94-775, 95-865 Neural net handwritten digit recognition.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "# This demo draws heavily from the handwritten digit example in\n",
    "# Chapter 2 of Francois Chollet's \"Deep Learning with Python\" book.\n",
    "# I've added a simpler single-layer example first before moving to\n",
    "# the 2-layer example. -George Chen (CMU Fall 2017)\n",
    "\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "from keras.datasets import mnist\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense\n",
    "\n",
    "(train_images, train_labels), (test_images, test_labels) = mnist.load_data()\n",
    "\n",
    "flattened_train_images = train_images.reshape(len(train_images), -1)  # flattens out each training image\n",
    "flattened_train_images = flattened_train_images.astype(np.float32) / 255  # rescale to be between 0 and 1\n",
    "flattened_test_images = test_images.reshape(len(test_images), -1)  # flattens out each test image\n",
    "flattened_test_images = flattened_test_images.astype(np.float32) / 255  # rescale to be between 0 and 1\n",
    "\n",
    "from keras.utils import to_categorical\n",
    "train_labels_categorical = to_categorical(train_labels)\n",
    "test_labels_categorical = to_categorical(test_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_labels[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 0., 0., 0., 0., 1., 0., 0., 0., 0.], dtype=float32)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_labels_categorical[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_1 (Dense)              (None, 10)                7850      \n",
      "=================================================================\n",
      "Total params: 7,850\n",
      "Trainable params: 7,850\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "# extremely shallow single-layer model\n",
    "single_layer_model = Sequential()  # this is Keras's way of specifying a model that is a single sequence of layers\n",
    "single_layer_model.add(Dense(10, activation='softmax', input_shape=(784,)))\n",
    "single_layer_model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "single_layer_model.compile(optimizer='rmsprop',\n",
    "                           loss='categorical_crossentropy',\n",
    "                           metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 48000 samples, validate on 12000 samples\n",
      "Epoch 1/5\n",
      "48000/48000 [==============================] - 3s 66us/step - loss: 0.6779 - acc: 0.8305 - val_loss: 0.3614 - val_acc: 0.9015\n",
      "Epoch 2/5\n",
      "48000/48000 [==============================] - 3s 62us/step - loss: 0.3526 - acc: 0.9020 - val_loss: 0.3081 - val_acc: 0.9163\n",
      "Epoch 3/5\n",
      "48000/48000 [==============================] - 3s 67us/step - loss: 0.3159 - acc: 0.9120 - val_loss: 0.2895 - val_acc: 0.9203\n",
      "Epoch 4/5\n",
      "48000/48000 [==============================] - 3s 64us/step - loss: 0.2994 - acc: 0.9166 - val_loss: 0.2807 - val_acc: 0.9223\n",
      "Epoch 5/5\n",
      "48000/48000 [==============================] - 3s 62us/step - loss: 0.2896 - acc: 0.9183 - val_loss: 0.2771 - val_acc: 0.9217\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x13275d0f0>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "single_layer_model.fit(flattened_train_images,\n",
    "                       train_labels_categorical,\n",
    "                       validation_split=0.2,\n",
    "                       epochs=5,\n",
    "                       batch_size=128)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_2 (Dense)              (None, 512)               401920    \n",
      "_________________________________________________________________\n",
      "dense_3 (Dense)              (None, 10)                5130      \n",
      "=================================================================\n",
      "Total params: 407,050\n",
      "Trainable params: 407,050\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "# two-layer model\n",
    "two_layer_model = Sequential()  # this is Keras's way of specifying a model that is a single sequence of layers\n",
    "two_layer_model.add(Dense(512, activation='relu', input_shape=(784,)))\n",
    "two_layer_model.add(Dense(10, activation='softmax'))\n",
    "two_layer_model.compile(optimizer='rmsprop',\n",
    "                        loss='categorical_crossentropy',\n",
    "                        metrics=['accuracy'])\n",
    "two_layer_model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 48000 samples, validate on 12000 samples\n",
      "Epoch 1/5\n",
      "48000/48000 [==============================] - 55s 1ms/step - loss: 0.2878 - acc: 0.9173 - val_loss: 0.1465 - val_acc: 0.9573\n",
      "Epoch 2/5\n",
      "48000/48000 [==============================] - 53s 1ms/step - loss: 0.1178 - acc: 0.9654 - val_loss: 0.1098 - val_acc: 0.9672\n",
      "Epoch 3/5\n",
      "48000/48000 [==============================] - 53s 1ms/step - loss: 0.0774 - acc: 0.9772 - val_loss: 0.0925 - val_acc: 0.9714\n",
      "Epoch 4/5\n",
      "48000/48000 [==============================] - 54s 1ms/step - loss: 0.0559 - acc: 0.9836 - val_loss: 0.0898 - val_acc: 0.9707\n",
      "Epoch 5/5\n",
      "48000/48000 [==============================] - 52s 1ms/step - loss: 0.0419 - acc: 0.9871 - val_loss: 0.0795 - val_acc: 0.9773\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x132735a20>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "two_layer_model.fit(flattened_train_images,\n",
    "                    train_labels_categorical,\n",
    "                    validation_split=0.2,\n",
    "                    epochs=5,\n",
    "                    batch_size=128)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Finally evaluate on test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 0s 48us/step\n",
      "Test accuracy: 0.9216\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = single_layer_model.evaluate(flattened_test_images, test_labels_categorical)\n",
    "print('Test accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 5s 503us/step\n",
      "Test accuracy: 0.9776\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = two_layer_model.evaluate(flattened_test_images, test_labels_categorical)\n",
    "print('Test accuracy:', test_acc)"
   ]
  }
 ],
 "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}