{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from keras.models import Model\n",
    "from keras.layers import Input\n",
    "from keras.layers.pooling import GlobalMaxPooling1D\n",
    "from keras import backend as K"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def format_decimal(arr, places=6):\n",
    "    return [round(x * 10**places) / 10**places for x in arr]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### GlobalMaxPooling1D"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**[pooling.GlobalMaxPooling1D.0] input 6x6**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "in shape: (6, 6)\n",
      "in: [-0.806777, -0.564841, -0.481331, 0.559626, 0.274958, -0.659222, -0.178541, 0.689453, -0.028873, 0.053859, -0.446394, -0.53406, 0.776897, -0.700858, -0.802179, -0.616515, 0.718677, 0.303042, -0.080606, -0.850593, -0.795971, 0.860487, -0.90685, 0.89858, 0.617251, 0.334305, -0.351137, -0.642574, 0.108974, -0.993964, 0.051085, -0.372012, 0.843766, 0.088025, -0.598662, 0.789035]\n",
      "out shape: (6,)\n",
      "out: [0.776897, 0.689453, 0.843766, 0.860487, 0.718677, 0.89858]\n"
     ]
    }
   ],
   "source": [
    "data_in_shape = (6, 6)\n",
    "L = GlobalMaxPooling1D()\n",
    "\n",
    "layer_0 = Input(shape=data_in_shape)\n",
    "layer_1 = L(layer_0)\n",
    "model = Model(input=layer_0, output=layer_1)\n",
    "\n",
    "# set weights to random (use seed for reproducibility)\n",
    "np.random.seed(260)\n",
    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
    "print('')\n",
    "print('in shape:', data_in_shape)\n",
    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
    "result = model.predict(np.array([data_in]))\n",
    "print('out shape:', result[0].shape)\n",
    "print('out:', format_decimal(result[0].ravel().tolist()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**[pooling.GlobalMaxPooling1D.1] input 3x7**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "in shape: (3, 7)\n",
      "in: [0.601872, -0.028379, 0.654213, 0.217731, -0.864161, 0.422013, 0.888312, -0.714141, -0.184753, 0.224845, -0.221123, -0.847943, -0.511334, -0.871723, -0.597589, -0.889034, -0.544887, -0.004798, 0.406639, -0.35285, 0.648562]\n",
      "out shape: (7,)\n",
      "out: [0.601872, -0.028379, 0.654213, 0.217731, 0.406639, 0.422013, 0.888312]\n"
     ]
    }
   ],
   "source": [
    "data_in_shape = (3, 7)\n",
    "L = GlobalMaxPooling1D()\n",
    "\n",
    "layer_0 = Input(shape=data_in_shape)\n",
    "layer_1 = L(layer_0)\n",
    "model = Model(input=layer_0, output=layer_1)\n",
    "\n",
    "# set weights to random (use seed for reproducibility)\n",
    "np.random.seed(261)\n",
    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
    "print('')\n",
    "print('in shape:', data_in_shape)\n",
    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
    "result = model.predict(np.array([data_in]))\n",
    "print('out shape:', result[0].shape)\n",
    "print('out:', format_decimal(result[0].ravel().tolist()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**[pooling.GlobalMaxPooling1D.2] input 8x4**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "in shape: (8, 4)\n",
      "in: [-0.215694, 0.441215, 0.116911, 0.53299, 0.883562, -0.535525, -0.869764, -0.596287, 0.576428, -0.689083, -0.132924, -0.129935, -0.17672, -0.29097, 0.590914, 0.992098, 0.908965, -0.170202, 0.640203, 0.178644, 0.866749, -0.545566, -0.827072, 0.420342, -0.076191, 0.207686, -0.908472, -0.795307, -0.948319, 0.683682, -0.563278, -0.82135]\n",
      "out shape: (4,)\n",
      "out: [0.908965, 0.683682, 0.640203, 0.992098]\n"
     ]
    }
   ],
   "source": [
    "data_in_shape = (8, 4)\n",
    "L = GlobalMaxPooling1D()\n",
    "\n",
    "layer_0 = Input(shape=data_in_shape)\n",
    "layer_1 = L(layer_0)\n",
    "model = Model(input=layer_0, output=layer_1)\n",
    "\n",
    "# set weights to random (use seed for reproducibility)\n",
    "np.random.seed(262)\n",
    "data_in = 2 * np.random.random(data_in_shape) - 1\n",
    "print('')\n",
    "print('in shape:', data_in_shape)\n",
    "print('in:', format_decimal(data_in.ravel().tolist()))\n",
    "result = model.predict(np.array([data_in]))\n",
    "print('out shape:', result[0].shape)\n",
    "print('out:', format_decimal(result[0].ravel().tolist()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": 0
}