{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "\n",
    "I = [1, 0, 2, 3, 0, 1, 1] * 100\n",
    "K = [2, 1, 3] * 10\n",
    "\n",
    "i = tf.constant(I, dtype=tf.float32, name='i')\n",
    "k = tf.constant(K, dtype=tf.float32, name='k')\n",
    "\n",
    "data   = tf.reshape(i, [1, int(i.shape[0]), 1], name='data')\n",
    "kernel = tf.reshape(k, [int(k.shape[0]), 1, 1], name='kernel')\n",
    "\n",
    "res = tf.squeeze(tf.nn.conv1d(data, kernel, 1, 'VALID'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sess = tf.Session()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "109 µs ± 4.34 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "result_tf = sess.run(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "76.3 µs ± 1.67 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "result_np = np.convolve(I, K[::-1], 'VALID')"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [default]",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}