{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
      "11490434/11490434 [==============================] - 3s 0us/step\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "import ssl\n",
    "ssl._create_default_https_context = ssl._create_unverified_context\n",
    "(xtrain, ytrain),(xtest,ytest) = tf.keras.datasets.mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x161118fa0>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "image_index = 7777\n",
    "print(ytrain[image_index])\n",
    "plt.imshow(xtrain[image_index],cmap= 'Greys')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(60000, 28, 28)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xtrain.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train Shape: (60000, 28, 28, 1)\n",
      "Number of images in x_train 60000\n",
      "Number of images in x_test 10000\n"
     ]
    }
   ],
   "source": [
    "xtrain = xtrain.reshape(xtrain.shape[0], 28, 28, 1)\n",
    "xtest = xtest.reshape(xtest.shape[0], 28,28,1)\n",
    "input_shape = (28,28,1)\n",
    "\n",
    "xtrain = xtrain.astype('float32')\n",
    "xtest = xtest.astype('float32')\n",
    "\n",
    "xtrain /= 255\n",
    "xtest /= 255\n",
    "\n",
    "print('x_train Shape:', xtrain.shape)\n",
    "print('Number of images in x_train', xtrain.shape[0])\n",
    "print('Number of images in x_test', xtest.shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Sequential\n",
    "from keras.layers import Dense,Conv2D, Dropout, Flatten, MaxPooling2D\n",
    "\n",
    "model = Sequential()\n",
    "model.add(Conv2D(28, kernel_size=(3,3), input_shape = input_shape))\n",
    "model.add(MaxPooling2D(pool_size=(2,2)))\n",
    "model.add(Flatten())\n",
    "model.add(Dense(128, activation=tf.nn.relu))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(Dense(10, activation= tf.nn.softmax))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "1875/1875 [==============================] - 25s 13ms/step - loss: 0.2077 - accuracy: 0.9379\n",
      "Epoch 2/10\n",
      "1875/1875 [==============================] - 22s 12ms/step - loss: 0.0807 - accuracy: 0.9757\n",
      "Epoch 3/10\n",
      "1875/1875 [==============================] - 22s 12ms/step - loss: 0.0561 - accuracy: 0.9826\n",
      "Epoch 4/10\n",
      "1875/1875 [==============================] - 22s 12ms/step - loss: 0.0423 - accuracy: 0.9863\n",
      "Epoch 5/10\n",
      "1875/1875 [==============================] - 22s 12ms/step - loss: 0.0348 - accuracy: 0.9884\n",
      "Epoch 6/10\n",
      "1875/1875 [==============================] - 22s 12ms/step - loss: 0.0275 - accuracy: 0.9910\n",
      "Epoch 7/10\n",
      "1875/1875 [==============================] - 24s 13ms/step - loss: 0.0242 - accuracy: 0.9916\n",
      "Epoch 8/10\n",
      "1875/1875 [==============================] - 24s 13ms/step - loss: 0.0196 - accuracy: 0.9935\n",
      "Epoch 9/10\n",
      "1875/1875 [==============================] - 23s 12ms/step - loss: 0.0194 - accuracy: 0.9936\n",
      "Epoch 10/10\n",
      "1875/1875 [==============================] - 23s 12ms/step - loss: 0.0175 - accuracy: 0.9936\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x161433e80>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.compile(optimizer='adam',\n",
    "              loss = 'sparse_categorical_crossentropy',\n",
    "              metrics=['accuracy'])\n",
    "model.fit(x = xtrain, y = ytrain, epochs = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "313/313 [==============================] - 1s 4ms/step - loss: 0.0584 - accuracy: 0.9861\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.05844942107796669, 0.9861000180244446]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(xtest, ytest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 136ms/step\n",
      "9\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "image_index = 4444\n",
    "plt.imshow(xtest[image_index].reshape(28,28), cmap = 'Greys')\n",
    "pred = model.predict(xtest[image_index].reshape(1,28,28,1))\n",
    "print(pred.argmax())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 27ms/step\n",
      "1\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "image_index = 3625\n",
    "plt.imshow(xtest[image_index].reshape(28,28), cmap = 'Greys')\n",
    "pred = model.predict(xtest[image_index].reshape(1,28,28,1))\n",
    "print(pred.argmax())"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### THANK YOU!"
   ]
  }
 ],
 "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": "3.10.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}