[mnist] visualizing individual filters tensorflow notebook

filters.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import matplotlib as mp\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "\n",
    "# %% Imports\n",
    "%matplotlib inline\n",
    "import tensorflow as tf\n",
    "import tensorflow.examples.tutorials.mnist.input_data as input_data\n",
    "from libs.utils import *\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting MNIST_data/train-images-idx3-ubyte.gz\n",
      "Extracting MNIST_data/train-labels-idx1-ubyte.gz\n",
      "Extracting MNIST_data/t10k-images-idx3-ubyte.gz\n",
      "Extracting MNIST_data/t10k-labels-idx1-ubyte.gz\n"
     ]
    }
   ],
   "source": [
    "mnist = input_data.read_data_sets(\"MNIST_data/\", one_hot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "sess = tf.Session()\n",
    "\n",
    "x = tf.placeholder(tf.float32, [None, 784],name=\"x-in\")\n",
    "y_ = tf.placeholder(tf.float32, [None, 10],name=\"y-in\")\n",
    "\n",
    "def weight_variable(shape):\n",
    "    initial = tf.truncated_normal(shape, stddev=0.1)\n",
    "    return tf.Variable(initial)\n",
    "\n",
    "def bias_variable(shape):\n",
    "    initial = tf.constant(0.1, shape=shape)\n",
    "    return tf.Variable(initial)\n",
    "\n",
    "def conv2d(x, W):\n",
    "    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')\n",
    "\n",
    "def max_pool_2x2(x):\n",
    "    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')\n",
    "\n",
    "x_image = tf.reshape(x, [-1,28,28,1])\n",
    "W_conv1 = weight_variable([5, 5, 1, 5])\n",
    "b_conv1 = bias_variable([5])\n",
    "h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)\n",
    "h_pool1 = max_pool_2x2(h_conv1)\n",
    "\n",
    "W_conv2 = weight_variable([5, 5, 5, 5])\n",
    "b_conv2 = bias_variable([5])\n",
    "h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)\n",
    "h_pool2 = max_pool_2x2(h_conv2)\n",
    "\n",
    "W_conv3 = weight_variable([5, 5, 5, 20])\n",
    "b_conv3 = bias_variable([20])\n",
    "h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)\n",
    "\n",
    "W_fc1 = weight_variable([7 * 7 * 20, 10])\n",
    "b_fc1 = bias_variable([10])\n",
    "h_conv3_flat = tf.reshape(h_conv3, [-1, 7*7*20])\n",
    "keep_prob = tf.placeholder(\"float\")\n",
    "h_conv3_drop = tf.nn.dropout(h_conv3_flat, keep_prob)\n",
    "y_conv = tf.nn.softmax(tf.matmul(h_conv3_drop, W_fc1) + b_fc1)\n",
    "\n",
    "cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))\n",
    "correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))\n",
    "accuracy = tf.reduce_mean(tf.cast(correct_prediction, \"float\"))\n",
    "train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "step 0, training accuracy 0.16\n",
      "step 100, training accuracy 0.4\n",
      "step 200, training accuracy 0.46\n",
      "step 300, training accuracy 0.66\n",
      "step 400, training accuracy 0.78\n",
      "step 500, training accuracy 0.78\n",
      "step 600, training accuracy 0.84\n",
      "step 700, training accuracy 0.88\n",
      "step 800, training accuracy 0.84\n",
      "step 900, training accuracy 0.96\n",
      "step 1000, training accuracy 0.88\n"
     ]
    }
   ],
   "source": [
    "sess.run(tf.initialize_all_variables())\n",
    "iterations = 0\n",
    "batchSize = 50\n",
    "while iterations < 1001:\n",
    "    batch = mnist.train.next_batch(batchSize)\n",
    "    train_step.run(session=sess, feed_dict={x:batch[0],y_:batch[1], keep_prob:0.5})\n",
    "    if iterations%100 == 0:\n",
    "        trainAccuracy = accuracy.eval(session=sess, feed_dict={x:batch[0],y_:batch[1], keep_prob:1.0})\n",
    "        print(\"step %d, training accuracy %g\"%(iterations, trainAccuracy))\n",
    "    iterations += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test accuracy 0.8918\n"
     ]
    }
   ],
   "source": [
    "testAccuracy = accuracy.eval(session=sess, feed_dict={x:mnist.test.images,y_:mnist.test.labels, keep_prob:1.0})\n",
    "print(\"test accuracy %g\"%(testAccuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def getActivations(layer,stimuli):\n",
    "    units = layer.eval(session=sess,feed_dict={x:np.reshape(stimuli,[1,784],order='F'),keep_prob:1.0})\n",
    "    plotNNFilter(units)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def plotNNFilter(units):\n",
    "    filters = units.shape[3]\n",
    "    plt.figure(1, figsize=(20,20))\n",
    "    for i in xrange(0,filters):\n",
    "        plt.subplot(7,6,i+1)\n",
    "        plt.title('Filter ' + str(i))\n",
    "        plt.imshow(units[0,:,:,i], interpolation=\"nearest\", cmap=\"gray\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fec81d0e510>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAV8AAAFfCAYAAADptc+BAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fecb805b690>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "imageToUse = mnist.test.images[0]\n",
    "plt.imshow(np.reshape(imageToUse,[28,28]), interpolation=\"nearest\", cmap=\"gray\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can look at how that image activates the neurons of the first convolutional layer. Notice how each filter has learned to activate optimally for different features of the image. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABQ0AAAD3CAYAAAC3tXJBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n1psSboxU/RYAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fec969e5490>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "getActivations(h_conv1,imageToUse)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can do this again for the second layer..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABQwAAAD3CAYAAABYdxl/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAAAAAAAAAAAAAAAAAAAAYMX7/90DJM9G/TpLAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fec81b96250>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "getActivations(h_conv2,imageToUse)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "...and the third."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABg4AAAOgCAYAAADlA42RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fec81b60450>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "getActivations(h_conv3,imageToUse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "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
}