{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sequential and Functional Interfaces"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.simplefilter(action='ignore', category=FutureWarning)\n",
    "import h5py\n",
    "warnings.resetwarnings()\n",
    "warnings.simplefilter(action='ignore', category=ImportWarning)\n",
    "warnings.simplefilter(action='ignore', category=RuntimeWarning)\n",
    "warnings.simplefilter(action='ignore', category=DeprecationWarning)\n",
    "warnings.simplefilter(action='ignore', category=ResourceWarning)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "from keras import models\n",
    "from keras import layers\n",
    "from keras import optimizers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.utils import to_categorical\n",
    "from keras.datasets import mnist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "(X_train, y_train), (X_test, y_test) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = X_train.reshape((-1, 28*28))\n",
    "X_train = X_train.astype('float32')/255\n",
    "X_test = X_test.reshape((-1, 28*28))\n",
    "X_test = X_test.astype('float32')/255\n",
    "y_train = to_categorical(y_train)\n",
    "y_test = to_categorical(y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Sequential Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = models.Sequential()\n",
    "model.add(layers.Dense(32, activation='relu', input_shape=(28*28,)))\n",
    "model.add(layers.Dense(10, activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='rmsprop',\n",
    "              loss='categorical_crossentropy',\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "60000/60000 [==============================] - 7s 113us/step - loss: 0.4663 - acc: 0.8763\n",
      "Epoch 2/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.2368 - acc: 0.9319\n",
      "Epoch 3/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1959 - acc: 0.9429\n",
      "Epoch 4/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1701 - acc: 0.9505\n",
      "Epoch 5/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1519 - acc: 0.9554\n",
      "Epoch 6/10\n",
      "60000/60000 [==============================] - 1s 23us/step - loss: 0.1380 - acc: 0.9591\n",
      "Epoch 7/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1265 - acc: 0.9634\n",
      "Epoch 8/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1175 - acc: 0.9660\n",
      "Epoch 9/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1104 - acc: 0.9675\n",
      "Epoch 10/10\n",
      "60000/60000 [==============================] - 1s 21us/step - loss: 0.1038 - acc: 0.9688\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f2cc7c0e630>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train, y_train, \n",
    "          batch_size=128, epochs=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 0s 38us/step\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = model.evaluate(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.12339150645062327, 0.9629)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_loss, test_acc"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Functional Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_tensor = layers.Input(shape=(784,))\n",
    "x = layers.Dense(32, activation='relu')(input_tensor)\n",
    "output_tensor = layers.Dense(10, activation='softmax')(x)\n",
    "model = models.Model(inputs=input_tensor, outputs=output_tensor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='rmsprop',\n",
    "              loss='categorical_crossentropy',\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "60000/60000 [==============================] - 1s 23us/step - loss: 0.4438 - acc: 0.8815\n",
      "Epoch 2/10\n",
      "60000/60000 [==============================] - 1s 21us/step - loss: 0.2417 - acc: 0.9304\n",
      "Epoch 3/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1989 - acc: 0.9432\n",
      "Epoch 4/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1719 - acc: 0.9506\n",
      "Epoch 5/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1527 - acc: 0.9558\n",
      "Epoch 6/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1384 - acc: 0.9600\n",
      "Epoch 7/10\n",
      "60000/60000 [==============================] - 1s 21us/step - loss: 0.1272 - acc: 0.9631\n",
      "Epoch 8/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1174 - acc: 0.9655\n",
      "Epoch 9/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1104 - acc: 0.9677\n",
      "Epoch 10/10\n",
      "60000/60000 [==============================] - 1s 22us/step - loss: 0.1034 - acc: 0.9699\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f2cc585a898>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train, y_train, \n",
    "          batch_size=128, epochs=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 0s 40us/step\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = model.evaluate(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.12404100528806448, 0.964)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_loss, test_acc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}