just finished ch15 code

Author: rasbt

code/ch15/computing-convolution.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Sebastian Raschka 2017-08-19 \n",
+      "\n",
+      "numpy 1.12.1\n",
+      "scipy 0.19.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "%load_ext watermark\n",
+    "%watermark -a 'Sebastian Raschka' -d -p numpy,scipy"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Convolution in 1D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conv1d Implementation:  [  5.  14.  16.  26.  24.  34.  19.  22.]\n",
+      "Numpy Results:          [ 5 14 16 26 24 34 19 22]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "\n",
+    "def conv1d(x, w, p=0, s=1):\n",
+    "    w_rot = np.array(w[::-1])\n",
+    "    x_padded = np.array(x)\n",
+    "    if p > 0:\n",
+    "        zero_pad = np.zeros(shape=p)\n",
+    "        x_padded = np.concatenate([zero_pad, x_padded, zero_pad])\n",
+    "    res = []\n",
+    "    for i in range(0, int(len(x)/s),s):\n",
+    "        res.append(np.sum(x_padded[i:i+w_rot.shape[0]] * w_rot))\n",
+    "    return np.array(res)\n",
+    "\n",
+    "## Testing:\n",
+    "x = [1, 3, 2, 4, 5, 6, 1, 3]\n",
+    "w = [1, 0, 3, 1, 2]\n",
+    "print('Conv1d Implementation: ', \n",
+    "      conv1d(x, w, p=2, s=1))\n",
+    "print('Numpy Results:         ', \n",
+    "      np.convolve(x, w, mode='same'))\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Convolution in 2D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conv2d Implementation: \n",
+      " [[ 11.  25.  32.  13.]\n",
+      " [ 19.  25.  24.  13.]\n",
+      " [ 13.  28.  25.  17.]\n",
+      " [ 11.  17.  14.   9.]]\n",
+      "Scipy Results:         \n",
+      " [[11 25 32 13]\n",
+      " [19 25 24 13]\n",
+      " [13 28 25 17]\n",
+      " [11 17 14  9]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import scipy.signal\n",
+    "\n",
+    "\n",
+    "def conv2d(X, W, p=(0,0), s=(1,1)):\n",
+    "    W_rot = np.array(W)[::-1,::-1]\n",
+    "    X_orig = np.array(X)\n",
+    "    n1 = X_orig.shape[0] + 2*p[0]\n",
+    "    n2 = X_orig.shape[1] + 2*p[1]\n",
+    "    X_padded = np.zeros(shape=(n1,n2))\n",
+    "    X_padded[p[0]:p[0]+X_orig.shape[0], \n",
+    "             p[1]:p[1]+X_orig.shape[1]] = X_orig\n",
+    "\n",
+    "    res = []\n",
+    "    for i in range(0, int((X_padded.shape[0] - \\\n",
+    "                           W_rot.shape[0])/s[0])+1, s[0]):\n",
+    "        res.append([])\n",
+    "        for j in range(0, int((X_padded.shape[1] - \\\n",
+    "                               W_rot.shape[1])/s[1])+1, s[1]):\n",
+    "            X_sub = X_padded[i:i+W_rot.shape[0],j:j+W_rot.shape[1]]\n",
+    "            res[-1].append(np.sum(X_sub * W_rot))\n",
+    "    return(np.array(res))\n",
+    "    \n",
+    "X = [[1, 3, 2, 4], [5, 6, 1, 3], [1 , 2,0, 2], [3, 4, 3, 2]]\n",
+    "W = [[1, 0, 3], [1, 2, 1], [0, 1, 1]]\n",
+    "print('Conv2d Implementation: \\n', \n",
+    "      conv2d(X, W, p=(1,1), s=(1,1)))\n",
+    "\n",
+    "print('Scipy Results:         \\n', \n",
+    "      scipy.signal.convolve2d(X, W, mode='same'))\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "## Loading image with SciPy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Image shape:  (252, 221, 3)\n",
+      "Number of channels:  3\n",
+      "Image data type:  uint8\n",
+      "[[[179 134 110]\n",
+      "  [182 136 112]]\n",
+      "\n",
+      " [[180 135 111]\n",
+      "  [182 137 113]]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import scipy.misc\n",
+    "\n",
+    "\n",
+    "img = scipy.misc.imread('./example-image.png', mode='RGB')\n",
+    "\n",
+    "print('Image shape: ', img.shape)\n",
+    "print('Number of channels: ', img.shape[2])\n",
+    "print('Image data type: ', img.dtype)\n",
+    "\n",
+    "print(img[100:102,100:102,:])\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.6.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}