{"cells":[{"metadata":{},"cell_type":"markdown","source":"**This kernel implements VGG on APTOS data **"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import cv2\nfrom tqdm import tqdm\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Input\nfrom keras.layers import Conv2D\nfrom keras.layers import Flatten\nfrom keras.layers import Dropout\nfrom keras.utils import plot_model\nfrom keras.models import Sequential\nfrom keras.layers import MaxPooling2D\nfrom keras.utils import to_categorical\nfrom keras.layers import ZeroPadding2D\nfrom keras.layers.merge import concatenate\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import gc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['diagnosis'].hist()\ntrain['diagnosis'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_samples(df, columns=4, rows=3):\n    fig=plt.figure(figsize=(5*columns, 4*rows))\n\n    for i in range(columns*rows):\n        image_path = df.loc[i,'id_code']\n        image_id = df.loc[i,'diagnosis']\n        img = cv2.imread(f'../input/train_images/{image_path}.png')\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)\n        img = cv2.resize(img,(28,28),interpolation=cv2.INTER_CUBIC)\n        \n        fig.add_subplot(rows, columns, i+1)\n        plt.title(image_id)\n        plt.imshow(img)\n    \n    plt.tight_layout()\n\ndisplay_samples(train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = []\npaths = train.id_code\nfor path in paths :\n    img = cv2.imread(f'../input/train_images/{path}.png')\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n    img = cv2.resize(img,(112,112),interpolation=cv2.INTER_CUBIC).tolist()\n    images.append(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(ZeroPadding2D((1,1),input_shape=(112,112,1)))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2,2), strides=(2,2)))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2,2), strides=(2,2)))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(256, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(256, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(256, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2,2), strides=(2,2)))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512,kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2,2), strides=(2,2)))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512, kernel_size=(3, 3), activation='relu'))\nmodel.add(ZeroPadding2D((1,1)))\nmodel.add(Conv2D(512, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2,2), strides=(2,2)))\nmodel.add(Flatten())\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(5, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = np.array(images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainx, testx, trainy, testy = train_test_split(images,train.diagnosis,test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainy= to_categorical(trainy)\ntesty = to_categorical(testy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainx= trainx.reshape(-1, 112, 112,1)\ntestx= testx.reshape(-1, 112, 112,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del images\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(trainx, trainy,\n           epochs=10, batch_size=100, verbose=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(testx, testy,\n            batch_size=100)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}