Skip to content

M
musicinformationretrieval-com
Commit be82b853 authored by Steve Tjoa's avatar Steve Tjoa
Browse files
Options

lots of updates, too lazy to make descriptive commit message

parent c7208e11
Hide whitespace changes
Inline Side-by-side
Showing with 1275 additions and 830 deletions
Table_of_Contents.ipynb
View file @ be82b853
{
"metadata": {
"name": "",
"signature": "sha256:f715a5084a07e4d0fbc7e724694bded7340626b350e82428991d7645976d31b3"
"signature": "sha256:bdbfa3ec9eb61c71cd974adaf3009224ed93c7ca79b24beed967e29b8ac8aba9"
},
"nbformat": 3,
"nbformat_minor": 0,
......@@ -118,16 +118,15 @@
"level": 2,
"metadata": {},
"source": [
"Day 5: Neural Networks"
"Day 5: Music Fingerprinting"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"cell_type": "markdown",
"metadata": {},
"outputs": []
"source": [
"1. [Locality Sensitive Hashing](notebooks/lsh_fingerprinting.ipynb)"
]
},
{
"cell_type": "heading",
......
Vagrantfile
View file @ be82b853
......@@ -17,7 +17,7 @@ Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
config.vm.provider "virtualbox" do |v|
v.memory = 1024
v.cpus = 2
v.cpus = 1
end
config.ssh.forward_agent = true
......
exercises/feature_sonification.ipynb
View file @ be82b853
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/ipython_audio.ipynb
View file @ be82b853
{
"metadata": {
"name": "",
"signature": "sha256:dc2d519cf8158ddde08869c1e4bdc1bf230dda51aeea74b84739eedd05d4272e"
"signature": "sha256:10a96a42f1a86ec36e94c4b4752dae6f748916ce4faf6c29f6cfae3032f5f073"
},
"nbformat": 3,
"nbformat_minor": 0,
......@@ -92,7 +92,7 @@
"output_type": "pyout",
"prompt_number": 1,
"text": [
"('simpleLoop.wav', <httplib.HTTPMessage instance at 0x4276098>)"
"('simpleLoop.wav', <httplib.HTTPMessage instance at 0x3629b48>)"
]
}
],
......@@ -118,7 +118,7 @@
"output_type": "stream",
"stream": "stdout",
"text": [
"\u001b[0m\u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
"\u001b[0m\u001b[00;36mdefault.wav\u001b[0m \u001b[00;36mout.wav\u001b[0m \u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
]
}
],
......@@ -200,15 +200,15 @@
"output_type": "pyout",
"prompt_number": 4,
"text": [
"<matplotlib.text.Text at 0x43906d0>"
"<matplotlib.text.Text at 0x40f4bd0>"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEMCAYAAADDMN02AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
"png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEMCAYAAADDMN02AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text": [
"<matplotlib.figure.Figure at 0x4398310>"
"<matplotlib.figure.Figure at 0x37e57d0>"
]
}
],
......@@ -298,7 +298,7 @@
"output_type": "pyout",
"prompt_number": 6,
"text": [
"<IPython.lib.display.Audio at 0x61d5050>"
"<IPython.lib.display.Audio at 0x410bed0>"
]
}
],
......@@ -326,7 +326,7 @@
"output_type": "pyout",
"prompt_number": 7,
"text": [
"<IPython.lib.display.Audio at 0x64dd250>"
"<IPython.lib.display.Audio at 0x580d690>"
]
}
],
......@@ -365,7 +365,7 @@
"output_type": "pyout",
"prompt_number": 8,
"text": [
"<IPython.lib.display.Audio at 0x64fa250>"
"<IPython.lib.display.Audio at 0x5e1e710>"
]
}
],
......@@ -422,15 +422,15 @@
"output_type": "pyout",
"prompt_number": 9,
"text": [
"<matplotlib.text.Text at 0x64fb810>"
"<matplotlib.text.Text at 0x5810cd0>"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEMCAYAAADeYiHoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYRzy/won3wKGcFuVAAAAAElFTkSuQmCC\n",
"png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEMCAYAAADeYiHoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n10Mrs7BScyQAAAAASUVORK5CYII=\n",
"text": [
"<matplotlib.figure.Figure at 0x4867910>"
"<matplotlib.figure.Figure at 0x5e1e810>"
]
}
],
......@@ -459,15 +459,15 @@
"output_type": "pyout",
"prompt_number": 10,
"text": [
"<matplotlib.text.Text at 0x6813fd0>"
"<matplotlib.text.Text at 0x5f4f4d0>"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAZwAAAEKCAYAAAAmfuNnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nKHBERMQW/x+fal+1runOsgAAAABJRU5ErkJggg==\n",
"png": "iVBORw0KGgoAAAANSUhEUgAAAZwAAAEKCAYAAAAmfuNnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X1UE3faN/BrJNFaBS0oARM0VoKIgkQxZF+s6QMI8mxR\niwtiVVTs3YOr2GqVuntvhX1awe7aVmrpyxZWtPeKPlqBbZGibrGtLUQR6wtWYwUh4UULarEiJDj3\nH+x0WaqCwswQ5vs5Z86BMcNcFx7n6+83v0wYlmUJAACAbwPELgAAAKQBgQMAAIJA4AAAgCAQOAAA\nIAgEDgAACAKBAwAAguAtcKqrqz2efPLJzyZOnHh20qRJZ9LS0hKIiJKSkpJUKpVZq9WWabXasgMH\nDszijklJSdmg0WhM3t7e3xYWFs7k9peWlk719fU9rdFoTKtXr97K7W9paRkUHR29W6PRmPR6ffHl\ny5fH8NUPAAD0EMuyvGy1tbVuZWVl/izLUlNT01AvL6/z5eXlE5KSkjZu2bJlTefXnz171mfy5Mkn\nW1tb5RUVFepx48ZdvHPnDsOyLE2bNs1YUlKiY1mWZs2alX/gwIEwlmXp7bffXhEfH5/OsixlZ2dH\nR0dHZ/PVDzZs2LBh69nG2wjHzc2tzt/f/yQR0dChQ29OmDDhnMViUf4r5JjOr8/NzZ0dExOzSy6X\nW9VqdaWnp+fFkpKSwNraWvempiZHnU5nJCJavHjxjpycnDlERHl5eRGxsbFZRESRkZH7Dh8+HMRX\nPwAA0DMyIU5SWVmpLisr0+r1+uKjR4/+6q233lq1Y8eOxQEBAce3bNmydvjw4ddrampG6fX6Yu4Y\nlUpltlgsSrlcblWpVGZuv1KptHDBZbFYlB4eHtVERDKZzDZs2LAbjY2Nzs7Ozo3c6xmGwaMUAAAe\n0N0GBj3F+6KBmzdvDp03b97erVu3rh46dOjN+Pj4dyoqKsaePHnS393dvXbt2rVb+K5B7GEkX9vG\njRtFrwH9oT/01/82vvAaOFarVR4ZGblv4cKFH86ZMyeHiMjV1fUKwzAswzDs8uXLPzAajTqi9pFL\ndXW1B3es2WxWqVQqs1KptJjNZlXn/dwxVVVVo4mIbDab7MaNG8M6jm4AAKDv4C1wWJZl4uLiMnx8\nfMqff/75N7n9tbW17tzX+/fvn+vr63uaiCgiIiIvOzt7fmtr68CKioqxJpNJo9PpjG5ubnVOTk4/\nlJSUBLIsy+zcuXPR7Nmzc7ljsrKyYomI9u7dOy8oKOgwX/0AAEDP8HYP5+jRo7/68MMPF/r5+Z3S\narVlRESbNm36/a5du2JOnjzpzzAMO3bs2Ir33nvvOSIiHx+f8qioqD0+Pj7lMpnMlp6evoK7/5Ke\nnr5iyZIl25ubmweHh4fnh4WFFRARxcXFZSxatGinRqMxubi4NGRnZ8/nq5++yGAwiF0Cr9CffUN/\n0BnD53xdX8AwDNvfewQA6E0MwxBrj4sGAAAAiBA4AAAgEAQOAAAIAoEDAACCQOAAAIAgEDgAACAI\nBA4AAAgCgQMAAIJA4AAAgCAQOAAAIAgEDgAACAKBAwAAgkDgAACAIBA4AAAgCAQOAAAIAoEDAACC\nQOAAAIAgEDgAACAIBA4AAAgCgQMAAIKQiV2AEPbuLRe7BACAPuHppyfQgAGMKOdmWJYV5cRCYRiG\nJTordhkAAH2C1TqBZLL7Bw7DMMSybK+nEqbUAABAEAgcAAAQBAIHAAAEgcABAABBIHAAAEAQCBwA\nABAEAgcAAASBwAEAAEEgcAAAQBAIHAAAEAQCBwAABCGJh3cSycUuAABA8jDCAQAAQfAWONXV1R5P\nPvnkZxMnTjw7adKkM2lpaQlERI2Njc4hISEHvby8LsycObPw+vXrw7ljUlJSNmg0GpO3t/e3hYWF\nM7n9paWlU319fU9rNBrT6tWrt3L7W1paBkVHR+/WaDQmvV5ffPny5TF89QMAAD3DW+DI5XLrG2+8\n8cLZs2cnFhcX699+++3fnTt3bkJqaupLISEhBy9cuOAVFBR0ODU19SUiovLycp/du3dHl5eX+xQU\nFIStWLEinXs8dnx8/DsZGRlxJpNJYzKZNAUFBWFERBkZGXEuLi4NJpNJ88ILL7yRmJi4ma9+AACg\nZ3gLHDc3tzp/f/+TRERDhw69OWHChHMWi0WZl5cXERsbm0VEFBsbm5WTkzOHiCg3N3d2TEzMLrlc\nblWr1ZWenp4XS0pKAmtra92bmpocdTqdkYho8eLFO7hjOv6syMjIfYcPHw7iqx8AAOgZQRYNVFZW\nqsvKyrSBgYEl9fX1CoVCUU9EpFAo6uvr6xVERDU1NaP0en0xd4xKpTJbLBalXC63qlQqM7dfqVRa\nLBaLkojIYrEoPTw8qomIZDKZbdiwYTcaGxudnZ2dG/+zgrc6fK0jokC+WgUAsDtFRUVUVFTE+3l4\nD5ybN28OjYyM3Ld169bVjo6OTR3/jGEYtv0TOfm2iv9TAADYKYPBQAaD4afvk5OTeTkPr6vUrFar\nPDIyct+iRYt2zpkzJ4eofVRTV1fnRkRUW1vr7urqeoWofeRSXV3twR1rNptVKpXKrFQqLWazWdV5\nP3dMVVXVaCIim80mu3HjxrCfj24AAKAv4C1wWJZl4uLiMnx8fMqff/75N7n9EREReVlZWbFERFlZ\nWbFcEEVERORlZ2fPb21tHVhRUTHWZDJpdDqd0c3Nrc7JyemHkpKSQJZlmZ07dy6aPXt2bueftXfv\n3nlBQUGH716NDBs2bNiwkYzExLAsPzNaX3755a+feOKJz/38/E5x02YpKSkbdDqdMSoqak9VVdVo\ntVpduWfPnqjhw4dfJyLatGnT7zMzM5fJZDLb1q1bV4eGhn5K1L4sesmSJdubm5sHh4eH53NLrFta\nWgYtWrRoZ1lZmdbFxaUhOzt7vlqtrvyPBhmGJbrES48AAPbGalWTTMbc9zUMwxC3Srg38RY4fQUC\nBwDg38QMHDxpAAAABIHAAQAAQYh7B0kwvT4yBACABySRwJFImwAAfRim1AAAQBAIHAAAEAQCBwAA\nBCGRmxtYNAAAIDaJBI5E2gQA6MMwpQYAAIJA4AAAgCAkMteEXAUAEBsCBwAABIErMQAACAKBAwAA\ngpDIlJpc7AIAACQPIxwAABAEAgcAAAQhkSk1ibQJANCHYYQDAACCQOAAAIAgJDLXhFVqAABiwwgH\nAAAEgcABAABBSGRKTSJtAgD0YRjhAACAICTyX398xDQAgNgwwgEAAEEgcAAAQBAIHAAAEAQCBwAA\nBIHAAQAAQSBwAABAEAgcAAAQBAIHAAAEgcABAABB8BY4y5Yty1QoFPW+vr6nuX1JSUlJKpXKrNVq\ny7RabdmBAwdmcX+WkpKyQaPRmLy9vb8tLCycye0vLS2d6uvre1qj0ZhWr169ldvf0tIyKDo6erdG\nozHp9friy5cvj7lnMTJs2LBhw0YyElWXgXP69Gnfh/nBS5cu/VtBQUFYx30Mw7Br1qx5vaysTFtW\nVqadNWvWASKi8vJyn927d0eXl5f7FBQUhK1YsSKdZVmGiCg+Pv6djIyMOJPJpDGZTBruZ2ZkZMS5\nuLg0mEwmzQsvvPBGYmLi5oepEwAAhNFl3sXHx7/T0tIyaOnSpX975pln/mfYsGE3uvODp0+f/kVl\nZaW6834uSDrKzc2dHRMTs0sul1vVanWlp6fnxZKSksAxY8ZcbmpqctTpdEYiosWLF+/IycmZExYW\nVpCXlxeRnJy8kYgoMjJy38qVK7c9fJcAAMC3Li/FX3755a8vXLjglZmZuWzKlCkndDqdcenSpX+b\nOXNm4cOc8K233lq1Y8eOxQEBAce3bNmydvjw4ddrampG6fX6Yu41KpXKbLFYlHK53KpSqczcfqVS\nabFYLEoiIovFovTw8KgmIpLJZLZhw4bdaGxsdHZ2dm782UltSf/+eoCByMHwMKUDAPRLRUVFVFRU\nxPt5uvV/fy8vrwuvvPLKfwcEBBxPSEhIO3nypP+dO3cGbNq06feRkZH7unuy+Pj4d15++eU/ERH9\n8Y9//H9r167dkpGREfewxXfbI0m8nwIAwF4ZDAYyGAw/fZ+cnMzLeboMnG+++Wby9u3bl3z88ce/\nCQkJOfjxxx//ZsqUKSe4UcmDBI6rq+sV7uvly5d/8NRTT/2DqH3kUl1d7cH9mdlsVqlUKrNSqbSY\nzWZV5/3cMVVVVaNHjRpVY7PZZDdu3Bh219ENEdbiAQD0AV1eihMSEtK0Wm3ZN998Mzk9PX3FlClT\nThARjRo1quaVV1757wc5WW1trTv39f79++dyK9giIiLysrOz57e2tg6sqKgYazKZNDqdzujm5lbn\n5OT0Q0lJSSDLsszOnTsXzZ49O5c7JisrK5aIaO/evfOCgoIO37dLbNiwYcMmKoZl2fu+4ObNm0MH\nDx7c7ODg0EZE1NbW5nD79u1HhgwZ8uP9jouJidl15MiRGd9///0IhUJRn5ycvLGoqMhw8uRJf4Zh\n2LFjx1a89957zykUinoiok2bNv0+MzNzmUwms23dunV1aGjop0Tty6KXLFmyvbm5eXB4eHh+Wlpa\nAlH7suhFixbtLCsr07q4uDRkZ2fPV6vVlT9rkGFYcrl/jwAAUmGtI5J1MbfFMMxdF3j1VJeBo9fr\niw8dOhQ8dOjQm0RETU1NjqGhoZ9+9dVXv+ztYvjAMAxLIxA4AABERNZa8QKny3s4t2/ffoQLGyIi\nR0fHplu3bj3a24XwCsuiAQBE1+WM3pAhQ34sLS2dyn1//PjxgMGDBzfzWxYAAPQ3Xf7f/80333w+\nKipqj7u7ey1R+43/3bt3R/NfWi/CCAcAQHRd3sMhImptbR14/vz58QzDsOPHjz8vl8utAtTWKxiG\nYWkM7uEAABARWS/24UUDRERfffXVLysqKsbabDYZwzAsUftjZnq7GD4wDMOSGoEDAEBEZDX14UUD\nCxcu/PDSpUuP+/v7n+SWRhPZT+AQEabUAAD6gC4vxaWlpVPLy8t9uJGNXRL5zU4AANCNwJk0adKZ\n2tpa91GjRtUIURAvEDgAAKLrMnCuXr060sfHp1yn0xkHDRrUQtR+XyQvLy+C//J6CabUAADa9fqd\nme7r8lKclJSURNQeMtxNJLubXhPxFwwAAO26tUqtsrJSffHiRc/g4OBDt27detRms8mcnJx+EKC+\nHmMYhiV/+8pHAAC+WI8TyRzu/xrRVqm9//77//XXv/712cbGRufvvvtunNlsVsXHx79z+PDhoN4u\nhjeYUgMAEF2Xl+K33377d0ajUcd9IqeXl9eFK1euuPJfWi9C4AAAiK7L9VuDBg1q4RYLEBF1fPMn\nAABAd3X5f/8ZM2YcefXVV/9w69atRw8ePBiSnp6+gvukTruBEQ4AgOi6XDTQ1tbmkJGREVdYWDiT\niCg0NPTT5cuXf2AvoxyGYVgy2EWpAAC8sx4Sb9FAt1ap2TOGYVj6P/27RwCA7rIW9uFVamPHjq24\nSzHspUuXHu/tYniDJw0AAIiuy8A5duzYNO7r27dvP7J37955DQ0NLvyW1ctwDwcAQHQPNaU2ZcqU\nEydOnJjCQz29jmEYln6DKTUAACIia04fnlIrLS2dyi0QuHPnzoDjx48HtLW1dVFuH4MRDgCA6Lq8\nFK9du3YLFzgymcymVqsr9+zZE8V/ab0IgQMAIDpprFKb3797BADoLuuHfXhKbcuWLWs7v+em41Oj\n16xZ83pvFwUAAP1Pt+7hHDt2bFpEREQey7LMxx9//Jtp06Yd8/LyuiBEgb0CU2oAAKLrckpt+vTp\nX+Tn54c7Ojo2ERE1NTU5hoeH53/xxRfTBamwhxiGYWkJptQAAIiIrB/04Sm1K1euuMrlciv3vVwu\nt+Jp0QAA8KC6vBQvXrx4h06nMz799NMfsSzL5OTkzImNjc0Sorheg8ABABBdt1aplZaWTv3yyy9/\nTUT0xBNPfK7Vast4r6yXMAzD0kpMqQEAEBFZ3+zDU2pERLdu3XrU0dGxadmyZZlXr14dWVFRMfZu\nz1jrszDCAQBo1+sx0n1dXoqTkpKSSktLp54/f378smXLMltbWwcuXLjww6NHj/5KiAJ7BQIHAEB0\nXV6K9+/fP7esrEw7derUUiIipVJpaWpqcuS/tF6EwAEAEF2Xl+JBgwa1DBgw4A73/Y8//jiE35J4\ngMABABBdl5fi3/72t///ueeee+/69evD33///f/KzMxctnz58g+EKK7XIHAAAER331VqLMsy1dXV\nHt9++613x4+YDgkJOShYhT3EMAxLr2CVGgAAEZF1A5Gsiw+lFOUjplmWZXx9fU+fOXNmUm+fWCgM\nw7CUisABACAisq4TL3Due1qGYdipU6eWGo1G3YP+4GXLlmUqFIp6X1/f09y+xsZG55CQkINeXl4X\nZs6cWXj9+vXh3J+lpKRs0Gg0Jm9v72+50RRR+3uAfH19T2s0GtPq1au3cvtbWloGRUdH79ZoNCa9\nXl98+fLlMfcsRoYNGzZs2EhGouryjZ/jx48/f/HiRc8xY8ZcHjJkyI9E7UF06tQpv/sd98UXX0wf\nOnTozcWLF+84ffq0LxHR+vXrXxsxYsT369evf23z5s2J165deyw1NfWl8vJynwULFvz92LFj0ywW\nizI4OPiQyWTSMAzD6nQ647Zt21bqdDpjeHh4fkJCQlpYWFhBenr6ijNnzkxKT09fsXv37uj9+/fP\nzc7Onv+zBhmGpTcxwgEAICKyriLRRjj3zLuqqqrRo0ePrvr0009DGYZhH/Tk06dP/6KyslLdcV9e\nXl7EkSNHZhARxcbGZhkMhqLU1NSXcnNzZ8fExOySy+VWtVpd6enpebGkpCRwzJgxl5uamhx1Op2R\nqP0xOzk5OXPCwsIK8vLyIpKTkzcSEUVGRu5buXLltnsWM/BBKgcAAD7cM3Bmz56dW1ZWplWr1ZWR\nkZH79u3bF9nTk9XX1ysUCkU9EZFCoaivr69XEBHV1NSM0uv1xdzrVCqV2WKxKOVyuVWlUpm5/Uql\n0mKxWJRERBaLRenh4VFNRCSTyWzDhg270djY6Ozs7Nz4sxMXJP376/GG9g0AAIiIqKioiIqKing/\nT7dm9C5duvR4b5+YYRi28we78WZukiCnAQCwRwaDgQwGw0/fJycn83IeQW8hKRSK+rq6Ojc3N7e6\n2tpad1dX1ytE7SOX6upqD+51ZrNZpVKpzEql0mI2m1Wd93PHVFVVjR41alSNzWaT3bhxY9hdRzdE\nRHKeGwMAgC7dM3BOnTrlx33oWnNz82Dua6L20ckPP/zg9KAni4iIyMvKyopNTEzcnJWVFTtnzpwc\nbv+CBQv+vmbNmtctFovSZDJpdDqdkWEY1snJ6YeSkpJAnU5n3Llz56KEhIS0jj9Lr9cX7927d15Q\nUNDhB+8SAACEcs9LcVtbWxcPsL6/mJiYXUeOHJnx/fffj/Dw8Kj+05/+9PJLL72UGhUVtScjIyNO\nrVZX7tmzJ4qIyMfHpzwqKmqPj49PuUwms6Wnp6/gptvS09NXLFmyZHtzc/Pg8PDw/LCwsAIiori4\nuIxFixbt1Gg0JhcXl4a7rVDruksAABBKtz4Px54xDMNSTv/uEQCgu6xP9cFl0f3KILELAAAAaQQO\n3ocDANCuL38AW7+AEQ4AgOikETjS6BIAoE+TxqVYGl0CAPRp0rgUY0oNAEB00ggcPGkAAEB00gic\nQTaxKwAA6CMcSKylatIIHDkCBwCgXY8eItMjkggc+SOtYpcAANBHiHdTWxKB4yDDCAcAQGySCJxB\nGOEAAIhOEoEzcFArtd8k6/wQT3vYR53292QfXzXa4z4i/F7xe7WffUS9+3sVhyQCR05WsUsAAJA8\nBA4AAAhCIoGDKTV+a7THfUT4veL3aj/7iHr39yoOSQTOQIxwAACI6N8RJAZJBI6MsCwaAEBskgic\nwdQsdgkAAJInicDBogEAAA5LYk2sSSJwHsEIBwBAdJIIHCwaAAAQnyQC5xG6LXYJAACSJ4nAwT0c\nAADxIXAAAEAQkggcLIsGABCfJAIHq9QAAMQnkcBpEbsEAIA+AY+24Rmm1AAAxCeJwMGyaAAA8Uki\ncDDCAQDgiPdRBZIIHCwaAAAQn0QCB4sGAADEJpHAwQgHAEBskgicwVg0AAAgOlECR61WVzo5Of3g\n4ODQJpfLrUajUdfY2OgcHR29+/Lly2PUanXlnj17ooYPH36diCglJWVDZmbmMgcHh7a0tLSEmTNn\nFhIRlZaWTl2yZMn227dvPxIeHp6/devW1Xc731C6KWR7AAB9lpjvw2FYVvgVC2PHjq0oLS2d6uzs\n3MjtW79+/WsjRoz4fv369a9t3rw58dq1a4+lpqa+VF5e7rNgwYK/Hzt2bJrFYlEGBwcfMplMGoZh\nWJ1OZ9y2bdtKnU5nDA8Pz09ISEgLCwsr+I8GGYb9mp1MDP18bYY97KNO+3uyj68a7XEfEX6v+L3a\nzz6i3vu9BlIpMeRA98MwDLEs2+vZJNqUWudm8vLyIo4cOTKDiCg2NjbLYDAUpaamvpSbmzs7JiZm\nl1wut6rV6kpPT8+LJSUlgWPGjLnc1NTkqNPpjEREixcv3pGTkzOnc+AQETnRDWGaAgDo8yS2LJph\nGDY4OPiQg4ND23PPPffes88++9f6+nqFQqGoJyJSKBT19fX1CiKimpqaUXq9vpg7VqVSmS0Wi1Iu\nl1tVKpWZ269UKi0Wi0V5t/P9NenKT1/rDXL6hUHOW28AAPamqKiIioqKeD+PKIFz9OjRX7m7u9de\nvXp1ZEhIyEFvb+9vO/45wzAswzC9FsN/TLrT4buWf20AAEBEZDAYyGAw/PR9cnIyL+cRJXDc3d1r\niYhGjhx5de7cufuNRqNOoVDU19XVubm5udXV1ta6u7q6XiFqH7lUV1d7cMeazWaVSqUyK5VKi9ls\nVnXcr1QqLXc7n9MNrFIDACAiIicSbeWA4IFz69atR9va2hwcHR2bfvzxxyGFhYUzN27cmBwREZGX\nlZUVm5iYuDkrKyt2zpw5OUREEREReQsWLPj7mjVrXrdYLEqTyaTR6XRGhmFYJyenH0pKSgJ1Op1x\n586dixISEtLudk4ZFqkBALRzEu/UggdOfX29Yu7cufuJiGw2m+yZZ575n5kzZxYGBAQcj4qK2pOR\nkRHHLYsmIvLx8SmPiora4+PjUy6TyWzp6ekruOm29PT0FUuWLNne3Nw8ODw8PP9uCwaIiLBmAADg\nX0aJd2pRlkULiWEYlj0qdhUAAH3EL6xEzP3HGv1uWbSgGsQuAACgj2BJOvdwRHFV7AIAAEAagVMt\ndgEAAIDAAQCQEhFv20sjcCrFLgAAAKQROBjhAAC0wwiHXzcROAAAREQ0hMT7iAJJBM5lfOAnAAAR\nEfmIeG5JBM5dH7AGACBBEwgjHF59L3YBAAAgjcDBgwYAAMQnicDBw6IBAMQnicDBx60BAIhvgNgF\nAACANCBwAABAEJKYUpOLXQAAAEgjcIaIXQAAAEgjcIaLXQAAAEgjcEaIXQAAAEgjcJzFLgAAoI8Q\n67E2RBIJHA+xCwAAAGkEjhtu4gAAiE4SgSMfKXYFAAAgicAhhdgFAAD0ESLexJFG4GBKDQBAdNII\nnGFiFwAAANIInEfFLgAAAKQROAPFLgAAAKQROI+IXQAAQB+BRQM8GyR2AQAAII3AwZQaAIDopBE4\n+EAcAADRSSNwMKUGACA6aQSONLoEAOjTpHEpxpQaAIDopBE4DmIXwI+iC0QGL7Gr4A/6s2/oDzob\nIHYBPVVQUBDm7e39rUajMW3evDnxri9y6J9bkUn8GtAf+kN/draJyK4Dp62tzWHlypXbCgoKwsrL\ny3127doVc+7cuQli1wUAAD9n14FjNBp1np6eF9VqdaVcLrfOnz8/Ozc3d7bYdQEAwM/Z9T0ci8Wi\n9PDwqOa+V6lU5pKSksDOr2OeFbYuISX/Q+wK+IX+7Bv664OeFW8VlV0HDsMwbFevYVlWxCcHAQAA\nx66n1JRKpaW6utqD+766utpDpVKZxawJAADuzq4DJyAg4LjJZNJUVlaqW1tbB+7evTs6IiIiT+y6\nAADg5+x6Sk0mk9m2bdu2MjQ09NO2tjaHuLi4jAkTJpwTuy4AALgLlmXtZjtw4EDY+PHjv/X09DSl\npqYm3u01q1atSvP09DT5+fl9c+LECW1XxzY0NDgHBwcf1Gg0F0JCQgqvXbs2vD/19+KLL/7Z29v7\nnJ+f3zdz58796Pr168P6U3/c9pe//GUtwzB3GhoanPtbf2lpaau8vb3PTZw48cz69es396f+SkpK\ndNOmTTP6+/uXBQQEHDMajdPsrbelS5dmurq61k+aNOl0x9f3l2vLvfp7mGuLKM0/zGaz2RzGjRt3\nsaKiQt3a2iqfPHnyyfLy8gkdX/PJJ5+Ez5o1K59lWSouLg4MDAws7urYdevWvbZ58+b1LMtSampq\nYmJiYmp/6q+wsDCkra1tAMuylJiYmNrf+mNZlqqqqjxCQ0ML1Gp1hViBw1d///znP58MDg4+2Nra\nKmdZlq5cuTKyP/U3Y8aMooKCglCWZSk/P3+WwWD4zJ56Y1mWPv/88+knTpzQdr4g94dry/36e5hr\ni93cw+nOe27y8vIiYmNjs4iIAgMDS65fvz68rq7O7X7HdjwmNjY2KycnZ47w3fHXX0hIyMEBAwbc\n4Y4xm80q4bvjrz8iojVr1rz+2muvrRe6p4746u+dd96J37BhQ4pcLrcSEY0cOfKq8N3x15+7u3vt\njRs3hhERXb9+fbhSqbTYU29ERNOnT//iscceu9b55/aHawvRvft7mGuL3QTO3d5zY7FYlN15TU1N\nzah7HVtfX69QKBT1REQKhaK+vr5ewX83P8dXfx1lZmYuCw8Pz+erh/vhq7/c3NzZKpXK7Ofnd0qI\nPu6Fr/5MJpPm888/f0Kv1xcbDIai48ePBwjRT2d89ZeamvrS2rVrt4wePbpq3bp1f05JSdkgRD/d\nqftBX9NZf7i2dPcc3b222E3gdOc9N0Tde98Ny7LM3X4ewzBsd8/T23qzv7t59dVX/zBw4MDWBQsW\n/P1hju99R5JoAAAER0lEQVQpPvprbm4evGnTpt8nJydvfJjjexNff382m0127dq1x4qLi/V//vOf\n10VFRe15uAp7hq/+4uLiMtLS0hKqqqpGv/HGGy8sW7Ys8+EqfHgP29uDXCvs8drS3eMe5NpiN6vU\nuvOem86vMZvNKpVKZbZarfLO+7mhu0KhqK+rq3Nzc3Orq62tdXd1db0iRD+d9WZ/nY/dvn37kvz8\n/PDDhw8H8d3HvfDR33fffTeusrJSPXny5G+410+dOrXUaDTqhP575OvvT6VSmZ9++umPiIimTZt2\nbMCAAXcaGhpcXFxcGvjv6t6191Z/RqNRd+jQoWAionnz5u1dvnz5B/x3858etreupv/s/drSnenN\nB762iHET62E2q9Uqe/zxx7+rqKhQt7S0DOzqxtfXX3+t52583e/YdevWvcat2khJSXlJrBt7fPV3\n4MCBMB8fn7NXr14d0R///jpuYi4a4Ku/d99997mXX345mWVZOn/+vJeHh0dVf+pPq9WeKCoqmsGy\nLB06dCgoICDgmD31xm0VFRXquy0asPdry/36e5hri+DN92TLz8+f5eXldX7cuHEXN23atIFl2/9B\nvvvuu89xr/nd7363bdy4cRf9/Py+KS0tnXK/Y1m2feliUFDQob6wdJGP/jw9PU2jR4++7O/vX+bv\n718WHx+f3p/667iNHTv2kpjLovnor7W1Vb5w4cKdkyZNOj1lypTSzz77zNCf+jt27FiATqcrmTx5\n8km9Xv91x+W49tLb/Pnzd7m7u9cMHDiwRaVSVWdmZi5l2f5zbblXfw9zbWFYVpRpRQAAkBi7WTQA\nAAD2DYEDAACCQOAAAIAgEDgAACAIBA5AL2poaHDRarVlWq22zN3dvValUpm1Wm2Zo6Nj08qVK7eJ\nXR+AmLBKDYAnycnJGx0dHZvWrFnzuti1APQFGOEA8Ij91+NCioqKDE899dQ/iIiSkpKSYmNjs554\n4onP1Wp15UcfffT0iy+++Bc/P79Ts2bNOmCz2WRERKWlpVMNBkNRQEDA8bCwsALuYYoA9gqBAyCC\nioqKsZ999tmTeXl5EQsXLvwwJCTk4KlTp/wGDx7c/Mknn/xfq9UqX7Vq1Vv79u2LPH78eMDSpUv/\n9oc//OFVsesG6Am7eZYaQH/BMAw7a9asAw4ODm2TJk06c+fOnQGhoaGfEhH5+vqerqysVF+4cMHr\n7NmzE4ODgw8REbW1tTmMGjWqRtzKAXoGgQMggoEDB7YSEQ0YMOAO91k33Pc2m03GsiwzceLEs199\n9dUvxasSoHdhSg1AYGw3HuE/fvz481evXh1ZXFysJyKyWq3y8vJyH/6rA+APAgeAR9xninT8PJTO\nn43S+XNHGIZh5XK5de/evfMSExM3+/v7n9RqtWVff/31L4StHqB3YVk0AAAIAiMcAAAQBAIHAAAE\ngcABAABBIHAAAEAQCBwAABAEAgcAAATxvzCOtYE+olFUAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x4271750>"
"<matplotlib.figure.Figure at 0x5e3b790>"
]
}
],
......@@ -512,7 +512,7 @@
"output_type": "stream",
"stream": "stdout",
"text": [
"\u001b[0m\u001b[00;36mnoise1.wav\u001b[0m \u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
"\u001b[0m\u001b[00;36mdefault.wav\u001b[0m \u001b[00;36mnoise1.wav\u001b[0m \u001b[00;36mout.wav\u001b[0m \u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
]
}
],
......@@ -549,7 +549,7 @@
"output_type": "stream",
"stream": "stdout",
"text": [
"\u001b[0m\u001b[00;36mnoise1.wav\u001b[0m \u001b[00;36mnoise2.wav\u001b[0m \u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
"\u001b[0m\u001b[00;36mdefault.wav\u001b[0m \u001b[00;36mnoise1.wav\u001b[0m \u001b[00;36mnoise2.wav\u001b[0m \u001b[00;36mout.wav\u001b[0m \u001b[00;36msimpleLoop.wav\u001b[0m\r\n"
]
}
],
notebooks/kmeans.ipynb
View file @ be82b853
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/knn_instrument_classification.ipynb
View file @ be82b853
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/lsh_fingerprinting.ipynb
View file @ be82b853
{
"metadata": {
"name": "",
"signature": "sha256:1f044aa25a32fe434bce4255de83af940291fe22648bb0bd1aa00a36fab6d135"
"signature": "sha256:5d2db016d8cce3a76c015e44ee4f8e4c94a94e3dbfbc27ad7e4bab24b8b01c31"
},
"nbformat": 3,
"nbformat_minor": 0,
......@@ -10,7 +10,21 @@
"cells": [
{
"cell_type": "heading",
"level": 2,
"level": 1,
"metadata": {},
"source": [
"Music Fingerprinting using Locality Sensitive Hashing"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook shows a simple system for performing retrieval of musical tracks using LSH."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Import libraries:"
......@@ -20,6 +34,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"from sklearn.random_projection import GaussianRandomProjection\n",
"import essentia.standard as ess\n",
"import os\n",
"import os.path"
......@@ -30,8 +45,25 @@
"prompt_number": 1
},
{
"cell_type": "heading",
"level": 2,
"cell_type": "markdown",
"metadata": {},
"source": [
"Set figure size:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"rcParams['figure.figsize'] = (15, 5)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Select training data:"
......@@ -47,11 +79,10 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
"prompt_number": 3
},
{
"cell_type": "heading",
"level": 2,
"cell_type": "markdown",
"metadata": {},
"source": [
"Define a hash function:"
......@@ -61,14 +92,14 @@
"cell_type": "code",
"collapsed": false,
"input": [
"def hash_func(vec, projections):\n",
" bools = dot(projections, vec) > 0\n",
" return bool2int(bools)"
"def hash_func(vecs, model):\n",
" bools = model.transform(vecs) > 0\n",
" return [bool2int(bool_vec) for bool_vec in bools]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
"prompt_number": 4
},
{
"cell_type": "code",
......@@ -83,15 +114,14 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 4
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"projections = randn(5, 512)\n",
"x = randn(512)\n",
"hash_func(x, projections)"
"model = GaussianRandomProjection(n_components=3)\n",
"model.fit(randn(10000, 8))"
],
"language": "python",
"metadata": {},
......@@ -99,17 +129,38 @@
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 5,
"prompt_number": 6,
"text": [
"24"
"GaussianRandomProjection(eps=0.1, n_components=3, random_state=None)"
]
}
],
"prompt_number": 5
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"X = randn(12, 8)\n",
"hash_func(X, model)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 7,
"text": [
"[3, 5, 2, 6, 0, 0, 6, 1, 0, 2, 1, 7]"
]
}
],
"prompt_number": 7
},
{
"cell_type": "heading",
"level": 2,
"level": 3,
"metadata": {},
"source": [
"Create three LSH structures: Table, LSH, and MusicSearch:"
......@@ -125,37 +176,63 @@
" self.table = dict()\n",
" self.hash_size = hash_size\n",
" self.dim = dim # TODO is this necessary?\n",
" self.projections = randn(self.hash_size, self.dim)\n",
" #self.projections = randn(self.hash_size, self.dim)\n",
" self.projections = GaussianRandomProjection(n_components=hash_size)\n",
" self.projections.fit(randn(10000, dim))\n",
"\n",
" def add(self, vec, label):\n",
" entry = {'vector': None, 'label': label}\n",
" h = hash_func(vec, self.projections)\n",
" if self.table.has_key(h):\n",
" self.table[h].append(entry)\n",
" else:\n",
" self.table[h] = [entry]\n",
" def add(self, vecs, label):\n",
" entry = {'label': label}\n",
" hashes = hash_func(vecs, self.projections)\n",
" for h in hashes:\n",
" if self.table.has_key(h):\n",
" self.table[h].append(entry)\n",
" else:\n",
" self.table[h] = [entry]\n",
"\n",
" def query(self, vec):\n",
" h = hash_func(vec, self.projections)\n",
" if self.table.has_key(h):\n",
" results = self.table[h]\n",
" else:\n",
" results = list()\n",
" def query(self, vecs):\n",
" hashes = hash_func(vecs, self.projections)\n",
" results = list()\n",
" for h in hashes:\n",
" if self.table.has_key(h):\n",
" results.extend(self.table[h])\n",
" return results"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 6
"prompt_number": 8
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"input": [
"t = Table(2, 8)\n",
"t.add(randn(5, 8), '1')\n",
"t.add(randn(5, 8), '2')\n",
"t.query(randn(2,8))"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 6
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 9,
"text": [
"[{'label': '1'},\n",
" {'label': '1'},\n",
" {'label': '1'},\n",
" {'label': '2'},\n",
" {'label': '2'},\n",
" {'label': '1'},\n",
" {'label': '1'},\n",
" {'label': '1'},\n",
" {'label': '2'},\n",
" {'label': '2'}]"
]
}
],
"prompt_number": 9
},
{
"cell_type": "code",
......@@ -164,21 +241,21 @@
"class LSH:\n",
" \n",
" def __init__(self, dim):\n",
" self.num_tables = 7\n",
" self.hash_size = 10\n",
" self.num_tables = 4\n",
" self.hash_size = 8\n",
" self.dim = dim\n",
" self.tables = list()\n",
" for i in range(self.num_tables):\n",
" self.tables.append(Table(self.hash_size, self.dim))\n",
" \n",
" def add(self, vec, label):\n",
" def add(self, vecs, label):\n",
" for table in self.tables:\n",
" table.add(vec, label)\n",
" table.add(vecs, label)\n",
" \n",
" def query(self, vec):\n",
" def query(self, vecs):\n",
" results = list()\n",
" for table in self.tables:\n",
" results.extend(table.query(vec))\n",
" results.extend(table.query(vecs))\n",
" return results\n",
"\n",
" def describe(self):\n",
......@@ -188,7 +265,33 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 7
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"lsh = LSH(8)\n",
"lsh.add(randn(10,8), '1')\n",
"lsh.add(randn(10,8), '2')\n",
"lsh.describe()\n",
"#lsh.query(randn(2,8))"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"{110: [{'label': '2'}], 3: [{'label': '2'}], 36: [{'label': '1'}], 133: [{'label': '1'}, {'label': '2'}], 106: [{'label': '2'}], 151: [{'label': '2'}], 205: [{'label': '1'}], 78: [{'label': '1'}], 176: [{'label': '1'}, {'label': '1'}], 145: [{'label': '2'}], 180: [{'label': '2'}], 46: [{'label': '1'}], 87: [{'label': '2'}], 185: [{'label': '2'}], 250: [{'label': '1'}], 5: [{'label': '1'}], 74: [{'label': '2'}], 149: [{'label': '1'}]}\n",
"{163: [{'label': '1'}], 9: [{'label': '2'}], 113: [{'label': '2'}], 40: [{'label': '2'}], 201: [{'label': '1'}], 74: [{'label': '1'}], 203: [{'label': '1'}, {'label': '2'}, {'label': '2'}], 44: [{'label': '2'}], 45: [{'label': '2'}], 142: [{'label': '2'}], 48: [{'label': '2'}], 209: [{'label': '1'}], 18: [{'label': '2'}], 147: [{'label': '1'}], 84: [{'label': '1'}], 215: [{'label': '1'}], 92: [{'label': '1'}], 247: [{'label': '1'}]}\n",
"{240: [{'label': '2'}], 69: [{'label': '2'}], 71: [{'label': '2'}], 43: [{'label': '2'}], 110: [{'label': '1'}], 79: [{'label': '2'}], 144: [{'label': '1'}], 177: [{'label': '1'}], 178: [{'label': '2'}], 148: [{'label': '1'}], 86: [{'label': '1'}], 56: [{'label': '2'}], 184: [{'label': '1'}, {'label': '1'}], 84: [{'label': '2'}], 26: [{'label': '2'}], 111: [{'label': '2'}], 156: [{'label': '1'}], 94: [{'label': '1'}], 127: [{'label': '1'}]}\n",
"{65: [{'label': '2'}], 99: [{'label': '1'}, {'label': '1'}], 132: [{'label': '1'}], 214: [{'label': '1'}], 231: [{'label': '1'}], 72: [{'label': '2'}], 75: [{'label': '1'}], 140: [{'label': '1'}], 45: [{'label': '1'}], 168: [{'label': '2'}], 149: [{'label': '2'}], 150: [{'label': '1'}, {'label': '2'}], 87: [{'label': '2'}], 88: [{'label': '2'}], 164: [{'label': '2'}], 186: [{'label': '2'}], 86: [{'label': '1'}, {'label': '2'}]}\n"
]
}
],
"prompt_number": 11
},
{
"cell_type": "code",
......@@ -214,17 +317,17 @@
" def train(self):\n",
" for filepath in self.training_files:\n",
" x = ess.MonoLoader(filename=filepath)()\n",
" for frame in ess.FrameGenerator(x, frameSize=self.frame_size, hopSize=self.hop_size):\n",
" self.lsh.add(self.get_features(frame), filepath)\n",
" self.num_features_in_file[filepath] += 1\n",
" features = [self.get_features(frame) \n",
" for frame in ess.FrameGenerator(x, frameSize=self.frame_size, hopSize=self.hop_size)]\n",
" self.lsh.add(features, filepath)\n",
" self.num_features_in_file[filepath] += len(features)\n",
" \n",
" def query(self, filepath):\n",
" x = ess.MonoLoader(filename=filepath)()\n",
" features = [self.get_features(frame) \n",
" for frame in ess.FrameGenerator(x, frameSize=self.frame_size, hopSize=self.hop_size)]\n",
" results = list()\n",
" for vec in features:\n",
" results.extend(self.lsh.query(vec))\n",
" results = self.lsh.query(features)\n",
" print 'num results', len(results)\n",
"\n",
" counts = dict()\n",
" for r in results:\n",
......@@ -239,11 +342,10 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 8
"prompt_number": 12
},
{
"cell_type": "heading",
"level": 2,
"cell_type": "markdown",
"metadata": {},
"source": [
"Train:"
......@@ -259,11 +361,10 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 9
"prompt_number": 13
},
{
"cell_type": "heading",
"level": 2,
"cell_type": "markdown",
"metadata": {},
"source": [
"Test:"
......@@ -273,17 +374,24 @@
"cell_type": "code",
"collapsed": false,
"input": [
"test_file = '../test/steve_bach_p3.wav'\n",
"test_file = '../test/test.wav'\n",
"results = ms.query(test_file)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 10
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"num results 69490\n"
]
}
],
"prompt_number": 27
},
{
"cell_type": "heading",
"level": 2,
"cell_type": "markdown",
"metadata": {},
"source": [
"Display the results:"
......@@ -303,63 +411,63 @@
"output_type": "stream",
"stream": "stdout",
"text": [
"../train/brahms_s1_1_perlman_02.wav 8.69369369369\n",
"../train/bach_p3_1_perlman_01.wav 8.22522522523\n",
"../train/Beethoven_vln_sonata5_Francescatti_05.wav 8.22413793103\n",
"../train/Beethoven_vln_sonata5_Francescatti_03.wav 7.79518072289\n",
"../train/brahms_s1_1_perlman_04.wav 7.40540540541\n",
"../train/brahms_s1_1_perlman_01.wav 7.31531531532\n",
"../train/Beethoven_vln_sonata5_Zukerman_03.wav 6.53684210526\n",
"../train/brahms_s1_1_perlman_05.wav 6.18918918919\n",
"../train/Beethoven_vln_sonata5_Zukerman_01.wav 6.15094339623\n",
"../train/Beethoven_vln_sonata5_Francescatti_01.wav 6.125\n",
"../train/Beethoven_vln_sonata5_Francescatti_02.wav 5.984375\n",
"../train/Beethoven_vln_sonata5_Oistrakh_02.wav 5.95275590551\n",
"../train/brahms_s1_1_perlman_03.wav 5.94594594595\n",
"../train/Beethoven_vln_sonata5_Francescatti_04.wav 5.79245283019\n",
"../train/lady_madonna_crop.wav 5.70535714286\n",
"../train/brahms_rhapsody_02.wav 5.48823529412\n",
"../train/brahms_s1_1_perlman_06.wav 5.43243243243\n",
"../train/moonlight.wav 5.4\n",
"../train/office_theme.wav 5.39959839357\n",
"../train/brandenburg3_01.wav 5.37688442211\n",
"../train/lady_madonna.wav 5.21385542169\n",
"../train/Beethoven_vln_sonata5_Oistrakh_01.wav 5.11403508772\n",
"../train/bach_s3_3_szeryng_01.wav 4.89189189189\n",
"../train/bach_p3_1_heifetz_04.wav 4.87387387387\n",
"../train/konstantine.wav 4.87072243346\n",
"../train/Bach Vln Partita3 - Milstein 1955 - 01.wav 4.81233933162\n",
"../train/Beethoven_vln_sonata5_Zukerman_02.wav 4.62222222222\n",
"../train/Beethoven_vln_sonata5_Zukerman_04.wav 4.57391304348\n",
"../train/dont_stop_believin.wav 4.57256461233\n",
"../train/bach_p3_1_perlman_05.wav 4.4954954955\n",
"../train/Beethoven_vln_sonata5_Zukerman_05.wav 4.45833333333\n",
"../train/Beethoven_vln_sonata5_Oistrakh_03.wav 4.39772727273\n",
"../train/bach_p3_1_perlman_04.wav 4.33333333333\n",
"../train/Bach Vln Partita3 - Milstein 1955 - 03.wav 4.24712643678\n",
"../train/bach_p3_1_heifetz_01.wav 4.22522522523\n",
"../train/bach_p3_1_perlman_03.wav 4.17117117117\n",
"../train/Beethoven_vln_sonata5_Oistrakh_05.wav 4.07518796992\n",
"../train/Beethoven_vln_sonata5_Oistrakh_04.wav 4.01785714286\n",
"../train/Bach Vln Partita3 - Fischbach 2004 - 01.wav 3.77605321508\n",
"../train/bach_p3_1_perlman_02.wav 3.72972972973\n",
"../train/bach_s3_3_szeryng_05.wav 3.64864864865\n",
"../train/bach_p3_1_perlman_06.wav 3.51351351351\n",
"../train/brahms_rhapsody_01.wav 3.38855421687\n",
"../train/Bach Vln Partita3 - Fischbach 2004 - 03.wav 3.17877094972\n",
"../train/bach_p3_1_heifetz_03.wav 3.02702702703\n",
"../train/bach_p3_1_heifetz_02.wav 3.00900900901\n",
"../train/bach_s3_3_szeryng_06.wav 2.95495495495\n",
"../train/bach_s3_3_szeryng_02.wav 2.74774774775\n",
"../train/Bach Vln Sonata1 - Milstein 1954 - 02.wav 2.70438799076\n",
"../train/bach_p3_1_heifetz_05.wav 2.63963963964\n",
"../train/bach_s3_3_szeryng_04.wav 2.61261261261\n",
"../train/bach_s3_3_szeryng_03.wav 2.36936936937\n",
"../train/Bach Vln Sonata1 - Fischbach 2004 - 02.wav 2.36225596529\n"
"../train/bach_s3_3_szeryng_02.wav 16.9279279279\n",
"../train/bach_s3_3_szeryng_04.wav 14.2702702703\n",
"../train/Beethoven_vln_sonata5_Zukerman_03.wav 13.2526315789\n",
"../train/bach_s3_3_szeryng_03.wav 12.6036036036\n",
"../train/Beethoven_vln_sonata5_Oistrakh_02.wav 12.2755905512\n",
"../train/bach_s3_3_szeryng_01.wav 11.8018018018\n",
"../train/Beethoven_vln_sonata5_Zukerman_02.wav 11.7111111111\n",
"../train/Beethoven_vln_sonata5_Oistrakh_03.wav 11.6477272727\n",
"../train/Beethoven_vln_sonata5_Zukerman_04.wav 11.5739130435\n",
"../train/moonlight.wav 10.0018181818\n",
"../train/Beethoven_vln_sonata5_Oistrakh_04.wav 9.66071428571\n",
"../train/brahms_s1_1_perlman_06.wav 8.68468468468\n",
"../train/Beethoven_vln_sonata5_Francescatti_03.wav 8.59036144578\n",
"../train/brahms_s1_1_perlman_01.wav 8.45945945946\n",
"../train/Beethoven_vln_sonata5_Francescatti_02.wav 8.4375\n",
"../train/Beethoven_vln_sonata5_Francescatti_04.wav 8.30188679245\n",
"../train/Beethoven_vln_sonata5_Zukerman_01.wav 8.12264150943\n",
"../train/Beethoven_vln_sonata5_Oistrakh_01.wav 8.06140350877\n",
"../train/brandenburg3_01.wav 7.99497487437\n",
"../train/brahms_rhapsody_01.wav 7.61144578313\n",
"../train/Bach Vln Sonata1 - Fischbach 2004 - 02.wav 7.51626898048\n",
"../train/Beethoven_vln_sonata5_Zukerman_05.wav 7.45138888889\n",
"../train/Beethoven_vln_sonata5_Francescatti_01.wav 7.36538461538\n",
"../train/Bach Vln Partita3 - Milstein 1955 - 03.wav 7.24712643678\n",
"../train/brahms_rhapsody_02.wav 7.2\n",
"../train/brahms_s1_1_perlman_04.wav 6.90990990991\n",
"../train/dont_stop_believin.wav 6.76938369781\n",
"../train/konstantine.wav 6.60836501901\n",
"../train/Bach Vln Sonata1 - Milstein 1954 - 02.wav 6.54965357968\n",
"../train/brahms_s1_1_perlman_03.wav 6.43243243243\n",
"../train/brahms_s1_1_perlman_05.wav 6.10810810811\n",
"../train/lady_madonna_crop.wav 6.0625\n",
"../train/brahms_s1_1_perlman_02.wav 5.85585585586\n",
"../train/bach_s3_3_szeryng_05.wav 5.85585585586\n",
"../train/Beethoven_vln_sonata5_Francescatti_05.wav 5.81034482759\n",
"../train/bach_p3_1_perlman_04.wav 5.7027027027\n",
"../train/lady_madonna.wav 5.40662650602\n",
"../train/Bach Vln Partita3 - Fischbach 2004 - 03.wav 5.37709497207\n",
"../train/bach_p3_1_heifetz_04.wav 5.34234234234\n",
"../train/bach_p3_1_perlman_05.wav 5.27027027027\n",
"../train/Beethoven_vln_sonata5_Oistrakh_05.wav 5.1954887218\n",
"../train/bach_p3_1_heifetz_05.wav 5.10810810811\n",
"../train/bach_p3_1_perlman_06.wav 5.07207207207\n",
"../train/bach_p3_1_heifetz_01.wav 4.90990990991\n",
"../train/bach_s3_3_szeryng_06.wav 4.8018018018\n",
"../train/bach_p3_1_perlman_02.wav 4.55855855856\n",
"../train/bach_p3_1_perlman_01.wav 4.54954954955\n",
"../train/bach_p3_1_heifetz_02.wav 4.38738738739\n",
"../train/Bach Vln Partita3 - Fischbach 2004 - 01.wav 4.38580931264\n",
"../train/office_theme.wav 4.33734939759\n",
"../train/bach_p3_1_perlman_03.wav 3.99099099099\n",
"../train/Bach Vln Partita3 - Milstein 1955 - 01.wav 3.89974293059\n",
"../train/bach_p3_1_heifetz_03.wav 3.73873873874\n"
]
}
],
"prompt_number": 11
"prompt_number": 28
},
{
"cell_type": "code",
......@@ -368,7 +476,7 @@
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 11
"prompt_number": 15
}
],
"metadata": {}
......
notebooks/nmf.ipynb
View file @ be82b853
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/onset_detection.ipynb
View file @ be82b853
{
"metadata": {
"name": "",
"signature": "sha256:be6cfcdd1ec9b91debb9cd9886337318485f67d942cd35bab648a2c9c40acdbe"
"signature": "sha256:06a01c7defee6116c6bbb1fd895c49a6b3b4dfbaaa094f95f91bfbb0b1a490dc"
},
"nbformat": 3,
"nbformat_minor": 0,
......@@ -51,7 +51,7 @@
]
}
],
"prompt_number": 20
"prompt_number": 1
},
{
"cell_type": "markdown",
......@@ -75,21 +75,21 @@
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 21,
"prompt_number": 2,
"text": [
"<matplotlib.text.Text at 0x5333590>"
"<matplotlib.text.Text at 0x11438f410>"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEMCAYAAADDMN02AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
"png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEPCAYAAABFpK+YAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nREREREREREREREREREREpMj+F7GuHma8F7KdAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x5188550>"
"<matplotlib.figure.Figure at 0x1104f0610>"
]
}
],
"prompt_number": 21
"prompt_number": 2
},
{
"cell_type": "markdown",
......@@ -119,13 +119,13 @@
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 22,
"prompt_number": 3,
"text": [
"<IPython.lib.display.Audio at 0x532fe50>"
"<IPython.lib.display.Audio at 0x1104f0890>"
]
}
],
"prompt_number": 22
"prompt_number": 3
},
{
"cell_type": "heading",
......@@ -164,7 +164,7 @@
]
}
],
"prompt_number": 23
"prompt_number": 4
},
{
"cell_type": "heading",
......@@ -204,13 +204,13 @@
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 24,
"prompt_number": 5,
"text": [
"<IPython.lib.display.Audio at 0x5154d90>"
"<IPython.lib.display.Audio at 0x11531d890>"
]
}
],
"prompt_number": 24
"prompt_number": 5
},
{
"cell_type": "markdown",
......
notebooks/pitch_transcription_answer.ipynb
View file @ be82b853
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment