keras

keras.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "aNyZv-Ec52ot"
   },
   "source": [
    "# **Import Libraries and modules**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "3m3w1Cw49Zkt"
   },
   "outputs": [],
   "source": [
    "# https://keras.io/\n",
    "# !pip install -q keras\n",
    "import keras"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "Eso6UHE080D4",
    "outputId": "5b9f89e3-75ed-4f87-ea12-e15e01f15e18"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Dropout, Activation, Flatten, Add\n",
    "from keras.layers import Convolution2D, MaxPooling2D\n",
    "from keras.utils import np_utils\n",
    "\n",
    "from keras.datasets import mnist"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "zByEi95J86RD"
   },
   "source": [
    "### Load pre-shuffled MNIST data into train and test sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 54
    },
    "colab_type": "code",
    "id": "7eRM0QWN83PV",
    "outputId": "7577d6a9-4503-4833-d61b-d906821dab72"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n",
      "11493376/11490434 [==============================] - 9s 1us/step\n"
     ]
    }
   ],
   "source": [
    "(X_train, y_train), (X_test, y_test) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 302
    },
    "colab_type": "code",
    "id": "4a4Be72j8-ZC",
    "outputId": "a9d7c0ee-bc49-47c7-95bd-84965edcc1b0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(60000, 28, 28)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fe912863f60>"
      ]
     },
     "execution_count": 4,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD4CAYAAADFJPs2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fe9632695f8>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "print (X_train.shape)\n",
    "from matplotlib import pyplot as plt\n",
    "%matplotlib inline\n",
    "plt.imshow(X_train[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "dkmprriw9AnZ"
   },
   "outputs": [],
   "source": [
    "X_train = X_train.reshape(X_train.shape[0], 28, 28,1)\n",
    "X_test = X_test.reshape(X_test.shape[0], 28, 28,1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "X2m4YS4E9CRh"
   },
   "outputs": [],
   "source": [
    "X_train = X_train.astype('float32')\n",
    "X_test = X_test.astype('float32')\n",
    "X_train /= 255\n",
    "X_test /= 255"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "0Mn0vAYD9DvB",
    "outputId": "e10d5f16-e10e-4c99-ef25-d0e5054adb76"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5, 0, 4, 1, 9, 2, 1, 3, 1, 4], dtype=uint8)"
      ]
     },
     "execution_count": 7,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "ZG8JiXR39FHC"
   },
   "outputs": [],
   "source": [
    "# Convert 1-dimensional class arrays to 10-dimensional class matrices\n",
    "Y_train = np_utils.to_categorical(y_train, 10)\n",
    "Y_test = np_utils.to_categorical(y_test, 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 201
    },
    "colab_type": "code",
    "id": "fYlFRvKS9HMB",
    "outputId": "2a3054de-a572-476d-8ee2-9be7f2157ef2"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n",
       "       [1., 0., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 1., 0., 0., 0., 0., 0.],\n",
       "       [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 0., 0., 0., 0., 0., 1.],\n",
       "       [0., 0., 1., 0., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 1., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 1., 0., 0., 0., 0., 0.]], dtype=float32)"
      ]
     },
     "execution_count": 9,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_train[:10]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 110
    },
    "colab_type": "code",
    "id": "osKqT73Q9JJB",
    "outputId": "4e8640d2-088a-4f6a-8d94-0fd2be15c104"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:5: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (5, 5), activation=\"relu\", input_shape=(28, 28, 1...)`\n",
      "  \"\"\"\n",
      "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:9: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), activation=\"relu\")`\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "from keras.layers import Activation\n",
    "model = Sequential()\n",
    "\n",
    " \n",
    "model.add(Convolution2D(32, 5,5, activation='relu', input_shape=(28,28,1)))\n",
    "model.add(Dropout(0.7))\n",
    "model.add(MaxPooling2D(pool_size=2, strides=None, padding='valid'))\n",
    "model.add(Convolution2D(32, 3, 3, activation='relu'))\n",
    "model.add(Convolution2D(10, 10))\n",
    "model.add(Flatten())\n",
    "model.add(Activation('softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 403
    },
    "colab_type": "code",
    "id": "TzdAYg1k9K7Z",
    "outputId": "d5774704-04b1-478f-b169-ba04b7279e6b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "conv2d_14 (Conv2D)           (None, 24, 24, 32)        832       \n",
      "_________________________________________________________________\n",
      "dropout_5 (Dropout)          (None, 24, 24, 32)        0         \n",
      "_________________________________________________________________\n",
      "max_pooling2d_5 (MaxPooling2 (None, 12, 12, 32)        0         \n",
      "_________________________________________________________________\n",
      "conv2d_15 (Conv2D)           (None, 10, 10, 32)        9248      \n",
      "_________________________________________________________________\n",
      "conv2d_16 (Conv2D)           (None, 1, 1, 10)          32010     \n",
      "_________________________________________________________________\n",
      "flatten_4 (Flatten)          (None, 10)                0         \n",
      "_________________________________________________________________\n",
      "activation_4 (Activation)    (None, 10)                0         \n",
      "=================================================================\n",
      "Total params: 42,090\n",
      "Trainable params: 42,090\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "Zp6SuGrL9M3h"
   },
   "outputs": [],
   "source": [
    "model.compile(loss='categorical_crossentropy',\n",
    "             optimizer='adam',\n",
    "             metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 439
    },
    "colab_type": "code",
    "id": "4xWoKhPY9Of5",
    "outputId": "6250a185-b4dd-4752-fde6-3981d885c00c"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.6/dist-packages/keras/models.py:981: UserWarning: The `nb_epoch` argument in `fit` has been renamed `epochs`.\n",
      "  warnings.warn('The `nb_epoch` argument in `fit` '\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "60000/60000 [==============================] - 16s 269us/step - loss: 0.1555 - acc: 0.9534\n",
      "Epoch 2/10\n",
      "60000/60000 [==============================] - 16s 265us/step - loss: 0.0614 - acc: 0.9816\n",
      "Epoch 3/10\n",
      "60000/60000 [==============================] - 16s 272us/step - loss: 0.0455 - acc: 0.9857\n",
      "Epoch 4/10\n",
      "60000/60000 [==============================] - 16s 273us/step - loss: 0.0381 - acc: 0.9879\n",
      "Epoch 5/10\n",
      "60000/60000 [==============================] - 16s 265us/step - loss: 0.0317 - acc: 0.9902\n",
      "Epoch 6/10\n",
      "60000/60000 [==============================] - 17s 278us/step - loss: 0.0280 - acc: 0.9910\n",
      "Epoch 7/10\n",
      "60000/60000 [==============================] - 16s 264us/step - loss: 0.0246 - acc: 0.9917\n",
      "Epoch 8/10\n",
      "60000/60000 [==============================] - 16s 264us/step - loss: 0.0215 - acc: 0.9931\n",
      "Epoch 9/10\n",
      "60000/60000 [==============================] - 16s 265us/step - loss: 0.0205 - acc: 0.9934\n",
      "Epoch 10/10\n",
      "60000/60000 [==============================] - 16s 264us/step - loss: 0.0188 - acc: 0.9933\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7fe8e4058a20>"
      ]
     },
     "execution_count": 30,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train, Y_train, batch_size=32, nb_epoch=10, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "AtsH-lLk-eLb"
   },
   "outputs": [],
   "source": [
    "score = model.evaluate(X_test, Y_test, verbose=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "mkX8JMv79q9r",
    "outputId": "a9fb4d33-f801-40ad-dbe8-1587abf0a35d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.039399714374169705, 0.9891]\n"
     ]
    }
   ],
   "source": [
    "print(score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "OCWoJkwE9suh"
   },
   "outputs": [],
   "source": [
    "y_pred = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 366
    },
    "colab_type": "code",
    "id": "Ym7iCFBm9uBs",
    "outputId": "d0632d33-66ff-4239-eb92-ccc0a3f35071"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[4.6504911e-06 1.2932352e-07 1.3936580e-04 1.2925369e-04 1.5963042e-08\n",
      "  2.3999789e-07 6.7777056e-12 9.9963379e-01 2.0790834e-07 9.2328257e-05]\n",
      " [1.6721019e-06 1.0428073e-06 9.9999213e-01 9.7466080e-09 5.6080549e-09\n",
      "  1.0589083e-09 5.0131234e-06 8.5470555e-09 1.0857921e-07 3.1700111e-09]\n",
      " [3.5164860e-05 9.8495412e-01 1.3879200e-03 3.8547008e-05 2.3570261e-03\n",
      "  2.0564464e-03 3.4241893e-04 2.5573054e-03 6.1596036e-03 1.1149778e-04]\n",
      " [9.7568262e-01 7.8739092e-08 5.2379171e-04 2.6200039e-06 5.8952564e-06\n",
      "  8.8926872e-06 2.2672631e-02 2.3730800e-05 4.4852699e-05 1.0348457e-03]\n",
      " [5.7802845e-05 8.4486537e-08 1.5275489e-05 4.2371494e-07 9.9511862e-01\n",
      "  3.2505883e-07 7.8070761e-06 1.9489504e-07 8.2068867e-04 3.9789029e-03]\n",
      " [1.9494173e-05 9.8408079e-01 3.8999956e-04 3.5470057e-06 1.7672644e-03\n",
      "  1.4219931e-04 2.9413803e-05 1.0506110e-02 2.9185570e-03 1.4252868e-04]\n",
      " [8.8176177e-09 2.9370529e-05 1.2537763e-03 2.3029065e-07 8.1202602e-01\n",
      "  3.2140056e-04 2.5848408e-07 3.6904054e-05 1.8465950e-01 1.6725609e-03]\n",
      " [4.2081516e-09 5.4273610e-08 1.3427930e-05 1.2760249e-06 8.1414808e-05\n",
      "  6.7895608e-06 3.0855045e-09 1.4213644e-07 1.3023544e-04 9.9976665e-01]\n",
      " [1.9706454e-06 2.7341884e-10 1.2200016e-07 4.8618984e-09 1.2283824e-06\n",
      "  9.4860429e-01 5.0306365e-02 2.0856197e-09 1.0431297e-03 4.2820026e-05]]\n",
      "[7 2 1 0 4 1 4 9 5]\n"
     ]
    }
   ],
   "source": [
    "print(y_pred[:9])\n",
    "print(y_test[:9])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "collapsed": true,
    "id": "CT--y98_dr2T"
   },
   "outputs": [],
   "source": [
    "layer_dict = dict([(layer.name, layer) for layer in model.layers])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 146
    },
    "colab_type": "code",
    "id": "_UM7c5b3NkdT",
    "outputId": "70b80b05-b61b-497b-91d2-a65a82918aa7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'activation_2': <keras.layers.core.Activation at 0x7fe90f6e4fd0>,\n",
       " 'conv2d_5': <keras.layers.convolutional.Conv2D at 0x7fe9128c5ef0>,\n",
       " 'conv2d_6': <keras.layers.convolutional.Conv2D at 0x7fe90f727080>,\n",
       " 'conv2d_7': <keras.layers.convolutional.Conv2D at 0x7fe90f727dd8>,\n",
       " 'dropout_2': <keras.layers.core.Dropout at 0x7fe9128c5b00>,\n",
       " 'flatten_2': <keras.layers.core.Flatten at 0x7fe90f745860>,\n",
       " 'max_pooling2d_2': <keras.layers.pooling.MaxPooling2D at 0x7fe90f787a20>}"
      ]
     },
     "execution_count": 21,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "layer_dict"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "collapsed_sections": [],
   "name": "ASHIS_BATCH_3_ASSIGNMENT4A.ipynb",
   "provenance": [],
   "version": "0.3.2"
  },
  "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}