Image_Classification_Model_V1.1.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Image Classification Model_V2.0.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "shirs6fTNuv3",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "!pip install PyDrive\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pRfW-AK3N5tt",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import os\n",
        "from pydrive.auth import GoogleAuth\n",
        "from pydrive.drive import GoogleDrive\n",
        "from google.colab import auth\n",
        "from oauth2client.client import GoogleCredentials"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Y_6PJpuYN93N",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "auth.authenticate_user()\n",
        "gauth = GoogleAuth()\n",
        "gauth.credentials = GoogleCredentials.get_application_default()\n",
        "drive = GoogleDrive(gauth)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7HvSKA8JN_iq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "download = drive.CreateFile({'id': '1IFUu9rFn2q938Myrgjk_CLEcDkePty5o'})"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FIQo2CfXOJ4_",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "download.GetContentFile('train_LbELtWX.zip.zip')\n",
        "!unzip train_LbELtWX.zip"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_AYBI2pPOOlo",
        "colab_type": "code",
        "outputId": "ece56396-199f-4611-db77-0b3e6dd873e4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "import keras\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Dropout, Flatten\n",
        "from keras.layers import Conv2D, MaxPooling2D\n",
        "from keras.utils import to_categorical\n",
        "from keras.preprocessing import image\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.model_selection import train_test_split\n",
        "from keras.utils import to_categorical\n",
        "from tqdm import tqdm"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "L3MQDxl0Oqn6",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train = pd.read_csv('train.csv')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "20HPQ0W6Os2H",
        "colab_type": "code",
        "outputId": "3db30707-4075-4ea4-de4f-a7cc911dcac4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 87
        }
      },
      "source": [
        "train_image = []\n",
        "for i in tqdm(range(train.shape[0])):\n",
        "    img = image.load_img('train/'+train['id'][i].astype('str')+'.png', target_size=(28,28,1), grayscale=True)\n",
        "    img = image.img_to_array(img)\n",
        "    img = img/255\n",
        "    train_image.append(img)\n",
        "X = np.array(train_image)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "  0%|          | 0/60000 [00:00<?, ?it/s]/usr/local/lib/python3.6/dist-packages/keras_preprocessing/image/utils.py:104: UserWarning: grayscale is deprecated. Please use color_mode = \"grayscale\"\n",
            "  warnings.warn('grayscale is deprecated. Please use '\n",
            "100%|██████████| 60000/60000 [00:21<00:00, 2737.77it/s]\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "abfhpzd8Ovsw",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "y = train['label'].values\n",
        "y = to_categorical(y)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WOOIsXMCqHy9",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42, test_size=0.2)\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4VJyn0V1qJnR",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = Sequential()\n",
        "model.add(Conv2D(32, kernel_size=(3, 3),activation='relu',input_shape=(28,28,1)))\n",
        "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
        "model.add(Dropout(0.25))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(128, activation='relu'))\n",
        "model.add(Dropout(0.5))\n",
        "model.add(Dense(10, activation='softmax'))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TlHi_RxkqMIM",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_0PB4jAjq04f",
        "colab_type": "code",
        "outputId": "5c51867b-20de-4a4f-e92c-d99d00029ce0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 321
        }
      },
      "source": [
        "model.fit(X_train, y_train, epochs = 6, validation_data=(X_test, y_test))"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "W0712 06:14:49.538600 140382674265984 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
            "Instructions for updating:\n",
            "Use tf.where in 2.0, which has the same broadcast rule as np.where\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "Train on 48000 samples, validate on 12000 samples\n",
            "Epoch 1/6\n",
            "48000/48000 [==============================] - 168s 3ms/step - loss: 0.4946 - acc: 0.8248 - val_loss: 0.3117 - val_acc: 0.8862\n",
            "Epoch 2/6\n",
            "48000/48000 [==============================] - 166s 3ms/step - loss: 0.3375 - acc: 0.8793 - val_loss: 0.2639 - val_acc: 0.8994\n",
            "Epoch 3/6\n",
            "48000/48000 [==============================] - 165s 3ms/step - loss: 0.2891 - acc: 0.8955 - val_loss: 0.2496 - val_acc: 0.9069\n",
            "Epoch 4/6\n",
            "48000/48000 [==============================] - 167s 3ms/step - loss: 0.2520 - acc: 0.9078 - val_loss: 0.2288 - val_acc: 0.9165\n",
            "Epoch 5/6\n",
            "48000/48000 [==============================] - 167s 3ms/step - loss: 0.2318 - acc: 0.9140 - val_loss: 0.2201 - val_acc: 0.9185\n",
            "Epoch 6/6\n",
            "48000/48000 [==============================] - 166s 3ms/step - loss: 0.2074 - acc: 0.9233 - val_loss: 0.2163 - val_acc: 0.9204\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7fad1fad1240>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Y64c25dIq7fz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "download = drive.CreateFile({'id': '1R2RZCkzigcV7x_E16oMcEDamOwthvOqJ'})\n",
        "download.GetContentFile('test_ScVgIM0.zip')\n",
        "!unzip test_ScVgIM0.zip"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8HUW5mQpwzdn",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "test = pd.read_csv('test.csv')\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CWsVlMjpw2g_",
        "colab_type": "code",
        "outputId": "1c0964de-3fc4-4db5-e47e-3c2e98c56c46",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 87
        }
      },
      "source": [
        "test_image = []\n",
        "for i in tqdm(range(test.shape[0])):\n",
        "    img = image.load_img('test/'+test['id'][i].astype('str')+'.png', target_size=(28,28,1), grayscale=True)\n",
        "    img = image.img_to_array(img)\n",
        "    img = img/255\n",
        "    test_image.append(img)\n",
        "test = np.array(test_image)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "  0%|          | 0/10000 [00:00<?, ?it/s]/usr/local/lib/python3.6/dist-packages/keras_preprocessing/image/utils.py:104: UserWarning: grayscale is deprecated. Please use color_mode = \"grayscale\"\n",
            "  warnings.warn('grayscale is deprecated. Please use '\n",
            "100%|██████████| 10000/10000 [00:03<00:00, 2792.59it/s]\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RN0JMqmew4Ek",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "prediction = model.predict_classes(test)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "F4ExCVFvw5kC",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "download = drive.CreateFile({'id': '1wDUOXFCJyTcuZitFOxGfOEr1sRiQ0i3g'})\n",
        "download.GetContentFile('sample_submission_I5njJSF.csv')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5555_jpuxZyP",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "sample = pd.read_csv('sample_submission_I5njJSF.csv')\n",
        "sample['label'] = prediction\n",
        "sample.to_csv('sample1.csv', header=True, index=False)"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}