micmon/notebooks/predict.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "source": [
    "This notebook uses a pre-trained Tensorflow model to make live\n",
    "predictions on the audio samples recorded from a microphone."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DEBUG:matplotlib:(private) matplotlib data path: /usr/lib/python3.8/site-packages/matplotlib/mpl-data\n",
      "DEBUG:matplotlib:matplotlib data path: /usr/lib/python3.8/site-packages/matplotlib/mpl-data\n",
      "DEBUG:matplotlib:CONFIGDIR=/home/blacklight/.config/matplotlib\n",
      "DEBUG:matplotlib:matplotlib version 3.3.2\n",
      "DEBUG:matplotlib:interactive is False\n",
      "DEBUG:matplotlib:platform is linux\n",
      "DEBUG:matplotlib:loaded modules: ['sys', 'builtins', '_frozen_importlib', '_imp', '_warnings', '_frozen_importlib_external', '_io', 'marshal', 'posix', '_thread', '_weakref', 'time', 'zipimport', '_codecs', 'codecs', 'encodings.aliases', 'encodings', 'encodings.utf_8', '_signal', '__main__', 'encodings.latin_1', '_abc', 'abc', 'io', '_stat', 'stat', '_collections_abc', 'genericpath', 'posixpath', 'os.path', 'os', '_sitebuiltins', '_locale', '_bootlocale', 'types', 'importlib._bootstrap', 'importlib._bootstrap_external', 'warnings', 'importlib', 'importlib.machinery', 'importlib.abc', '_operator', 'operator', 'keyword', '_heapq', 'heapq', 'itertools', 'reprlib', '_collections', 'collections', '_functools', 'functools', 'contextlib', 'importlib.util', 'google', 'google.assistant', 'google.assistant.embedded', 'googlesamples', 'googlesamples.assistant', 'google.cloud', 'google.logging', 'google.iam', 'mpl_toolkits', 'ruamel', 'sphinxcontrib', 'zope', 'site', '_weakrefset', 'weakref', 'pkgutil', 'runpy', 'ipykernel._version', '__future__', 'enum', '_sre', 'sre_constants', 'sre_parse', 'sre_compile', 'copyreg', 're', '_json', 'json.scanner', 'json.decoder', 'json.encoder', 'json', 'errno', 'signal', 'threading', '_posixsubprocess', 'select', 'collections.abc', 'math', 'selectors', 'subprocess', 'IPython.core', 'IPython.core.getipython', 'IPython.core.release', 'atexit', 'copy', 'fnmatch', 'glob', 'token', 'tokenize', 'linecache', 'traceback', '_string', 'string', 'logging', 'zlib', '_compression', '_bz2', 'bz2', '_lzma', 'lzma', 'pwd', 'grp', 'shutil', '_opcode', 'opcode', 'dis', 'inspect', '_struct', 'struct', 'six', 'traitlets.utils', 'traitlets.utils.getargspec', 'ipython_genutils._version', 'ipython_genutils', 'locale', 'ipython_genutils.encoding', 'ipython_genutils.py3compat', 'traitlets.utils.importstring', 'traitlets.utils.sentinel', 'traitlets.utils.bunch', 'traitlets.traitlets', 'traitlets._version', 'traitlets', 'decorator', 'gettext', 'argparse', '_ast', 'ast', '_bisect', 'bisect', '_sha512', '_random', 'random', 'ipython_genutils.path', 'traitlets.config.loader', 'textwrap', 'ipython_genutils.text', 'traitlets.config.configurable', 'ipython_genutils.importstring', 'traitlets.config.application', 'traitlets.config', 'pprint', 'platform', 'sysconfig', 'urllib', 'urllib.parse', '_sysconfigdata__linux_x86_64-linux-gnu', 'pydoc', 'bdb', 'IPython.utils', 'IPython.utils.ipstruct', 'IPython.utils.coloransi', 'pygments', 'IPython.utils.colorable', 'IPython.utils.PyColorize', 'IPython.utils.encoding', 'IPython.utils.py3compat', 'IPython.core.excolors', 'IPython.testing', 'IPython.testing.skipdoctest', 'cmd', 'codeop', 'code', 'pdb', 'IPython.core.debugger', 'IPython.core.display_trap', 'pexpect.exceptions', 'pexpect.utils', 'pexpect.expect', 'termios', 'tty', 'pty', 'fcntl', 'resource', 'ptyprocess.util', 'ptyprocess.ptyprocess', 'ptyprocess', 'pexpect.spawnbase', 'pexpect.pty_spawn', 'pexpect.run', 'pexpect', 'shlex', 'IPython.utils._process_common', 'IPython.utils._process_posix', 'IPython.utils.process', 'IPython.utils.decorators', 'IPython.utils.path', 'IPython.utils.data', 'IPython.utils.terminal', 'IPython.core.ultratb', 'IPython.utils._sysinfo', 'IPython.utils.sysinfo', 'IPython.core.crashhandler', 'tempfile', 'IPython.utils.importstring', 'IPython.paths', 'IPython.core.profiledir', 'IPython.core.application', 'IPython.terminal', '_hashlib', '_blake2', '_sha3', 'hashlib', 'IPython.core.compilerop', 'IPython.core.error', 'ntpath', 'pathlib', 'IPython.utils.text', 'IPython.core.magic_arguments', 'getopt', 'typing.io', 'typing.re', 'typing', 'binascii', 'mimetypes', 'IPython.core.display', 'IPython.core.page', 'getpass', 'IPython.lib.security', 'IPython.lib', '_datetime', 'datetime', 'IPython.lib.pretty', 'IPython.utils.openpy', 'IPython.utils.dir2', 'IPython.utils.wildcard', 'pygments.lexers._mapping', 'pygments.modeline', 'pygments.plugin', 'pygments.util', 'pygments.lexers', 'pygments.filter', 'pygments.token', 'pygments.filters', 'pygments.regexopt', 'pygments.lexer', 'pygments.unistring', 'pygments.lexers.p
      "DEBUG:matplotlib:CACHEDIR=/home/blacklight/.cache/matplotlib\n",
      "DEBUG:matplotlib.font_manager:Using fontManager instance from /home/blacklight/.cache/matplotlib/fontlist-v330.json\n",
      "DEBUG:matplotlib.pyplot:Loaded backend module://ipykernel.pylab.backend_inline version unknown.\n",
      "DEBUG:matplotlib.pyplot:Loaded backend module://ipykernel.pylab.backend_inline version unknown.\n",
      "DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client.\n",
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.summary API due to missing TensorBoard installation.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "from micmon.audio import AudioDevice, AudioPlayer\n",
    "from micmon.model import Model\n",
    "\n",
    "basedir = os.path.expanduser(os.path.join('~', 'projects', 'baby-monitor'))\n",
    "models_dir = os.path.join(basedir, 'models')\n",
    "model_path = os.path.join(models_dir, 'baby-monitor')\n",
    "audio_system = 'alsa'\n",
    "audio_device = 'plughw:3,0'\n",
    "label_names = ['negative', 'positive']"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "Load the model"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [],
   "source": [
    "model = Model.load(model_path)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Play some audio from the input device"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "with AudioDevice(audio_system, device=audio_device) as source, AudioPlayer() as player:\n",
    "    for sample in source:\n",
    "        player.play(sample)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Record frames from an audio source and make predictions using the model"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "negative\n",
      "negative\n",
      "negative\n",
      "negative\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
      "\u001B[0;32m<ipython-input-3-27c83a302cb8>\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[0;32mwith\u001B[0m \u001B[0mAudioDevice\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0maudio_system\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdevice\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0maudio_device\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mas\u001B[0m \u001B[0msource\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m----> 2\u001B[0;31m     \u001B[0;32mfor\u001B[0m \u001B[0msample\u001B[0m \u001B[0;32min\u001B[0m \u001B[0msource\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      3\u001B[0m         \u001B[0msource\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mpause\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      4\u001B[0m         \u001B[0mprediction\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mmodel\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mpredict\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0msample\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      5\u001B[0m         \u001B[0mprint\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mprediction\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
      "\u001B[0;32m~/projects/baby-monitor/micmon/audio/source.py\u001B[0m in \u001B[0;36m__next__\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m     36\u001B[0m             \u001B[0;32mraise\u001B[0m \u001B[0mStopIteration\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     37\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 38\u001B[0;31m         \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mffmpeg\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstdout\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mread\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mbufsize\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     39\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mdata\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     40\u001B[0m             \u001B[0;32mreturn\u001B[0m \u001B[0mAudioSegment\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mdata\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0msample_rate\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msample_rate\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mchannels\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mchannels\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
     ]
    }
   ],
   "source": [
    "with AudioDevice(audio_system, device=audio_device) as source:\n",
    "    for sample in source:\n",
    "        source.pause()\n",
    "        prediction = model.predict(sample)\n",
    "        print(prediction)\n",
    "        source.resume()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}