deep learning mnist dataset.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.datasets import mnist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n",
      "11493376/11490434 [==============================] - 61s 5us/step\n"
     ]
    }
   ],
   "source": [
    "(train_images, train_labels),(test_images,test_lables) =mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(60000, 28, 28)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_images.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "60000"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras import models\n",
    "from keras import layers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "network = models.Sequential()\n",
    "network.add(layers.Dense(512, activation = 'relu', input_shape = (28*28,)))\n",
    "network.add(layers.Dense(10, activation = 'softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "network.compile(optimizer = 'rmsprop', loss = 'categorical_crossentropy', metrics = ['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_images = train_images.reshape(60000,28*28)\n",
    "test_images  = test_images.reshape(10000,28*28)\n",
    "train_images = train_images.astype('float32')/255\n",
    "test_images = test_images.astype('float32')/255"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.utils import to_categorical\n",
    "train_labels = to_categorical(train_labels)\n",
    "test_lables = to_categorical(test_lables)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "60000/60000 [==============================] - 11s 187us/step - loss: 0.2537 - acc: 0.9279\n",
      "Epoch 2/5\n",
      "60000/60000 [==============================] - 10s 171us/step - loss: 0.1035 - acc: 0.9691\n",
      "Epoch 3/5\n",
      "60000/60000 [==============================] - 10s 172us/step - loss: 0.0684 - acc: 0.9792\n",
      "Epoch 4/5\n",
      "60000/60000 [==============================] - 11s 176us/step - loss: 0.0495 - acc: 0.9850\n",
      "Epoch 5/5\n",
      "60000/60000 [==============================] - 11s 178us/step - loss: 0.0363 - acc: 0.9891\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x263416b0908>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "network.fit(train_images,train_labels,batch_size=128,epochs=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 1s 129us/step\n",
      "0.9796\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = network.evaluate(test_images,test_lables)\n",
    "print(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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}