ |
| 715 |
"2048" |
| 716 |
] |
| 717 |
}, |
| 718 |
"execution_count": 12, |
| 719 |
"metadata": {},
|
| 720 |
"output_type": "execute_result" |
| 721 |
} |
| 722 |
], |
| 723 |
"source": [ |
| 724 |
"vamp.vampyhost.RealTime.to_frame(step, rate)" |
| 725 |
] |
| 726 |
}, |
| 727 |
{
|
| 728 |
"cell_type": "markdown", |
| 729 |
"metadata": {},
|
| 730 |
"source": [ |
| 731 |
"Show the chroma plot." |
| 732 |
] |
| 733 |
}, |
| 734 |
{
|
| 735 |
"cell_type": "code", |
| 736 |
"execution_count": 13, |
| 737 |
"metadata": {
|
| 738 |
"collapsed": false |
| 739 |
}, |
| 740 |
"outputs": [ |
| 741 |
{
|
| 742 |
"data": {
|
| 743 |
"text/plain": [ |
| 744 |
"<matplotlib.image.AxesImage at 0x7fc227986710>" |
| 745 |
] |
| 746 |
}, |
| 747 |
"execution_count": 13, |
| 748 |
"metadata": {},
|
| 749 |
"output_type": "execute_result" |
| 750 |
}, |
| 751 |
{
|
| 752 |
"data": {
|
| 753 |
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAW8AAABOCAYAAADvu5czAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzsvVmsbct63/WrGs3sV7/P7s7ZZ5/jc+717XJzEyM5kUwM\nMhIKUZ4QAoGIojzwkigKAhHlwQIkRCOhGPGAhARWLCIUMFEUISTkSBjyAjYxhMixud1pdrf2Xt3s\n52ireKj65qgx1ly7O74mV9rfVu2aa87R1KjmX9/3/76qoay1vJN38k7eyTv56RL9/3cB3sk7eSfv\n5J28ubwD73fyTt7JO/kplHfg/U7eyTt5Jz+F8g6838k7eSfv5KdQ3oH3O3kn7+Sd/BTKO/B+J+/k\nnbyTn0KJf1IXVkq9i0F8J+/knbyTtxBrrXrVMS8Fb6XUfw38C8ALa+13/HdHwN8CPgQ+B/4la+10\n9xX+PeB/Af4ZKdLrlZwoSBroPocNknmN68XAQZD2/Xdyj/8C+IvBNUVUcH/TSQWQARuf50AZpCJI\n8vebiY4gSi1RYokSKNe/yTD9BXRp0GWNqi3G+hLZdum7NS1/q26KI0hiSGJUmlCrmMomPqUYq8EY\nqI3LjbleFZRA5dNvAL+4485dUZ3Pu5L8loJ+D/QtUO+BPgQ7BTN1uZ0BEdgYiH0+AEbA2Ocxri01\n8NeBfwN4HqRF8Luk2ifj8265dz1H+Dw2ON+8pC5ukt+kXZc/AVEQJaAT0ClEiUKXI6JyRFSOicoR\n1q6oWWDsDMMci8XVZ0zO/0afX9pxWeX/V6BApyUqKVFJBXFFWSVUVUJZJZRlAtYESer6pt4MxPvQ\nf79J0TFUCkoNlYZaNUN8/e/D4S9DaaGwfoj6gUMwcG4B9y28D9wHsit4/BgeP3H5bAWkPvVo4HNX\nu3b7gmCJnCsJmr7xN4B/DfjnX9pk2yp4xe+/CvznwK8F3/1V4Destf+JUurf8X//1d2n93C1l9AG\nXJEuUIoImyMPJa3gB+cWUHcNdPlsg/OVL4sF1jiQiYOUAdMd5QkrXQagDMbSnyfAXdAAWJi2CPfG\nkgws45Oa0YlhdGyY/qjkZ45n9C8z+pcZ0aIkt5AZyI3rlyGm7qpteWKpTT1KUMcp6sSlTTphXh0w\nrfaY1QdkxQA2Bjb+RpltHjnD3ZS1Txua9n4ZYHXbTibRsE10873uQXoI6T6kI0j6UI39YE2gGoCJ\nwGiX2wjod1JE0ze0L2MfB+x7tPuNpIg2gOwakN1+EgV5RTO5Z/7vf7JEaegdKgbH0D9x+ehyzfBi\nw+jynNElFNWGzK7I7JrMrKi3dRNxyhV3+fG1mtEotIfwKIb4yBCfGOLjGnUAl9NjrqZHXE4PuJoe\nYascqsylOvMAHo6dTj+yFdQrKC9BRaDXUPegTqFKwSQeAizUBWQLp4BUBuraKSHWuoT/XAALC2ce\n0Ms5XE5htYYqHMvhZC5luwk7pF9omsm89MeZzjXC314tLwVva+3fV0o97Hz9Z4E/5T//DZx6cAN4\np7TBO4SUlw2K8DdDM6B7uAEXwk+onYdaelc9lM6wwmlZSXDdDXAVlHtXxYfXkUoW0JY8vE+otb0d\ng5QMLZM7hpOPK44/rog2Fd/6aMbeFwv2qzlJlrGo3dMsLaysu2MV3F1qUfJw3k+BaJii7/XRH/VR\nP9NnPjQ8zSfoos+mOCFb78PMNmlu3Q0X/gaFAWY+SV3Fwd1vmrhU5/hQG0naSfUg3YPhHoxGMOhD\npiBPIOtDPvbalr+e1WDDa6Q0/cpyHbwL/1130g37VFdhCL8Pn0NSggPsuT9OrJN/skRp6B3A5EPF\n/scuHX++4ujzFUdqxfFixcZmzE3ukioordShJueKjz14hzXioF25URorekfQewjpxxDdj/jiSZ8v\nH59QPT7gqnrgwLWYA3MHspQ0fai+Vu4GvCOwJagFmFGTbN8PQw/e+RLqCkzl89Jp+VifG8itA2/5\nXK1gMQvAW/CoO7pCXOv2kyisbdrjogq+l+d8fQv9bTjv29ba5/7zc+D2zYemwM/6vGs+hqk7U3WB\nV2b6HjCkgZ6UBoTDgQRt8CzxEIcD7zVtgPgIp3lDWzsLkw2uKeAttEiOa4gunfMm1M6O2htY9m7X\n3Pq04v3vldweHvNtNeOkuuDW1QW9qyWXCi6BC+PgMyQwZA4PSzXwaejzeNQjujtC/+yQ6HtDzvZS\n9KZis+lztjmG2XtOEznD5SkNo7CRehZwrICv+/aQ5w4nY5GwrWRy7wcl69MCc9WHZAijIewPYTyA\nVQLrPqjaDUjpO6Y76crkDs3A+6dpg3ftj8uDVHLd4guvG1oM4XPI9Jji+poA9+oVrb1LHr7FOW8m\nSkP/ULH3UHHyHcWtP6q5v7fmHmfcW7zg3tMXLKqCcyrObc05NUUwZhNyHvDja6MlVI3SWDE80gw/\nihh8VxN/vUf/929R9yKuqgOYPgB16c6qLag86DIy7joi4G1LqJagZmAPwO57rd2foyzYP+rA2xRg\ng0TtgdvjRGFgbpyFObdgMsjXUNykeYfjW8Z72D/CeJAujSbAHYL91/kD07xfJdZa+3LHZAJ8E1fg\ncNbZBd7hA4fHySBJcYN77HMZ4KKJh10HGpCtaMB1hdOGZjTdKwHu4cB7l8Z9E3hXtPnsHR3sK0rc\nswyPLYcPau58o+LBd46491vPuftixt3ROYN4xgsLL2rYU3DRKVHJ9ZpuWGDFGEgGfaKTDdGHI6Jv\n5gwOD5itDafLlGS1D5cnDk8TXyh57LWvvq2eL19+h7b2sMvyCCiRrdYtbTumAXAP6KoHSQr9FEYp\n7MWgYndZKY+MoRvjp8I+9Qu4fiAALv0z7Dti8QkgJ1zvE6HfRJSLcOJJ/X2WtDWw15WHN3z/Sl/W\na4vSkEwUozuKg080t76rubfJ+eh8ysMvn/Iw/oJpVHJqYaKgjyIPzr+PvTZVRqig1hS9SDHejxnf\nSxh/GpP8kSGLuuDFKmZ4to8a3MXWEVQ15FJfoUXepSVwNEftKZatTSnjsHvetxzAt/g+wYRgTBce\nwLdgLCpQSaOIdOu+q7CJCGZsa5oGwE2Qh3jzCT9pzfu5UuqOtfZUKXUXeHHzoX+H5sE+9mkXdRIO\ngi4Qa9xgHtFAj5jWon2H1ElIm9Q0g25Eo1F1wWSXM6o7oYQmU5cW+clIudEsThPOvq9I+gl5BJe/\nV/HsMRzPY3rlAdMKLg1cWWegS3cT7RsU1idQ9NAMUAzQDNDEqwT9tEf0+yk67XE+2eNxprjKVhSb\n57Co4ZwmXeDmvrW/EQY32CoccJ3QdtxKx++alqFG26NxLI5oJmTfPW0JRQmrpTutpk2zi7vhpc3R\nbbvQZ9Ed1NJP5FjxkXS1qi7HHdI0qS/g3BfybSf3l/l2uhTOLtoxzOVzk6yx5FcR8y8i0j2NJcL8\n7j6bz25xeVHxrIhY1jUXRnFhFJdoDy/NNV0JQhBXxCQkxMTEJFXM4EIz+CxiMNbEqx7/7w8e8vRH\nxyyeJ9hV5vwqRQz1GDhiS0OqkKIIb1vRbjdRDnNcve+iX8MggpzdFr6cE9oPfZp+m9LGnbBPhWAs\ntdGl0mquK4H/D/C77FZ0bpa3Ae+/C/w54D/2+d+5+dBfoj3ThNQCnYJKZXVZWdFmBkEuFdd1YEIb\nvENTZkybR+sCTLdM3QHSNZHCBns7TvtVUmw08+eauJdQ5ZZZFLP3CCZPEibzAUm5ZmlgaRzfvabd\nLQwK64eT5AkRKTEpESkR0Uqjnml0qtGZYj7Y43mhuSpXFMVz2Kwd/ixo8iWN37cl0j4yfUjejdro\ndmqhw0Y+T/31fJ3bEooc1t63UBRthqPgNebSUNsJAfymFJq3oljcBJohkIfPlfsK+4MA7+7EcV3f\nbbT7rr1lO983fdgaQz6NmX8Rg43IZzGbR3tcPap4dhHxeTlgU1sWRrO0EQu0b/bmmq6ETa6JiOij\nGRDRJ65S0ktIP1OkBqIXMY+fPuDp6RGL0wSWmdd6E6hH/tLm+pAWZdxC40+Y07STWNkrroOxZfeY\nD4/r3jD0q8nkHPpmxLcTYkFXOv6bljZf4vrGd4FPaQbV/7jjOtflVaGC/y3OOXmilHoE/DLwHwH/\nnVLqL+BDBW++ghhYuzrR9i401EjIQ3Y17e6MF2rmu0yZ8L4RDZBII4na1nUsdk20LnjLbyEY/GTA\nu1xrFqcRVR6xPIvoqz69WUJvNqQ3nxCVObl1AR8SAdUulcK2BnaEJiEmISImIkGvLOpZDZsa9bwm\nTxIWtWZZrynq51BeXVdKwwhIFDChoTwm7I66CVMXvEO+e+C/Czq4KaFcwXrhIgBWq2ZOCDXu7nht\nyS5AM52TuwNxl7OSGz7votpC7fCrgHeo4Xc/x50U+oxe9swu2dqQXTmtsJjFLB4lXM32GUwjBrMB\ng2KfqlbkNiK3MbmNPES1x4PYd+5zjGaMYoxmjK76RJeWyFqiqUX/GGaLQ2bzA+aLBLvcOCdlHTvw\npgfKY4LSoCKwquM+kbA9SxPJI5q3+BmgjQXSYeTYbkfpToyCRwLWAZVHn92adLe+Q9xKaAIdZCBJ\nP7E0A+v15FXRJv/KDT9dD+zcKbsKsov/hPbMNqYdly3mi8yEXXpjl3YRisyQAtzS+Q2u4UMAl/S6\n8pMBbnC0ybxIWJylaJ06iDADMBOUKVC2ck9rd0+L7lm7g9tZM0o61LpCZRk8z0BnWFVhrMGywrDY\nPf5bN4uAuzQd+4Q2qnY1jZLdmvcgSAo3sXptyZZQ+LAwzkFd3cwI3Ci7fuzSES+7yOvwzLuUiLfp\nU13ZpWGH2mDIy9/k8A/BuyHWrKnJr1KKeYJ6lKB0ijIaZQYoc4A2JdZqLDGWBNuKbb4ppahwTUU9\nQl3WMK1RugZtMCZyyUbOMWj9s1gfXqxiUAmo1OXoTtPMaMav8HgC3rX/vivdibo7CUedvwW8Q0pP\nFAxxBIX0RxdDDNdZhJwmfFSUx7W/Z+G/ez15a4elUuqvAH8BV6X/CPjz1tq8fdR7cjTtigpHXhdg\nxAO1oaFEupx4V8JBEqJLSKFsaCpNSFIZUDo4fpemvWtAh5xYQpxYBuOM4SRjON7Q7+dEa0O0Nuh1\nTbQxVLVXMGqXdg2xsHYiFZGqlEQnpDrB9mKyQUw2jNgMYoqkT5nHVHlCXSRUedzGygqnsRiFC5/r\nmt/gVvl0ny/U0LpWyC4RnnFOs/DgJkAMve6WRhOSNhfPaMhHb8AuwL4sVnoXN/wy2aVFd1vkD0K6\ndd41zUPZpYC0Ne3eyDCY1PTHlv7EEucKtQS9VKiFgtJiMFgkFxtMrusoBuUBR2GIVEKsYpd0QjaO\n2QxjsmFCNkgosz7Vqkm2wkX42BpsxTbUbnt9URL8uLIG6shp1ts6CI8Xmiqsq8RpJS0JlSzxs8Q4\ncA3rW/KuQ7nbvt0+050YBZNEu5eyCvCKUrhL+ZPnCyfWUPMWi2yOGzvC/b2+MvhW4K2Uug/8JeAb\n1tpcKfW3gH8ZF/cdyH12c4RdTSA0qYUHgobD6jZCy35iNwfdBeJiRxJTVq6p2d0Au6gRWQjiZuE4\nsRycXHLr/ppb91ccHsxIz8ptSs5LcqFrC8jr687Fro7U0xHjJGKcxox7MWbS5/LWHlcnE65u7TEb\n9FjPR2xmQzbzIdVi4PqBREOuAeNnDMlbWoI45oqgJKHp1wWaXYCj/PlLGhMw5Pik84dtI20e1mto\nrsogkXKJtiK6gWiYYRl2ccKvKwIm3Zb4qhKCQhfAw7EAu+kN2zlWMZhUHN0vOLpfcnS/oLcoiR6X\nRE9LorzCljU1lhpDhcUGtIZcW/mxojBoZejHEf00op+4/OrWvutnt/a4vLXH+iphczpkfTqhPh1T\nbyzUhU8StRGOGVGGKnwnpB1CKSAmoC0TclAX1sf3k3pt3ODC+6RPCPhpHFUn4cghfdEJOb0GsK/y\nH4R+EdHkw769y2HZbb+u5SuKShi2JZEwb6YwfJVQwRgYKqVqnA3x5PohAt5dLjAExhpXeEmiIYfO\nhy54i+zm8a7zldCuYAltE/COaXc807nmLpHQsAmwT5xY9k/W3PvY8tE3Vty/e8Hgs4zB5xkDndPL\nctYbj60G1qVbByB+79D3LU800orjVHM00BwPNdXxhCcP7vD0Q82ThxPivT7Jiwm8OKB8cQDnExfx\nuA27tlD5Dr/t+KI1hIuMwoEUPu9NPC+dY0oaTWhNmwIZdtpp12TdHQC7PPJh2cSh2TV5d/WR1xEp\nm7RCVzl4Wwn56rAPh0DeBe+uItKepAaTmqP7Gfe/seb9b64Zna9JeiuSYk18tsKuKkqsT1AHWnfj\nWHT3cR4RyzjSTFLFZKAZDzRP7tzhyUd3ePowJvloj6snKfoHQ2q7R7Y4hNpCuQHWuBWt3QVq8kzi\nhaloR4kNcX0wpHC6fcADvO3R9JUNWMEH0dQjGlojdMgILIV0R7dub4oekjYSSibDOZ6L4DdR+G6i\np0KlJLSeus770PP+hwDe1tonSqn/FPgSV5P/s7X2710/8h7XZ7PuA5e4GDShNmQwZzQV2zVl4OXa\ne9gwkqANQCEYhJq3XDNcUbVLNG5mnwBHxKnl4OSc+x8bvva9FZ98dM54smYSrRlvVgwvN8yVWwMw\nL5sAsjCF+osF9jXcTRR3Boq7YyiPD/nhg4jhN8fwLUt11IdHE4ovj1lPbkHvsAHurQGzdh3erEFt\nPHUig006TejI6Wrcr0NHSJutaTShPX+PkEeUDi2T5y4vqGgl3UHQ5Xm7ZdrluHuZdEFTal+0wD8I\n2iR0KobaWggQ3X7cHdzteuhPKo7ez3n/m0s+/fkZ+0+m9PIp6fmU3o+mGPIWHAjENeBNAOIQKziM\n4bCnOBzC4Vjxw7sle58kJN/ao/w28MMEY4dki33002MX1meXDrjFsbiT9xUFQWgU0UQHNFqt1H3I\n9ZWurmz4nVh3kqDNRcc05qb25w1xffHA57tok64DOARbAe5QwezKy6zzkAGANutAcN7bUXVvS5sc\n4pbJP8Q94X+vlPpXrbV/s3VgOmELvvYm8PYats39DJ7TeOCs571CnjSsrHAm3QXerlGU1uhBRDTQ\nRIOIqKdIi4y0yEmLjF6RY2qDqa1LxmKsGJ5tA7Sp9k2LRzzE8J4+53Z8yd1kyt3BgnS/InnPkryf\nYvOIehpRziLyacS6H5MVsKkgKyGroDYGQ71NKZa1tawMLGuoqj7rIiHbRBRLqFJDvaoxmxKbeU6m\npchYV6dh3UYG4giiPsQG6DlKxXpqxVoP8Mrl9iXgvaWKjTvPGM9/ivUi0Ra6fd6NG3iFe8TsmkAE\nuLvd1nKdU36VdAfUrrUCbyhxBGniNvpKE1JlGZiavikY2DVxDXUVYaqIuo4wtfL9ymK2PaxrfbS1\nudssuKvm3FNz3ldz+skGMzTUez3y40PKsqIoIS8teWmpa0eTKE+T4DVvicuOsPQspEaRGIhrWBUJ\nm0xTrKFcGKpVRZ3n2DLDmg2O697gfBDiQ+paS+EzCMV402S9K1RTgCycCMJN4ISiC7lraHAipDxy\n2lt0hFb2LmZAUugnE4tV7rHLP/G61toukH9zeVva5JeAz6y1FwBKqb8N/EmgDd7qP2RbsfEvQvzP\nNn9vnRkRbh+CPV8PCc3udR5UrnWMkNjfNXuFmoxCxZb0yNK7o+jfVvSPFQfTjIPplIPpFQfTKVVm\nKHMoc0uZWUoMJbVPhhrbmjYsPRSXwCmKPfaN5e7mKbemzzh4ccFokpGVfdbjMfmDPptRj6uLAVcX\n/W2eLxTFkm2qbYElw9gMS87Q1FwUlicbyxGW6mLIsy9OODUjni3hYrxhcTFjcwbVeQkXC6fSbxfR\nWKhyMHkD4gkw1DAYu71CrIXKuNVtlfHjTvmqVC65xvRAznUsr2q23thKBqsAdk4bDBVtugSaiVbM\nBtGsw8HVpR662orkMnhfB4C7fpE3HYQd6aWwN4b9MeyNGEQZt8sLblcz7lQXDPIN+VpTSKoVNVbi\nPqhv7MtSJsuH2Yb7VyvuPFtz67M15SLlIt/ncjjm4v6YVRJRLQzl3FAuDKZ2da08SCrvpBQgj6xh\nVCnGBYzXipGBZ6e3eJYeclqkvLgqmT1bsfosIj812NXGxaVWG1yUSEZ7IVa37GJ9CWUS+e9DUAw1\n7NAiVsE1Qssw9HuJghBxPSgBGtCXePA2NuwOB5XPa9zmE0uaZbzdvvE2k33XqvwMF3X9ZvK24P0F\n8PNKqQGupn4J+K1rRx39u758ChftID/Iw/oBXg98e/sg/do3og0dayE7HNIZN/FNTSOpWJEew/Aj\nGH+qmDyA+88y7j694t7Tp9yPn5EtLNnSuo3zcktmLRnGJ8chto3ZBEUf5WM+92vL3c2UW9MZh8+n\nDEcZKztiOt7nfHTC+fvHXD7f4/LFhIvne1xO9ijPobrwmLcBYzZgl1i1wNolaV0yKg1DLKPaYoiZ\n2QHT5YDZc1j0N2yWkC1KquUKlv02D1NYMJVPfnCkIxhNHMAcTFy75NYtkshtEAarvGKjAvzogLfG\n1XFRg6p8e3VNYGmvsJPLYDTBbyF1JX1jlykrA0usrZBu6GphL5PutbsD6i2kl7o6vX0Mt48YxDPu\nFDM+zZd8rXjM3vKS9VSzRrEuFJtcUWC9/ml9ZHJogncnE8sHecH704K7zwpu7edc1rfIin1Ohw/4\n4b0PmfWG1Gc1ta2pswqTF6ggNE15MkX5+tIYejX0ckXPKHolzE5HzMoR06uU2eOK9XRFdl5TvMgw\n67lTCmoff7/lu28ag9C2mKTtwo0cRHPftUw27CtCaYVtJn0M2p1fnPEbmo3odtXpTdSg0Ivi/Q+t\nATrHvYpWDKU7gYBbef5RUKb/9TWu8/ac928ppX4d+B1c7f0O8F9eO3DgHUfWA4ANH9jnVkHdh8oD\nt65A+YFvpYMIlyUNH87OXW3legdSsSU5gtFD2P+u4uib8MEPMz6ZXPFJ/JRPih+z1paVsawKWCnZ\nwsr6BLkH72b+1ygiFDGKiImBu+uCW9OcgxcFw5HGHMbMDvZ5fHifzycfcvH0iPPDYy7Gx5wPjjGJ\nckzDGswUqBZYrsBeAVdokxOXhrg2JIXBZoZiaSmeG4qepYg21GVBXa6oyxiqqLN4xdNOsk8yFhIN\noz04nMB7t8GkXlmx7T4f+jC3E3DQfFtXgnXtZUrc5j0lzbaD4kUPwbtLm4XgHfLZoWMoCm4sfUf4\n0pBaEHkdAA5DUKVMX1F6iQPvuyfw4T0GacLtzRd8bbPk5zaPOZk+dWsCC8V8CUsUGbZFBuzW/pvP\n9zLD/WnNnVPDrbRm3Tsks/s8G37M7w++x9ngEGsrR6VdSZSE8LWy2rNCSUexNVGliIwiKhWRVhQl\nFFdQ9BR5v6IuVtSbjCqbY7PI9ysT0GQ3gaLk4UrokNbYlbrau1Bo4Zjuat6CAbLwTjryht2gGtZt\n1yoMP++iY0NLrUu7vK61F1pUb9/vvkq0ya8A3wa+BfxTwB8H/vfWEdHm+iTcGleq+U3jtEDTA9UN\nqyq57vgKO8FNwO0qRimFTmr0QBNPDOkhDPZKRqOcvf6Gw2RJGltHBavrzKcYfmEztuFI0atBbaC6\ngs2pYpb0ODcjTnv7PDo85seD21wOTrgc3OJycMLF4ATb040lCTi+I9hVz2aOygh5v2UY/ywIe5Ps\nADE1gaiGREHaA9tzWnYNlOr6+AmrWy7XCuTx4K1LP+kmuIEj5nFFe0B329CGFws+74owCjtRGF52\nnRt+NYBHO46TB+6Wpys3XFvHECfQ68FwQJT26KEZUrNvNxz2lm69SdToMd11k68CgCQHPYPquXUx\nEJMel4M9ng/e4/HgAc8HJ5CWEJXOGtpqnrK3wYp2T67Z7oUupcnCPhauXrwBoJT/T4FzYOKOVdLe\nfuxa3HWsTLzBxL1dgyCjzXaques3gaYfiJUXToO79i65SUImIKgH7cEgilzSyj1TK+kmofwju4Ir\nJbsK+b+xKGo0taevwns3z7R+yW5RoXwV8P7PgP/JWvsvKqVinMu3LesvpTxNLlpcODPXylu+ypnp\nVe35bqFOMhpPcvetNeGsuIvTspjKUFxa1p8bokEFCxg8UpjHQ1aPTzi7yMnnls0aNqV770BogMmO\nA13GXW2rX9GvFfOV4uxS8SRRDKoej+e3eXy2x6PHCReHJYvzNeuLGeU5cFHCC+W2EZdQWLuiGWSy\n41JoRnephl0dOqzwHQOtLN3y8qtLIHbgnSuftLdgVZs+gcZ6Atc5tfWd1DjKpfRthgFvqzROoV10\nxkvKeOMzhW3bXbn5JsANbU5Wyid5GK3yMq2to5XkBmYZPJuBSlnHU07zmh/kI5LsLgfLiOUVrFaK\nVeWaPfdstOvRXVP8ulyWlrOV5WhqOVKWJ4s7/Kg35jyFordyW+We1d7DLfSETKCa9u6I4jtIO0m0\ndNE+ZRWsLBHX7eJ1WS1NG+CIwPRxvq2+63OyAGf7QgSxECXvVnnXwha6JKRTw2ilLh7skm59hyt9\nh84BPaRJPVx4TqJcHiun7QVJRQatDUobdGSIqImoiKmJqIkpSCiIMSTBQkEblOkHf/uG4nbkbaNN\n9oFfsNb+OQBrbYVTG9uy2QHeQFu39YBtNNvVgMZ6h6VUvDTQLuAOHV/dFvcVUynKS8P6M40tNOUz\nsJeK1cWI84sTvrzUlBtLsXEBGzct52nP4aJzOxBNa8X5SjO51ExqTbpMuDw75HK8z8Uk5nJUsVls\n2CwU5aKAxQoXO0izstfKSsUweLALWqEz5yZtRMy6HVKWbnc+IsdVk0KpXaoiqHwb1DjgttBEnIgY\nUKYB78o2NA3QjkCQcoYD5RVl3Cnh4A3jv4U3lWPC/GUiJnwI3lKukE6RMoemO1xvF+t8BtMM1Awy\nyyZa8LwyxOWIVXmXUTYkX0K2VuSV8puSKsSlWN/IvzYyLC3jlWGMYVRYrtI7PEkmnMeKIl66SXhm\nYeHbZVtHXfCW8D5Lg04Sly+OYwnZHeBCPyUENICN0FBqRWqqAMQ11In3aaVQ++18JapMAFxW+8r3\nIbvQcloPPD59AAAgAElEQVSKli0qVbh2YdeSt5dJ2D97/vn80v4kddGIhz5NgJ7yhrHyPli1XXek\nElBxjY4rorgmiisSSlIKUgoSSvpo+lh6VPRxUT+im0tE/k8UvHHs+plS6ldxW2L9A+AvW2vXraNE\n874mgaNIzCVZvr3NaWzLbdhPd01iSGJ0pWk8W1mKC4UpFMW5Yj2C9UZzvhky2Gj6m1Hzgo3KYdCu\n2Ja2XieN7l72pI0mXUf0qoh0qYnOYzZpj03aJ0sTNklJVaypipKqWGGLpK041LDl+a+FS9ngmRq9\n/2bwfgk4iuZd1O4NITbxZnMEJvaTKN5R6QHEdsGkxm3V6YFPJl8jZQpM8i1IQhuMQkB8lXQnr5CL\nDKmjN5kMRNMOo2NkEAs/G5YzBO8ucIfgvXH+g6uMjco5NYaVGfHM3CGpDqkLRVUo6koFbkMX/9FE\nYoeO1LYkZU2yMqRFTbI0ZNE+Cz1moaGIVo5my3FvGirlGYViEqoojNaB5lVwE58UjWa7xAH6Pm7f\nmhOHUluahAa8RXGXuU9oB6WgEuVAQx2xfenq1gDyg07Zpmg6+H0b6y2DBprFOhnNToJdfwrc3C/C\nttU4VN7DvczyNsR9B97HwB3cTrUjYKiadT8967f1sdCz6LQkSivitCROSvpkrTTCMqJkhGbkwduV\nVNr/9eVtwTsG/hjwF621v62U+hXcq9B+uXVUtmPR5bXOeT0prVFKoyL/2RqUrcH43LoFwOJwsVuw\nkgromFi1xU6hmjZ+7qUGdA+r+qAP2Ea/aoVJVXtstvqA73TdgVZrWEew3vZc2oM81Bhukl2m/y7z\nPazDXed3PwdS1lAK/SRAFe433LGKWpqJ3K/rYAr4aRUFZm5YT7vohm4ZbwLIlwG35K+SzsBQytOU\nFqWdVqpthLKRNyqCTU6tPL/BXiuT9DuLKkooKpivUShqZZnqmpnqgT7BKou1EYYIqzU2CazNbUx9\nOBbCMvt6KmuXtvUg2+lCE9LWvUZYzwLggozana9kMcsh2ygNKzv3DXDgLSjWD+ZyD+ISySmr3yPr\nu4S/rzSTzO1djBWDUsZX2GUUXqnJ2PY1Vbi+pqzzt1zbBO8mSjEQJfXtx6sd4N7EcwL2LqRDB9KH\nuPeFvUd7jhsDAwNDCwMLA4PqF+heQdQriHslKWv6rBmohCERE2vYo2TPFkyIiGwzcRv7GmUO5G3B\n+zHw2Fr72/7vX2fneyx/M/j80Kdu5+fad4M9y/CgSb2sIF3m22SLiroyVJWhrmofniz+c+V1U1n2\n4KqmrxpLpxdBtR+7dODyFSNWtklmE2FXClbK5YVx0RRl5XIT9sAwTC3kF3fNAG8iEvssSUxZGbg3\nOWG69wongPB8yeW3rjYvf4cvteouZvHOGh3RbN/pl+Obwg+6MMgyHLGh9qc699Sde5nOdcKNfELt\nvjtpyHXb19Q9TXyoSQ4U8YGmlxjGi4zRYsF4mTFYFZS1oqoUZa0cpb9VGVxMtt2CudsAyr2zURJE\nA4gOLNGBRR9Yyl6PeXXAvNpnXh2wyYc+EEQ1e6Rf6zPdibIOfheLVPbdqLkeI/8yusdr4VEP4qFz\nZEc4RaSKPcXRp7XJlPQZmdAUbtIJWSxrGge2Kp2VVnntu1bet+UjVbY5jfYtWnmrSeU5fUozGNcw\nGcL4Pegf7tZbwvyaTqLaKT+E1b57vd5aO+CWCEPZqSOoAnJwwILXvhUmjqiTxBkniSbTFrSm1jGV\n7lGVPfJywKqcMC8O0FXN6W//Ps9/5/dpheW+hrxtqOCpUuqRUupr1trv4+K8f/f6kb940xVoUwGh\ntqwY7FccfVBx/KDm5MOK8WzF6PmK8fMVo+dL7LIizwxFbslrE7gs1DZ61PihZbxpsqfYpnGsyI56\n5B/0yT7okT/oc2YTzs0+Z2aP3NyivErgXGPPIjjTsCwhy0FlYDIwIecRmqbybCGneoMWfE26WrZs\nkStLgCOuO2pf55rhYJYBYGm40BDkuqZbuDJWHFedndK0dilSLjcrqFfu2nUYwyvl3hUZFN6/q+0L\neIeg3w3fIrhOCOAhFdJYGLqvSW9p+h8q+g8Uk2HB7dMF751OuX16wQEzNgVsCsWmUGR1E4stuezd\nJ6skE2SjXZcnA0VyR5M+UCQfKtbjPZ5kA57mCWV2xGZxDC+sexNsDazFQgvbt/tiu3CshP4PqZNu\nvYncgGwqcsCdFJDW/m1ikXsxQpl6B6PsoQ9i7bp3Q/p+ERpFJQ6Qt5suecd77am5WntqrqLZlbBi\ny3mHeWvYhOCdQ2Lcuv47A7gzgf2o3T12GW9dIz/UR2JgPobzfTgfwIVujNEQvKWa5fF6QKrc/lmp\nxuoIE0GlFVZHEGtMHFPGKXlckm0GrNZjeuuc3jpH5QbqBxx+45/bvlbzpe+3CeSrRJv8JeBvKqVS\n4EfAn3+z07sRCE0+2Ms5/qDg/rdzPvhOztHzOYefTTlMpxyUMwwFGwVrY1kXlk0dvhVLkWO9Xuk0\npUhZbgG3FJxoOIoVq6Mxq4cjVt9y6Uu7T1THZPUel+YO9bM+5osI+hHWRKAL0CswS7e3NJKko4ZW\nRJewexPw7gKX7Cd8SBOGF24otesaYd4dzKI+dBcdSNlDIITGFhYADF+cMATVd+aneNxj5bQ2rNO+\nFW6QtjbCetmE1gXxsDwhAIXX2AVSHVprO/E4eNW9mPQ9xeBTxfjbipN9ePDDko8GUz6qH3N785zF\nxsddVIoFAh12CyGiHIju7RQwtY1X6A8i+rcj+l+L6H0nYn70HunqFuUq5XJ1BBf3HFda4ZyMGNqO\neVk5GFoe4fOHlozU78sm4m59W1cv0R6kOQxq17yRry+T4r4Iwbtyn23s2t3qpgiiS9TGW15rsHPc\n3jqxO8fGDsSRBT5inXkNXKJNrhW3q3kncHQIH0zgZw7g1mg35R12k+7SgcRC6lNi4awHjwbQH7gD\nKtrgLXuvybY8Kc5hmVgffQKWCL9fI4aYOo0pk5QoNURJTbSsiGcV8awmnldul7qNhY3Brm3g9H+1\nvDV4W2v/oVLq54H/E0istdejTW4+u5OLuM422M85+mDD+99a88mf2HDn0QXv9c55rzzn9vScuihY\nGFgUzuKUJSGSxA8tKcZyX8H7Gu5ruB1rZkf7zD/cY/6dfWZ/oiKyJXmVcFXvEVd3KD8bofox1sao\nVYytMqhnkM9AixkpwC2DKwTu3W7Ol4uAjagJsqx4ggPvHu1lxbtednHNNtyRSpr4xC6pH5rZoQkf\nAuAYR/7tASO2kQWiyeAHr/LaNyF4y0Y/ryMvA5/uc3aP6dIvYi24FbG6n5C8B8NPFJM/DsfHJQ/6\nBd+or/j27AkPLj7jysJVpbiK3GaNMl2vcQu3uhFIA8IXPMNoEDO6kzD8Wsrw5xLO72iKWc7VPOGL\n2RE8u+8G69zAM6mndXAnCVkUjTxs75BCEY38LUQlEK0dePdrH/CrXURImbrJ2YbL2kXF9sCNbWgT\nqX5loc6d9WVmTuGx4Z7WMdcnKV+LttsnRcr28enILTT7YAg/+x68f3ydXeoCeahlx0DPuNQ3zvH4\nWEHf78O01q4JQvCW4d7dFTZSWwetMUCtUcbNYW5Gt2532x6oqXXvE7lwOXPjwjrlfYblHwJ4e/nL\nwD/GocsO0UEeDrRdNk0DIMVKsTjTnH8RMzpKKE4HLB9NmJ1VXCzAZCWrAtZV8+7GZmA18CCs7lZn\nsM4yvawVy8WY5Ysxy8/HLPdHnJqIK1OzrtfU9RX28QYex3AWYecxbHLIF1AtXWfcruIKaQCRkAp6\nE/Cmc7wQa7Lnb7icOOS8u+D7siTaumzNKSqJ9OxuGQSwwwiMkGvVjalbWz9wl446sVJHYayxotEm\nd4GvCo4JnW5dOiHkxF92vfC6DS1hC0M1U+RPFZsfKObnhrPPE758PqI3O2CZvce8gHnld4KkCUiT\n1MYGtY0SlqC7QRExuIrpP0kY/CDm6nKP02XCbFlRLOdwduZok7l1PpVW2FuYwpckG5qNnuTFFd3n\n7PoLfH3IApqWcReBHjkALleQnUGxwe2Jo8D2aZaorXwbhBRUxHbrC+Mvrgqopw1wmzXN7oLSj7rB\nuLtU5VA6fb+qHJV5lsGjjduitpaIKU/RdIdeyPaleK3b+GThTMFUwUp7drJytF9eOss7qv0j2/aj\nhF3QN+N2DvLuKitG3xx3j6nPlxbWpkmvw4R6eWvwVkq9D/xp4D8A/s3dR0kPCVfKhSbgLhsHNnPN\n5aOEKLWUG82LK8vkqWbytMfkcoxZ1OSZ240vt9ff/d11kUXWWaUvjN8cslJsLvtknw/IVJ/NYsBz\nm3JqShZmTm1OsRcp9rnGnkaO/5qXsMlcJzHha4zCfcFFQjB9/Zm0OUdAOdybQeNaf5dt2LVkXmY2\ni/aW0sy50jbd6AQBdgEKsTakXNaZvOJ4qsX5dAVmDnbpATyso5DGuQl4RVOWUaZolksJbIb7ZYgK\nFJKY3agUgrIbTB5RvtBsfqCwRqNHNemThPLxHvOzOxyuYta523d9Y5p3nYRLQQS0paYSD+Db1w5s\nNOnziPT7EWkdsZoc8mXW42xTkGUXMFPw1MK5N523jtjuncIUWmRhLLqI1EOgGqqgbpVqN3ekQKWO\ni85XUJdusVFhfZy4fxFCy78TTq6yelI14E3pJ2+ftnROOBmHE7H4XmB3f5a6EXXMT3aXOTxeu0ni\nuSwE6vncKyJhtwrXGYk+EiuINcTW7UH1zAN4piCv/HMswSzcpKRtE0UTPk7omgnnoDCQKwbWyu2/\nsVKONshss6eQfTO8+Cqa918H/m2c7XyDhHyjlF4ohTAWOHxqy2YWcfHYUmwU8+cx/XVEb9ajPx3T\nmx1AZihLqEoX1tqNAA/98aLrDazXiAz0K0V5mVCqhHKZUD5NWJAwNxVzO6eyYFYRdq7dQpqFxnms\nSiiFo9sVjw3tyr+JHnqZyLECNLKlqkzjYU/Z1Vt2AfYujUYiWHZFdoTgrWhvKiQDWbTYDGwFtXdk\n6doBt5n7gRu+Od3SHvSh+hI+l7w7UJLGrQETDTwPzu++nFr+FmJS3oUZ2tQlJtMULzTWRJRTTdWr\nKKcps+k+T6eG4XJEWbnIv6K+vnVSs3zKtUNov2ynkI0mPlVElSa+1OT9IZdlylVZkJUXbhn6zMLM\nuBmi5Yjt3k0+C/KIjt8NL4uDY8S5rNmGxWnVmecs2NzRHNXSveapSl2qw/cuyl4hMnl22szgOXAF\nqqa1DfE1cAau8Rtd6YJ4eKwH76vC9bHFHAYa7Nif5i2SkCkUHWRrFslvqsmXwJXXije4fZpL/+7U\n8sJZELKyWOPyrt7RNbbD7q5xi+G2q5lVew57Qz3vbVdY/hnghbX2/1JK/eLNR3b5RgELCfjscpXu\n781cU2QJ89OYKLVEdQ9djdGVQZcGjN36NsKoohCiuldtTZgWzKXGLhX2qcakioqYylZUzKlYQ6Wa\nTQ0rxXaTJ9m7+hposuPObyrd8yUuvKbZk7hLuHW18K6Eg6Tm+lLobu+Se4eDpztZhDsGwjZiwFS4\n3QW7b0YiuH44mYfPEY60hCbCRqJsBLhls6GwX4kTNUxisViaCbax9kwOxYuYahqRfRGx1pZZlRKX\n+yRlj6g+2i7ytbY99bVhpRm510iqjUKdgrpUqM/B6IjSJpQmp7QXzkIpjdNAqrANX5ZkFYwsnOkO\n4ZT2mu5ggpY9OFr6VA3luU8rl5s9sHsOBG2fRklZ4JCtw7GHi7isIJhxk/k1kA4AeCfdR5DvGl8+\nCXgv1nAaOwvCysQ/cIeH2+PIBh5h6io6srhp6xetIFvB5gqyU6jmDrClDF22b1sfO77fDh+FW9Am\nUTe+3Nb/9gbytpr3nwT+rFLqT+OXJSmlfs1a+6+HBw34u0jHSfiElK/7v8OVcW4n47Bx49ptwBNX\nEOdgUk2VxtSTiCr1GrNNKG1KYRNMHV3f2132A9/ufCadyf8tykRLTHCRV4mAjNduVNS22gVXuzNL\nmKCD+6ZzILgWFy60pP2uvjg4Vs7r+hfkGrsoLB9HLm/q3sYI+xlRCm7DhwjL6Xn38N2CVmKown2e\nVZCLdEGpa70032sNg37BoL9m0J/R611SZz3qrE+96VFnPSwDDH0sA+x243+3R4fdLl5pJjFdQ7yJ\niLOIGI2ONPXAUvehPoSq16M0qetjJqE0aTtir8Ahuwny7iReWQfKm10gnO/4znbar2uXa4j3XEr2\nId53bdcSccpKShvQVpHTMFtsUw3rtYttLnvOSbl1mlc72lHu1+1fAp44DVz2v9EWIovqVdCrfF7j\nXgZhUMqicQG9ch2L9pGCaqugofzdlEUpC2WM3UTYTYVdr50Wu6174yiOELgjGkNMnGRhVwMXJRWk\nNC8Z5Ev65TmD8glxdYm11iUs1rZrYFtGGveCMFVNk3orKNJuh08U6/pLNvWX2xa8fB344S3B21r7\n14C/5gqp/hTwb3WBG+Bb3Eemebd05vsIbSIbrNpAG7I+H8Uw7sEohVEPiv0em8M+64MBm8M+i2jC\nvO4xN3vM6z2KTa/tBFgZtwy8LFxedXnD16ydl4pM5T62IOq3o+jk1Xu7FgWGeym1lJDusv/uHi4h\ndyuu2O7gD2ePXZEmISgYP8hiXMifD5Gy0MTZGlAy+YUafBhnLea+eB7E6xBqVIFG1vIR7DDBtzak\nc4zGMRwdvuDOrWfcvvWEk8PnbF4kZGcJm7OULE+obUpNSk0PQ4qlwHoz3157yVxNimKoNEOlGaGJ\nehH5rZTsvYTsdsLmsM+86jGvhsyqA8pyzzmb5GUXcxyfIiseS6kf23nOLu3RtZS6qll3cg2RNnZR\nFuOxS6MxRJ7b3Wp7IZXkKSm/4932FmEXUQqmPqKpFF+ClElmKmkv0eTZ0Z8IzvOXib252zeo4wp1\nXKKOK/RhRawqt1GTqoiUo07digwH67WJqExEbTWViTwIWr/pk4WVxZxazHOLee4W7jUW6hroX+9u\nYWBYGGW7bbIB7n0CLg2qktvVgtv2nDvRY4a8oDZQG0ttgnXdKui9yhs3Atp+zsSvYdty7BJWq32j\nqPe3iP+rP+K15KtGm4SPf00+5Atk4ya37qxh9W2QQF4B5aJmj2I46sPRCI5HsL4zZnZ/wuz+HrP7\nlrNkxIuqh60OWFe3KaZDeKrgma8UVUPm+bk63BtQtNg/CBHwPgKOQY+brREO/E/S90VTCz2robIp\nSs2WI5R8QxNDIxugCKhJxMUuCUEgHPwJIYBB7XtfDLoP0RhI2xqlaGBbEzhcihw+QBgAG5J43TKG\nJscuS0HRMMwuvDCODMeHZ3z04JRPP37Mw/tPmP8oZpFGzPOI+VlMRUxJRIn7bCSqZLukJgzdNAwU\nHCrNgVIcKkXaS1jeGrP4mRHLT8fM7sPz4pAoH5EXJyyy99xiGkng3mG38dZGVTYW3rZ+pU5Ck1C+\nlzroRs102yv0sPWh14e9Phz34XjggKCl8Hd9TFGjFkoWYq5R7trVxG3vwIBw1YTLJdZfwLs7wXTo\njharZVETi7pToj90KbpfkqqCRLk8VQVO/9bbvDQxZZ1S1AnGJKBAy059UY29LKi/78pn5xvsTJy9\nfmdOm7bHmNRRGCgVisVRRebIUxoDBrbkDks+5ZyvxY851E/dPF1BaS3GBpQ5/rMOksJvVuUNpBi/\noEd594wH73AG4CcM3kqpD4Bfw632t+x6EQPwkM+3bKD8czNs95+rPev/vxvD3T7cHcPdA5jfO+D8\nk2POPrWcfxoz6BlsmbIq9rko78CLfZh4UyTXzsvEwoWsld3tLa9xJW8pIXjfBX3YgPeJz4WaEdBe\n0SjLoWd1O/WFdp28usnSOAhl8IdaT5caCSM4hNoJnX/NetSt+qFjZzlEE1wwKk2hjME5aCtQQouI\nFt3WkK/F7LqL00aXUDPtcpwqOEc0+ZQ4Kjk6OOPhg2d891uP+fanX3KRaC5zxcWZ4kJpcqso0H6V\nrcbsUBDCyh4Dt1HcUXBbKfq9lKtbR1z9zCGX36s5/zQl2iiKbMRscwKrD9z7ozyd6qh3/4q5yq+8\nbWnX0teEQJW2CjfREkspDEkIna6yb4nsgjR0i1P2EjhJ4H4Mqe482i7KRap3B6daAVXPAXc68F+c\n00w4UxrQHuA0k22oBu0Q0qAZBe/7wNig7pboTwqib5bEXytIdUZfZfR9bjxoGyIMmrzuoaoepupT\nVX2sxu3UF9VEcQ3PVsAldpZhHou2vQrKFF3vbmE3Dd07Wzn2/HMf7D4DXXI7WvC16Iyfix5zRz8i\nx25fPOWXKzWh3h6LI+1T5ME7bZIso99a6d0XCOxoopvkbTXvEvgr1tr/Wyk1Bv6BUuo3rLW/Fx40\nYH3dicPNbhl8PlIwiWA/ditgdT+nGBZkk4r1Qc2gb0kLTVzEqKIHWd/t9NX3PFJUQVQ43qsVciZe\n+jD6oXv3MH+ZSO/0GpHqt6O0ely3nsO40C5ebSU8oUc7vonOSd0W74aJ7XLmyezheRvlW0PJZ9Mp\nV9j7Q43SmxSqhKSGxKISDUlEUhmSqiapSpK6xBrHExrrXu786hqX0e/SWJccD55z7+AFH90542sP\nLnj6PCF9kmAOErJhSlRBXFsiA1EdLlq3mB1OL1lQM8GyBwx0jzodUA6HFHsl60NDrwfJRqPTxE1u\nI9oLDiN89IHUi6bdp0JnbKiOBpSTStopbHPVd6W0gZctUS4mWebitL4+N75Kut1+2ycVjd9DnMOi\n+MjmV9LvXwHekmtclECawKiH2qtRhzVKb9AqQ+sNkc5Q6FbSdR9d9VHVAMo+SiuIK1RSo+KKqNDE\nx3PUSYk6nsNs6vdPadKW/bNsF212RbU+b3CcukKhuZVccJIsOO7nHPUNh0C2seSbmtwYqtoEa3Rs\nC8Rlq29Ho6jmfQ0R7scEvy+4r/ct5/Ia7Re0xBuLtfYUOPWfl0qp3wPuAS3w/pwHu9waN4K2fF5V\ncLmBZ5F7Lefq6YRptM9Vsc/VdMiLRHNW5SzKGVX1DC4X8Fi7FVKXyq1Y2qyhXNPEZAsYxji1uO6k\nrjcxHAW7uEkhtedABPWiUZbFORI6twraL/oIlbTtrUKtONCMGeNGatdTLyeGGmsI+ALe4d+hvqBx\nkSJLF+onJnIr8CEAbCugHZRTF6h94DhBHSWo4wkH80uO55ccz6cczy+oi5q8tBSVe6t5ZbuxH10Q\nD2mfiImtuFWdspdN3cZkc8W6PuCid8zjwxN+9P4JxcpSbizlxlBuLMZUuDePukmm6xQfYpljObeG\nx1h6ecL8bJ/5j/aYpxOmFylPc8NVviLLz2ATwzPgKY42WQDrwofW+Y24rk2esjxPLKBwQZfxjxn7\nFLlcpaADMLduRaiL/NBOKckyF+NM5qJFtl3BBtq3yA40CCu7Bs6t67e5/HCJe0uILMoJ1xpUNLOX\nkOede4TGmAKWGnuaYkcpdZ3AVUqhQSmN0TGVTh1dohRWCW2SkNc9qjrF1DEohYoUVRxhI7ft8sE0\n52A45eDTU0b7L5yRMFMwU9ilchvW1c5nLKvOuzXTmmf0lEhfofUpkf6C/WHB5GDJ9OCAf3TwHX5o\nH1BcbiivMorLDaYoHNFjDZGyaGvRppmvtMVPBAqMQlUKauXCBTPlVnFGgTNZeWcmf/96m+2Qr8x5\nK6UeAt8D/o/ub1/wQXNckN+kdW27TgXPMr/1ewWZGrDOh6yuhqyeDJlFmitTsKynVLVyL969VHCh\nXL9bGTeoipxmY6SQO0xpew67jsKQzwgBMkyxP3YBFGBiB8zykuolbV+V0J+CfcI4tByW0uPlBFmM\nMfa5DJ4QiFqtQTsssxta2A3NU44SMX5LO3vlvwvKhmUbpbPltgOHqjZwMEB90Ec9HKAeDjg4zXjw\n7AUPn1/xsfqSYl2yymCZWVZV+z3HEsfQroo2MTu2hlvlFZNsSrrKsHPNuj7gvPchjw4/5vvvf0x5\nZamnNbU1VFmN9T4D29qov6nb1Nac4V5qMMES55rN2ZBNMmCTDVk96nFV1kzLJVl15mL8r3AAceXb\nOfeB4JVMbF5T3tIMsrBJnIh2+0yg3GCNnLVC6nMdORpL+8829cCdgo1AV5Av4WoG6xnoMgDubl+F\nneANTbc2wMK6lMsPEuYZgneojYcmZIeakUsIBW3BLmPs6R7G7GPne9gnLgLG6IhKpxS6j1WqlSob\nUxmXrImxyhHKNjJYHRHpiGMKHo5mfPjJKSf3H8MTnO9LgS2Ui9H3xSjMbpIu7GmxGhLr58TxhCSa\nUI8G5Mc9prcPeH7nNqWtqHpzajOjWs4wrNG2RikT5M4Qc+HgAtwaVbktrh1wR85XkUQetENiXPOH\nAt6eMvl13IsYlt3fP+dB+3ifdy277t9p5XZ87JWQbqDKYsqrhPJJQjmIybUmMzmZnVHZHIq40Wo3\nyq0Oq2uXjJizMoAOaQjpUNPtehdvAm/psNJD5y43pqF7ZdvhrjIfMiK7FOgWalocEMiugsf+syC/\nTErh1CeTSncL1zAVtDWmylkntnAUCKYzm/oytcIFAzDXCnUQoz7YQ39rD/WdIw5+/IIHo5pv6ynf\n3XxJrgqmWK5quMqbdanhQv+QmGm0b5eG1nJSZexlGb1ljl1o1tUBF70HPD76Dt+vvkcdG4ytsFmN\nURXu9dFhvHnWumtERUpNYg2prdE5VGcx1SahfBFTDlIyU5OZJZmpoJ63X+uYgQ898GqdwU2y0FAP\n0g69oA8F/LaKnG2dKuhp58CKvNNdchvhlnprlxsfe7y6APMc9/alsH122bo3iJxS2Ca5L2jHRcqk\nLablK0ha6SKSVynW3MbMY3g2xgxTjIo9cLvXhqHxAO1y2d9aEsrtj26023892tMc38/5+N6U7947\n5YH+0g0TBawUZuagIMOtf8q4GbRlRCcqIY1SenFKmqScj+7yw+NP+NG92/zw4SdcmD6mPsMuzzBn\nZyMazLgAABSaSURBVFhmKGqwFUrVKFu7MHChSwyuzaoIpSVUM5ycfYiu6q67eD35KsvjE+B/AP4b\na+3OPQwf8YPgr4e4F/C8hlT4pbledm55JQNx/hoXlM2dYtwAO6FxDobL3AXEdwVpbwk8n4vnw4OD\nyf088AakFXDdkAu7lMzEI1/mUVDGcH+TcAYIgXpXTG7IweI0b5a41ZCyf8qbFD+G8R7qdoT6aIT+\n9jFj3ed2XvPxfM4fefGcTZFxVsJ55raPkAXT4XYGNxFWAD1r2Sug5zepy656zPIDzqL3eTz+Oj/m\nj2EK49ayX/mFQixwHUfS+vpdbbCKsTBwgUsttVR2zdk+8Es+WxqfigB1tz3DgZq0v+6rptlkfg1n\nNWNhnUO2gNUlrE6hltClLnh3Hdovk27td1vgDfuEgLa4lvI+dpVgGSNRUrXWL49i3VXs7XsxQd+1\n7A1z7j9c8PX753xt79Q17RR4CiZxBviqdivRJdYsTN3b9xT0taIXQT+GHw02PNq7x9WtPX7v3tf5\nwhzB1VM4fQbJHq6zePvRii3Zqb46pJfE5xFGFPWAHwD/kPZCuVfL20abKOC/Av6xtfZXbj7yz/i8\ny26H0uWWoW1I3+BpeCMxuAG7oNkfpBuWF2rdEoTd7chhzwoXMITgHibYTRjJs3YaVkUODLXP7Rjs\nBLeVZuG0r22URneFZRhXLXUXPofUqey9KGaxgNpbrM8FByjTHPtojpm48KzpF0u+/Eyx92wfNb1P\nviqZZTCt3GrwDZoCRYmmQHs9vu1kDOs/NZZsCdMzOB3AfpHwu9k+jzaK2WaB3TyFM9wy88x4LTTY\nS3rbh4RLF83YsDN88sYl292BGMbTRzQ7LQ5pNo2SSVbaJ4yGiBqmTANWXb9sl1rLLqCYueXs2xWF\n/197Zxcj2XHV8d+5ffu7Z+djvbveHa/YBBPbcRzbMbINAeEgE2wJghQhkUhBEQ95QgTxgDCIB78h\nJBAgIV74iCBSEolgkC2hyAYcKShSYid2svnYxBt/7m52e73emZ7unv669/BQVX2ra3rWMxOP5o64\nf6lUPbe7p8+tW/WvU6fOORW6G4ZyhrSFR47KdCmhoR/rvJWn/z2/vhHccnQdaGffmeZDsZciu4KY\nWYl68EQY9tu02wPO/6hKPTpGuzEwiakvmp9Jhyb30SAx6UN8fx93F+F8EStUEjErf+BS9wTnrzZp\nV2GYds3zutA3kZ1DN35Trw5dWHw+c7/qxq2f+uF9wF3ejf7LDtp075r3B4FPAN8WkRfstT9W1S/N\nfsztUOucwjZ1OG2/E+StGIJyWrojqzAril/mdU5fo3FGPaf9QqZG+WaJsMv4/9e3T1tfoqgCpbKp\nXZKdNLa2e/cbjoAga6uIWTOKv271Szcozpzg38cukCq6PoA3NsyfnSFrV7u83o6gfYTO+i2MNxP6\nA+iNhb46o0VWzFlH5pyaWdc+Q6pxoqx14XIbllJodGJeGy3y+khYH3VhdBHWI5OHZiCW1JzPuU/e\nru2UWc8Q115h9FSIqfMys/sKrnZBW3WyzUpnM+7bNg76hGcbJpGtOkA4bMZdGG0Y98SZPY7t6tA+\nHQXG39QsZ+hgJnXXD1wf97X5sB/P09LnIbVt4PLTuInHCpGCOdxBTZ2GfODLa+pB7zrtKwNeiiqM\nNo/xalXgMshl0DWj64wnNi9NOhvQv535pJRCnArxREyequ4JXnuzRTuFQX/DyHelB2+N7f6Arzz5\nD4ygToNrzpTWJFMkXdl5HMpevU3+lx3p901mNb9wNt+O0P1IwlBj3QvczI/932430de45hmkYfa3\nw87rlt1OTqfxuMETmkHC+w3c+KSGCZapGtc0jYw9VVOQkV3mV73fickmHieXfy9O+/ZXFCF5uw7j\nE/8u4DRvOtAZohe6rPU2oCt0uke40LuF1HqajCfCSIWEmJQy6bQ2cvuHjPn3EKUp9a45t6DWg0o7\n4npyhLVEWE82YHIJhjEMYrMZlMbes3Far3t+zqbokxJkfUTJgmh8uO/64ee1oFS912WyAdnDEJdL\nkmXHg+qsjjKWt5/vk7EtE0/zdv1onixesI6/LJ+mh02AN01fkwS077WXTzx+X/YF2sn4dNr9mm0P\n637oH3A9dVmd53+kmQgWw94m7faA8WaVN6/eRDNuZAvKDbOIcNsR7kDx0BLjN7FgFP8oESIVokTo\nd5dY0xbXezC8Zk9i6PahO5pD3r7cPlmH1gT3PefD74/PDXZjovpJbN6PAH9tJfkHVf3zrZ9y+aLD\nG4StRBYSuxu87wSc5j3GDCR/hgxlmWd19ZeO8667JZRzCfOTcPk25vCeGxhNzYbYSxOiOpQaUG7Y\nzdYe2bFikD34svcb/ij3O5Czy/vF9XBXfKLaG3nr2hA6IzTqQiSsaUonFS7qIlG6gNoBanJVGMLR\nmSyA4Puf6JR4DZlLkiJdkB5Tb6qUCokKKRuoDjHeGF7ZQjKQ6Rt+7YprN6cKz4NP3s732g+imWbn\nJ9scdn3uOll726KJN8eG5oxtoFNnYUzaU5eIyWn9LiGVn6chiLh0ECx5Wy8m3SRb0bk+NM9S7L+3\nG817ZNugxPSw5WlSK48fZgh8vnY/SFLamylvXq1Qio4h6BYdUcm+Ok/KLU2tYA5SMDLppEbSb9pc\nUnaVmo4xHlow65Xg2jFsl3ny+5r3JpkS5VbCO8Nebd4l4G8xZ1deBJ4TkSfDIJ0s+c48G7Z/U6Gt\n2IXi+tqwb9KYt8EyT1PGu+bLEM65rlMC09Sn4e7J2ywdpWS05ahu62rmMRBZl7Dp2Xx2aZjWIalD\n2jB1VDeaN1VIykbjTt2g6pDZ2d3hDH7Ah2/68dsrCM8uj6EcQ7kF5Rr1qM8CG7Sky4JsUErGpCOy\nkszXLfwWN8vNjLKShTJJKyZplUkWYoZpncGkxnBSZzCuk46rMCzDqGzqCXZAjMkOLfYd5CeYI0rU\nqFMzZg8XyRj2lXkTrV8coTlNFTJic+3pfy/sS/P6Ztg6/sB0WnLsfQ5zXcn61fS1j3DfJFQa3ETt\nNHv33F0mSkfafkCN/Z+agK5ZOV0KhlD79VeVbnzMU3Ts6ygyfutxDHGJUhlatR4LtT6t2hrNSt/u\nIgrSN7XaSBq1ueFN4qcsAVQ4rqUM0rKlCZNqma626KYLdNMW/aQO/cSUXgqbswrB3NVVpQK1KlSr\nptYajOswMoFCTEp2dTLJap0wjUBWn5u2aZ/4CJSXTWKxcgvKZSinJmCnXIJoFETLbI+9at73A+dV\n9VUAEfkC8Bts+Vk/ddd2JhMhc5Epe699rdXZL513SEhUoYZ+I23Af883aYSbUHHwet5mpK8tRJiD\nXOumVKrGd9flMihLtn5za7lxFUYVW1etxmj9eSdiNbMh5hipNTLvFqexOvPAvOLIJfDLLpdtxq8W\nNCs047c4KQNWoz6rcpnasMe4C+MNk6donGzdDQjXUNWgjI40GK66Umd9UmNts85af4Xx5gpptwqd\n2JaS2VGaeMEu040z/wSZcPC5Zxm6Szoim6fC+v3PLVtrmNSqPnGHG3f+YHRy+C6Xrp+mWTvPBDM5\nn32XRNp9fl4BtigWvsLgr6bcCiEhGxdOe/bHkj+e/EkCK/M66DqZX3c4TYeeMr7FdI5tR0pQqUGt\nBrUqcVNZWf4xq8sdTq1c48RCG2kDbUHagrRBExt9myqapFa/sVG5ChqM6agK0TGITkLpJAwWG1yc\nrHIpWeZScpT+4CZoD6E9MmUzXIHOIe9qGRZbsLwIS0dA69CtZGUYWRfk1JbEjNHUuSS7vhhO4l4p\nN6C5AA2bWKxZhUYJmjVoLBjlap/JexV4w/v7AvDA1o/1MW4wt8IW4nZws7rTTOpsScZDnxmD1nQj\nKtSAb7ThFhK6+24EvALcztYNH7+EXgYwQ5aOvKsNqDWgXrOmUTGlhqcgq02OUzJ22s3Y+HxOYuNa\nlJTM5lWaYE6q72Hshd8E7mQ2LNknmHDGn2PTLy+aDrO8BMvLNCvCyajNbdEm740u0+qvMbhmDlMZ\nDmAwnPXLGc3eNcrsgv0SPVaPnKJ/epHeHWP6d8CV0RJxp8a4s0yncwqu1aEdmVQGackMABkyPRSA\nAdkBgm6C9Qn5Rqa3CTfejlGMW8L77f+rY8jbRZ+6PBlOQw5/x5G3I2d/debI04/qdcqB6z/hZmeo\nNEBG1s9j9CTf3uxcOt14cPluHOm68bSdH55kOtNUo7Uyq8vPEipaM/6M3v8X4Bzw3tl2ispQaUHT\nZEAsLaWsrHY4c2rC7atvcevRV5FXQBpAKkgHmw5eDYmjngu9ksyxzkgV4psgfjfEt8HG8UVa4xV0\nHLM2Pgrd0/ByH6QP176G4aCeldk9l+CfVsuwtAA3H4WTx8yK+K0SvGXHZ1dMuOZYTS1uJZgyPWBg\nC88FY7FcM0S95EoCyzVYasH1r8BtPwtfYEfYK3nfSLX10MM83FM3+GqEIWl/82WBzBa8gOmoNSuu\n63n+0s2Vt7PBzSNwAV7GuOpMM8ewVZ/0A19cs3n6qAjETag2odGEVs27BTHMNrVgqN3HEnNenjuB\nBMGcGyhG805Tq4X2rOb9InDMk3ueXfdGtUK5acl7GY6v0qwPOFkqc3upz/2lyyytt81xepvQX8sc\n7lxxOovvk7PolZcYcs+isH56zMad0HmwQmUA42s1Nq4tU7p2Ci7ZHB0p5lio0cQQRzKEaABJn4zY\n/BWaT9DePc30Cbx6O5wD7sD0PUfedTLi7pBF0PpKgf/7Y2ZJUjCE7btiusnBzxVc9167Pr2dh9Ln\ngI8yS8JrWGd0ZonbTa/+qsRhTrvMDIVwkzvsOyF5++6JPwIeZOZZRBWoLEFjCY4sEd+UsnL6Dc7c\nOuH9t17j3lOvIg1j2pYOyCVrorPdP9Fs12OipmxhjSqUj0H5p6F8N1z/qWOkwzOsD8u8PjwKa6dB\nNqC/AWfPA/eREfc2yemqFUOiJ4/Cu09B0jS+95Ebj2TztTihbC1zzEfAFgWqHEMjhqUYjsdwXOF4\nCscUnj0Hd390vmxzsFfyvghe7Lt5fWHrx/4Lk50kBc7YEmLeDO9I3G0GJRjqcNrKdj6sO0XYsV3x\n7Xp+Mit/197VMGO+EcEkp6pBXDOmE/dVN1ad2L6iNppzfapI+mYA587nTqbZIyK14dhVaDSJ6zWa\nJWGxlHAs3mRl3KVXhV5s5hWXHNSV0GiVYvLMLWFiVxvA0UqfUmtIaXkEJxKam1CTmFirSNKEjWaW\n5KkMJpGYHSRANsD8cH6/gfxGCrWdncC1q3vm4QTtk3ISfC9c0fg2VD/3b5+sP7nUBs406HeMMCLW\n748VTEOFJsRwVeJWBL6r417a5UYIzYth4InfPhU7DupQaRLVEqqtmIUlZeXokBPHN5BliBbMkJHY\nLDKT1NZiyhjDme6OfJRKRomtLED5KJSPN1kaTGgMhfKgCqUWLCRQn0DknrH/bOcgikwCrUYNFmxe\n7w6zw9/tS7rmcN1oWwQr3ygy468amaPbmgJXvgzf+jKc/yo88Rc7ehpsfxdvi+eBnxGRMyJSAX4L\neHLrxx7CELarCxQoUKDADG59CH7zcbjnIfjU4zv+mqjubWYWkUfJXAX/UVX/LHj/nZryCxQoUOD/\nFVT1bU0JeybvAgUKFChwcNir2aRAgQIFChwgCvIuUKBAgUOIfSVvEXlERM6JyEsi8kf7+Vs7hYj8\nk4hcEZGz3rUVEXlGRH4oIk+LyNIBy3haRJ4Vke+KyHdE5NM5lbMmIl8TkRetnI/nUU4rU0lEXhCR\np/Ioo4i8KiLftjJ+PY8yWpmWROSLIvJ9EfmeiDyQJzlF5Dbbhq6si8in8ySjlfMP7Jg5KyKfE5Hq\nbmXcN/L2QugfwXjxf1xE7tiv39sFPoORycdjwDOq+h7gv+3fBwl3RuidGCfa37Vtlys5VXUAfEhV\n7wHuAR4RkQfImZwWvw98j8zrLG8yKvCQqt6rqvfba3mTEeBvgP9U1TswkU7nyJGcqvoD24b3Ypy7\n+8C/50lGEVkFfg+4T1Xvwjh9fGzXMqrqvhTg54AveX8/Bjy2X7+3S9nOAGe9v88BJ+zrm4FzBy1j\nIO9/YPLI5FZOjIv3NzAhgbmSE7gFE3TwIeCpPD5zTJjv0eBa3mRcBF6ecz1XcnpyfRj4St5kxESo\nv44JjYiBp4Bf2a2M+2k2mRdCv7qPv/eT4ISqXrGvrwAnDlIYH8EZobmTU0QiEXnRyvO0qn6d/Mn5\nV8AfMps/IW8yKvC0iDwvIp+y1/Im47uAqyLyGRH5poj8vYg0yZ+cDh8DPm9f50ZGVb0I/CWGwC8B\na6r6DLuUcT/J+1D6IKqZ9nIhuz0j9N8wZ4Ru+O/lRU5VTdWYTW4BHhCR9wXvH6icIvJrQFtVX2Cb\nWLiDltHig6p6H/Aoxkz2i/6bOZExBj4A/J2qfgAT6jmztM+JnNjgwV8H/jV876BlFJFl4CMYC8Ap\noCUin/A/sxMZ95O8dxhCnwtcEZGbAUTkJOaspgOFd0boZzU7IzR3cjqo6jrwLPCr5EvOnwc+IiKv\nYLSwXxaRz+ZMRlT1x7a+irHR3k/OZMSM3wuq+pz9+4sYMr+cMznBTILfsO0J+WrLh4FXVPWaqk6A\nJzBm5l21436S9w5D6HOBJ4FP2tefxNiYDwwi254Rmjc5b3I74iJSx9jtvk+O5FTVP1HV06r6Lswy\n+n9U9bfzJKOINERkwb5uYmy1Z8mRjACqehl4Q0TeYy89DHwXY7PNjZwWHyczmUC+2vI14EERqdux\n/jBmM3137bjPhvlHgR8A5zFnXOZhE+PzGDvTCGOT/x1gBbOh9UPgaWDpgGX8BYx99kXgBVseyaGc\nd2Hy1H4LQzZ/aq/nSk5P3l8CnsybjBhb8ou2fMeNlTzJ6Ml6N/CcfeZPYDYxcyUnJpvXm8CCdy1v\nMj6OUXTOAv+MSX21KxmL8PgCBQoUOIQoIiwLFChQ4BCiIO8CBQoUOIQoyLtAgQIFDiEK8i5QoECB\nQ4iCvAsUKFDgEKIg7wIFChQ4hCjIu0CBAgUOIQryLlCgQIFDiP8DD/RVkrAIhzsAAAAASUVORK5C\nYII=\n", |
| 754 |
"text/plain": [ |
| 755 |
"<matplotlib.figure.Figure at 0x7fc227c5acd0>" |
| 756 |
] |
| 757 |
}, |
| 758 |
"metadata": {},
|
| 759 |
"output_type": "display_data" |
| 760 |
} |
| 761 |
], |
| 762 |
"source": [ |
| 763 |
"plt.imshow(chroma.transpose(), origin=\"lower\")" |
| 764 |
] |
| 765 |
}, |
| 766 |
{
|
| 767 |
"cell_type": "markdown", |
| 768 |
"metadata": {},
|
| 769 |
"source": [ |
| 770 |
"### How did we know which parameters were available?\n", |
| 771 |
"A bit further back, we set up some plugin parameters in a Python dictionary:" |
| 772 |
] |
| 773 |
}, |
| 774 |
{
|
| 775 |
"cell_type": "code", |
| 776 |
"execution_count": 14, |
| 777 |
"metadata": {
|
| 778 |
"collapsed": true |
| 779 |
}, |
| 780 |
"outputs": [], |
| 781 |
"source": [ |
| 782 |
"plugin_params = { \"tuningmode\": 1, \"s\": 0.9, \"chromanormalize\": 3 }"
|
| 783 |
] |
| 784 |
}, |
| 785 |
{
|
| 786 |
"cell_type": "markdown", |
| 787 |
"metadata": {},
|
| 788 |
"source": [ |
| 789 |
"We also included `output = chroma` in the `vamp.collect` call to make sure we got the right output from the plugin. How did we know which parameters and outputs were available?\n", |
| 790 |
"\n", |
| 791 |
"Outputs are pretty simple, there's a `vamp.get_outputs_of` call that returns them directly." |
| 792 |
] |
| 793 |
}, |
| 794 |
{
|
| 795 |
"cell_type": "code", |
| 796 |
"execution_count": 15, |
| 797 |
"metadata": {
|
| 798 |
"collapsed": false |
| 799 |
}, |
| 800 |
"outputs": [ |
| 801 |
{
|
| 802 |
"data": {
|
| 803 |
"text/plain": [ |
| 804 |
"['logfreqspec',\n", |
| 805 |
" 'tunedlogfreqspec',\n", |
| 806 |
" 'semitonespectrum',\n", |
| 807 |
" 'chroma',\n", |
| 808 |
" 'basschroma',\n", |
| 809 |
" 'bothchroma']" |
| 810 |
] |
| 811 |
}, |
| 812 |
"execution_count": 15, |
| 813 |
"metadata": {},
|
| 814 |
"output_type": "execute_result" |
| 815 |
} |
| 816 |
], |
| 817 |
"source": [ |
| 818 |
"vamp.get_outputs_of(\"nnls-chroma:nnls-chroma\")" |
| 819 |
] |
| 820 |
}, |
| 821 |
{
|
| 822 |
"cell_type": "markdown", |
| 823 |
"metadata": {},
|
| 824 |
"source": [ |
| 825 |
"Querying details of a plugin's parameters is a bit more tricky with the current version of the module. You have to use a lower-level interface for this. It looks like the following." |
| 826 |
] |
| 827 |
}, |
| 828 |
{
|
| 829 |
"cell_type": "code", |
| 830 |
"execution_count": 16, |
| 831 |
"metadata": {
|
| 832 |
"collapsed": false |
| 833 |
}, |
| 834 |
"outputs": [ |
| 835 |
{
|
| 836 |
"data": {
|
| 837 |
"text/plain": [ |
| 838 |
"[{'defaultValue': 1.0,\n",
|
| 839 |
" 'description': 'Toggles approximate transcription (NNLS).',\n", |
| 840 |
" 'identifier': 'useNNLS',\n", |
| 841 |
" 'isQuantized': True,\n", |
| 842 |
" 'maxValue': 1.0,\n", |
| 843 |
" 'minValue': 0.0,\n", |
| 844 |
" 'name': 'use approximate transcription (NNLS)',\n", |
| 845 |
" 'quantizeStep': 1.0,\n", |
| 846 |
" 'unit': ''},\n", |
| 847 |
" {'defaultValue': 0.0,\n",
|
| 848 |
" 'description': 'Consider the cumulative energy spectrum (from low to high frequencies). All bins below the first bin whose cumulative energy exceeds the quantile [bass noise threshold] x [total energy] will be set to 0. A threshold value of 0 means that no bins will be changed.',\n", |
| 849 |
" 'identifier': 'rollon',\n", |
| 850 |
" 'isQuantized': True,\n", |
| 851 |
" 'maxValue': 5.0,\n", |
| 852 |
" 'minValue': 0.0,\n", |
| 853 |
" 'name': 'bass noise threshold',\n", |
| 854 |
" 'quantizeStep': 0.5,\n", |
| 855 |
" 'unit': '%'},\n", |
| 856 |
" {'defaultValue': 0.0,\n",
|
| 857 |
" 'description': 'Tuning can be performed locally or on the whole extraction segment. Local tuning is only advisable when the tuning is likely to change over the audio, for example in podcasts, or in a cappella singing.',\n", |
| 858 |
" 'identifier': 'tuningmode',\n", |
| 859 |
" 'isQuantized': True,\n", |
| 860 |
" 'maxValue': 1.0,\n", |
| 861 |
" 'minValue': 0.0,\n", |
| 862 |
" 'name': 'tuning mode',\n", |
| 863 |
" 'quantizeStep': 1.0,\n", |
| 864 |
" 'unit': '',\n", |
| 865 |
" 'valueNames': ['global tuning', 'local tuning']},\n", |
| 866 |
" {'defaultValue': 1.0,\n",
|
| 867 |
" 'description': 'Spectral whitening: no whitening - 0; whitening - 1.',\n", |
| 868 |
" 'identifier': 'whitening',\n", |
| 869 |
" 'isQuantized': False,\n", |
| 870 |
" 'maxValue': 1.0,\n", |
| 871 |
" 'minValue': 0.0,\n", |
| 872 |
" 'name': 'spectral whitening',\n", |
| 873 |
" 'unit': ''},\n", |
| 874 |
" {'defaultValue': 0.699999988079071,\n",
|
| 875 |
" 'description': 'Determines how individual notes in the note dictionary look: higher values mean more dominant higher harmonics.',\n", |
| 876 |
" 'identifier': 's',\n", |
| 877 |
" 'isQuantized': False,\n", |
| 878 |
" 'maxValue': 0.8999999761581421,\n", |
| 879 |
" 'minValue': 0.5,\n", |
| 880 |
" 'name': 'spectral shape',\n", |
| 881 |
" 'unit': ''},\n", |
| 882 |
" {'defaultValue': 0.0,\n",
|
| 883 |
" 'description': 'How shall the chroma vector be normalized?',\n", |
| 884 |
" 'identifier': 'chromanormalize',\n", |
| 885 |
" 'isQuantized': True,\n", |
| 886 |
" 'maxValue': 3.0,\n", |
| 887 |
" 'minValue': 0.0,\n", |
| 888 |
" 'name': 'chroma normalization',\n", |
| 889 |
" 'quantizeStep': 1.0,\n", |
| 890 |
" 'unit': '',\n", |
| 891 |
" 'valueNames': ['none', 'maximum norm', 'L1 norm', 'L2 norm']}]" |
| 892 |
] |
| 893 |
}, |
| 894 |
"execution_count": 16, |
| 895 |
"metadata": {},
|
| 896 |
"output_type": "execute_result" |
| 897 |
} |
| 898 |
], |
| 899 |
"source": [ |
| 900 |
"plug = vamp.vampyhost.load_plugin(\"nnls-chroma:nnls-chroma\", 44100, vamp.vampyhost.ADAPT_NONE)\n", |
| 901 |
"plug.parameters" |
| 902 |
] |
| 903 |
}, |
| 904 |
{
|
| 905 |
"cell_type": "markdown", |
| 906 |
"metadata": {},
|
| 907 |
"source": [ |
| 908 |
"From this we can work out that (for example) to set the chroma vector normalisation to \"L2 norm\" we should supply something like `parameters = { \"chromanormalize\" : 3 }` in the call to `vamp.collect`.\n",
|
| 909 |
"\n", |
| 910 |
"(Strictly speaking we're supposed to call" |
| 911 |
] |
| 912 |
}, |
| 913 |
{
|
| 914 |
"cell_type": "code", |
| 915 |
"execution_count": 17, |
| 916 |
"metadata": {
|
| 917 |
"collapsed": false |
| 918 |
}, |
| 919 |
"outputs": [ |
| 920 |
{
|
| 921 |
"data": {
|
| 922 |
"text/plain": [ |
| 923 |
"True" |
| 924 |
] |
| 925 |
}, |
| 926 |
"execution_count": 17, |
| 927 |
"metadata": {},
|
| 928 |
"output_type": "execute_result" |
| 929 |
} |
| 930 |
], |
| 931 |
"source": [ |
| 932 |
"plug.unload()" |
| 933 |
] |
| 934 |
}, |
| 935 |
{
|
| 936 |
"cell_type": "markdown", |
| 937 |
"metadata": {},
|
| 938 |
"source": [ |
| 939 |
"after doing the above, as well; otherwise a bit of memory is wasted.)" |
| 940 |
] |
| 941 |
}, |
| 942 |
{
|
| 943 |
"cell_type": "markdown", |
| 944 |
"metadata": {},
|
| 945 |
"source": [ |
| 946 |
"### Exporting the result to a CSV file\n", |
| 947 |
"This is a pretty standard use of Python's `csv` module." |
| 948 |
] |
| 949 |
}, |
| 950 |
{
|
| 951 |
"cell_type": "code", |
| 952 |
"execution_count": 18, |
| 953 |
"metadata": {
|
| 954 |
"collapsed": true |
| 955 |
}, |
| 956 |
"outputs": [], |
| 957 |
"source": [ |
| 958 |
"import csv\n", |
| 959 |
"out_file = open('features.csv', 'w')\n",
|
| 960 |
"writer = csv.writer(out_file)\n", |
| 961 |
"writer.writerows(chroma)\n", |
| 962 |
"out_file.close()" |
| 963 |
] |
| 964 |
}, |
| 965 |
{
|
| 966 |
"cell_type": "markdown", |
| 967 |
"metadata": {},
|
| 968 |
"source": [ |
| 969 |
"(Might be a good moment to find the `features.csv` file in the filesystem and check that it looks OK.)" |
| 970 |
] |
| 971 |
}, |
| 972 |
{
|
| 973 |
"cell_type": "markdown", |
| 974 |
"metadata": {},
|
| 975 |
"source": [ |
| 976 |
"### Processing many files\n", |
| 977 |
"We define a function that exports chroma features, with the parameters used above, from an audio file given the filename. Then we can call that for a set of files.\n", |
| 978 |
"\n", |
| 979 |
"This time we are overriding the `sr` parameter of `librosa.load` to tell it to use the file's own sample rate always (that's what `sr = None` does). We also print out what that rate is, for each file, as well as the resulting step size in audio samples between chroma features." |
| 980 |
] |
| 981 |
}, |
| 982 |
{
|
| 983 |
"cell_type": "code", |
| 984 |
"execution_count": 19, |
| 985 |
"metadata": {
|
| 986 |
"collapsed": true |
| 987 |
}, |
| 988 |
"outputs": [], |
| 989 |
"source": [ |
| 990 |
"import os, glob\n", |
| 991 |
"def extract_chroma(audiofile):\n", |
| 992 |
" data, rate = librosa.load(audiofile, sr = None)\n", |
| 993 |
" out = vamp.collect(data, rate,\n", |
| 994 |
" plugin_key = \"nnls-chroma:nnls-chroma\",\n", |
| 995 |
" output = \"chroma\",\n", |
| 996 |
" process_timestamp_method = vamp.vampyhost.SHIFT_DATA)\n", |
| 997 |
" step, chroma = out[\"matrix\"]\n", |
| 998 |
" print(\"File \" + audiofile +\n", |
| 999 |
" \": sample rate = \" + str(rate) +\n", |
| 1000 |
" \", chroma step = \" + str(vamp.vampyhost.RealTime.to_frame(step, rate)))\n", |
| 1001 |
" out_file = open(os.path.splitext(audiofile)[0] + \"_chroma.csv\", \"w\")\n", |
| 1002 |
" csv.writer(out_file).writerows(chroma)\n", |
| 1003 |
" out_file.close()" |
| 1004 |
] |
| 1005 |
}, |
| 1006 |
{
|
| 1007 |
"cell_type": "code", |
| 1008 |
"execution_count": 20, |
| 1009 |
"metadata": {
|
| 1010 |
"collapsed": false |
| 1011 |
}, |
| 1012 |
"outputs": [ |
| 1013 |
{
|
| 1014 |
"name": "stdout", |
| 1015 |
"output_type": "stream", |
| 1016 |
"text": [ |
| 1017 |
"File data/Music/07 - King Henry.flac: sample rate = 44100, chroma step = 2048\n" |
| 1018 |
] |
| 1019 |
} |
| 1020 |
], |
| 1021 |
"source": [ |
| 1022 |
"for file in glob.glob(\"data/Music/*.flac\"):\n", |
| 1023 |
" extract_chroma(file)" |
| 1024 |
] |
| 1025 |
}, |
| 1026 |
{
|
| 1027 |
"cell_type": "markdown", |
| 1028 |
"metadata": {},
|
| 1029 |
"source": [ |
| 1030 |
"### Further exercises\n", |
| 1031 |
"\n", |
| 1032 |
"* Load the \"King Henry\" audio data and chroma .csv file into Sonic Visualiser, and verify that the chroma data exported in the last step appear similar to those generated by running the plugin within Sonic Visualiser.\n", |
| 1033 |
"* Adapt this notebook so as to extract \"smoothed pitch curve\" features for the \"King Henry\" audio using the pYIN plugin, and figure out how to display the results using in a Matplotlib plot." |
| 1034 |
] |
| 1035 |
} |
| 1036 |
], |
| 1037 |
"metadata": {
|
| 1038 |
"kernelspec": {
|
| 1039 |
"display_name": "Python 2", |
| 1040 |
"language": "python", |
| 1041 |
"name": "python2" |
| 1042 |
}, |
| 1043 |
"language_info": {
|
| 1044 |
"codemirror_mode": {
|
| 1045 |
"name": "ipython", |
| 1046 |
"version": 2 |
| 1047 |
}, |
| 1048 |
"file_extension": ".py", |
| 1049 |
"mimetype": "text/x-python", |
| 1050 |
"name": "python", |
| 1051 |
"nbconvert_exporter": "python", |
| 1052 |
"pygments_lexer": "ipython2", |
| 1053 |
"version": "2.7.10" |
| 1054 |
} |
| 1055 |
}, |
| 1056 |
"nbformat": 4, |
| 1057 |
"nbformat_minor": 0 |
| 1058 |
} |