Keras_CIFAR10.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Keras CIFAR10.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/anupamtamrakar/Machine-learning/blob/master/Keras_CIFAR10.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "metadata": {
        "id": "RjUYvnGQ_z9c",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "from keras.datasets import cifar10\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Activation,Dropout,Conv2D,Flatten,BatchNormalization\n",
        "from keras.utils import to_categorical\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "%matplotlib inline"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "gXz5cbT4__Zf",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "(x_train, y_train), (x_test, y_test) = cifar10.load_data()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "YHsUafC9AM_6",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 92
        },
        "outputId": "2f7e1d78-14a1-443f-eb0b-15bdc822c82e"
      },
      "cell_type": "code",
      "source": [
        "print(\"Shape of x_train: \" + str(x_train.shape))\n",
        "print(\"Shape of x_test: \" + str(x_test.shape))\n",
        "print(\"Shape of y_test: \" + str(y_test.shape))\n",
        "print(\"Shape of y_train: \" + str(y_train.shape))"
      ],
      "execution_count": 103,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shape of x_train: (50000, 32, 32, 3)\n",
            "Shape of x_test: (10000, 32, 32, 3)\n",
            "Shape of y_test: (10000, 1)\n",
            "Shape of y_train: (50000, 1)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "--kN69hhArmZ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#x_train = x_train / 255\n",
        "#x_test = x_test / 255"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Hln7DwGWBgKh",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#x_train = x_train.reshape(50000,3072)\n",
        "#x_test = x_test.reshape(10000,3072)\n",
        "one_hot_labels = to_categorical(y_train, num_classes=10)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "h92XbP_iBiTy",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "model = Sequential()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "ddO6DOyxCZPo",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "model.add(Conv2D(input_shape=x_train[0,:,:,:].shape, filters=96, kernel_size=(3,3)))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Conv2D(filters=96, kernel_size=(3,3), strides=2))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Dropout(0.2))\n",
        "model.add(Conv2D(filters=192, kernel_size=(3,3)))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Conv2D(filters=192, kernel_size=(3,3), strides=2))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Dropout(0.5))\n",
        "model.add(Flatten())\n",
        "model.add(BatchNormalization())\n",
        "model.add(Dense(256))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Dense(10, activation=\"softmax\"))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "RLpt0VbaDOpz",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "model.compile('Adam',loss='categorical_crossentropy',metrics=['accuracy'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "VwKfwZhQDQLo",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 784
        },
        "outputId": "f8358bc2-8452-4c90-d301-9710daa88eb5"
      },
      "cell_type": "code",
      "source": [
        "model.fit(x=x_train,y=one_hot_labels,batch_size=256,epochs=20,shuffle=True)"
      ],
      "execution_count": 109,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/20\n",
            "50000/50000 [==============================] - 22s 438us/step - loss: 1.8443 - acc: 0.3471\n",
            "Epoch 2/20\n",
            "50000/50000 [==============================] - 19s 378us/step - loss: 1.3620 - acc: 0.5077\n",
            "Epoch 3/20\n",
            "50000/50000 [==============================] - 19s 390us/step - loss: 1.1802 - acc: 0.5790\n",
            "Epoch 4/20\n",
            "50000/50000 [==============================] - 20s 394us/step - loss: 1.0340 - acc: 0.6327\n",
            "Epoch 5/20\n",
            "50000/50000 [==============================] - 20s 395us/step - loss: 0.9272 - acc: 0.6733\n",
            "Epoch 6/20\n",
            "50000/50000 [==============================] - 20s 398us/step - loss: 0.8430 - acc: 0.7028\n",
            "Epoch 7/20\n",
            "50000/50000 [==============================] - 20s 407us/step - loss: 0.7707 - acc: 0.7272\n",
            "Epoch 8/20\n",
            "50000/50000 [==============================] - 20s 407us/step - loss: 0.7020 - acc: 0.7528\n",
            "Epoch 9/20\n",
            "50000/50000 [==============================] - 19s 380us/step - loss: 0.6431 - acc: 0.7728\n",
            "Epoch 10/20\n",
            "50000/50000 [==============================] - 19s 374us/step - loss: 0.5883 - acc: 0.7909\n",
            "Epoch 11/20\n",
            "50000/50000 [==============================] - 19s 374us/step - loss: 0.5504 - acc: 0.8049\n",
            "Epoch 12/20\n",
            "50000/50000 [==============================] - 19s 375us/step - loss: 0.5048 - acc: 0.8212\n",
            "Epoch 13/20\n",
            "50000/50000 [==============================] - 19s 374us/step - loss: 0.4698 - acc: 0.8325\n",
            "Epoch 14/20\n",
            "50000/50000 [==============================] - 19s 376us/step - loss: 0.4402 - acc: 0.8444\n",
            "Epoch 15/20\n",
            "50000/50000 [==============================] - 19s 375us/step - loss: 0.4099 - acc: 0.8550\n",
            "Epoch 16/20\n",
            "50000/50000 [==============================] - 19s 375us/step - loss: 0.3847 - acc: 0.8632\n",
            "Epoch 17/20\n",
            "50000/50000 [==============================] - 19s 376us/step - loss: 0.3538 - acc: 0.8728\n",
            "Epoch 18/20\n",
            "50000/50000 [==============================] - 19s 376us/step - loss: 0.3396 - acc: 0.8792\n",
            "Epoch 19/20\n",
            "50000/50000 [==============================] - 19s 373us/step - loss: 0.3192 - acc: 0.8868\n",
            "Epoch 20/20\n",
            "50000/50000 [==============================] - 19s 374us/step - loss: 0.3071 - acc: 0.8924\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f7128b30da0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 109
        }
      ]
    },
    {
      "metadata": {
        "id": "hu1-pSmuLYvZ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "one_hot_labels_test = to_categorical(y_test, num_classes=10)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "HnHwylFOEIRm",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 54
        },
        "outputId": "45754806-8ded-4de0-9ffa-94d75bae561d"
      },
      "cell_type": "code",
      "source": [
        "model.evaluate(x=x_test,y=one_hot_labels_test,batch_size=32,verbose=1)"
      ],
      "execution_count": 111,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "10000/10000 [==============================] - 2s 244us/step\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.7665724459648132, 0.7652]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 111
        }
      ]
    },
    {
      "metadata": {
        "id": "rcOMH9AqHCA7",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "predictions = model.predict(x=x_test,batch_size=32)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "UFagg1pRMZ8U",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "preds = np.argmax(predictions,axis=1)\n",
        "corr = preds == y_test"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "3788UvTbMbZ4",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "outputId": "b8f116c0-83fb-44d7-d1c5-0ae869f7c5b3"
      },
      "cell_type": "code",
      "source": [
        "index = 9\n",
        "plt.imshow(x_test[index])\n",
        "print(\"Acutual: {}, Prediction: {}\".format(y_test[index],preds[index]))"
      ],
      "execution_count": 119,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Acutual: [1], Prediction: 9\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "metadata": {
        "id": "mVQyfhCONWVx",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1374
        },
        "outputId": "941bf83c-2f5a-4303-a916-ee82f4bb51e4"
      },
      "cell_type": "code",
      "source": [
        "print(\"Correct Predictions\")\n",
        "count = 0;\n",
        "for i in range(len(x_test)):\n",
        "  if(preds[i]==y_test[i]):\n",
        "    plt.imshow(x_test[i])\n",
        "    count +=1\n",
        "    print(\"Acutual: {}, Prediction: {}\".format(y_test[i],preds[i]))\n",
        "    plt.show()"
      ],
      "execution_count": 122,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Correct Predictions\n",
            "Acutual: [3], Prediction: 3\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nuqLEADV0RYkB/w8OoEb2ZrT8nQAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Acutual: [8], Prediction: 8\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Acutual: [8], Prediction: 8\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Acutual: [0], Prediction: 0\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\noIquKBlAFV1RMoAquqJkAFV0RckA/x831qducSLongAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Acutual: [6], Prediction: 6\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPoAAAD5CAYAAAAOeCiTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "metadata": {
        "id": "8m7SaCMIOkor",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 709
        },
        "outputId": "0467e35e-904e-4b26-ad1d-7dd553ae426d"
      },
      "cell_type": "code",
      "source": [
        "model.summary()"
      ],
      "execution_count": 118,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv2d_2 (Conv2D)            (None, 30, 30, 96)        2688      \n",
            "_________________________________________________________________\n",
            "activation_1 (Activation)    (None, 30, 30, 96)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_3 (Conv2D)            (None, 14, 14, 96)        83040     \n",
            "_________________________________________________________________\n",
            "activation_2 (Activation)    (None, 14, 14, 96)        0         \n",
            "_________________________________________________________________\n",
            "dropout_2 (Dropout)          (None, 14, 14, 96)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_4 (Conv2D)            (None, 12, 12, 192)       166080    \n",
            "_________________________________________________________________\n",
            "activation_3 (Activation)    (None, 12, 12, 192)       0         \n",
            "_________________________________________________________________\n",
            "conv2d_5 (Conv2D)            (None, 5, 5, 192)         331968    \n",
            "_________________________________________________________________\n",
            "activation_4 (Activation)    (None, 5, 5, 192)         0         \n",
            "_________________________________________________________________\n",
            "dropout_3 (Dropout)          (None, 5, 5, 192)         0         \n",
            "_________________________________________________________________\n",
            "flatten_1 (Flatten)          (None, 4800)              0         \n",
            "_________________________________________________________________\n",
            "batch_normalization_1 (Batch (None, 4800)              19200     \n",
            "_________________________________________________________________\n",
            "dense_42 (Dense)             (None, 256)               1229056   \n",
            "_________________________________________________________________\n",
            "activation_5 (Activation)    (None, 256)               0         \n",
            "_________________________________________________________________\n",
            "dense_43 (Dense)             (None, 10)                2570      \n",
            "=================================================================\n",
            "Total params: 1,834,602\n",
            "Trainable params: 1,825,002\n",
            "Non-trainable params: 9,600\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "SaC8Ep6FSMqc",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}