{"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"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":4104,"databundleVersionId":46661,"sourceType":"competition"}],"dockerImageVersionId":25160,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"#Import important libraries\nfrom PIL import Image\nfrom keras.preprocessing import image\nimport os\nimport numpy as np\nimport pandas as pd\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))","metadata":{"execution":{"iopub.status.busy":"2022-01-02T05:31:18.649656Z","iopub.execute_input":"2022-01-02T05:31:18.650071Z","iopub.status.idle":"2022-01-02T05:31:19.543723Z","shell.execute_reply.started":"2022-01-02T05:31:18.650005Z","shell.execute_reply":"2022-01-02T05:31:19.542417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"trainLabels = pd.read_csv(\"../input/diabetic-retinopathy-detection/trainLabels.csv.zip\")\ntrainLabels.head()","metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.status.busy":"2022-01-02T05:32:02.98099Z","iopub.execute_input":"2022-01-02T05:32:02.981315Z","iopub.status.idle":"2022-01-02T05:32:03.037965Z","shell.execute_reply.started":"2022-01-02T05:32:02.981272Z","shell.execute_reply":"2022-01-02T05:32:03.036817Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"listing = os.listdir(\"../input\") \nlisting.remove(\"trainLabels.csv\")\nnp.size(listing)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# input image dimensions\nimg_rows, img_cols = 200, 200\n\nimmatrix = []\nimlabel = []\n\nfor file in listing:\n    base = os.path.basename(\"../input/\" + file)\n    fileName = os.path.splitext(base)[0]\n    imlabel.append(trainLabels.loc[trainLabels.image==fileName, 'level'].values[0])\n    im = Image.open(\"../input/\" + file)   \n    img = im.resize((img_rows,img_cols))\n    gray = img.convert('L')\n    immatrix.append(np.array(gray).flatten())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"immatrix = np.asarray(immatrix)\nimlabel = np.asarray(imlabel)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.utils import shuffle\ndata,Label = shuffle(immatrix,imlabel, random_state=2)\ntrain_data = [data,Label]\ntype(train_data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport matplotlib\n\nimg=immatrix[167].reshape(img_rows,img_cols)\nplt.imshow(img)\nplt.imshow(img,cmap='gray')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#batch_size to train\nbatch_size = 32\n# number of output classes\nnb_classes = 5\n# number of epochs to train\nnb_epoch = 5\n# number of convolutional filters to use\nnb_filters = 32\n# size of pooling area for max pooling\nnb_pool = 2\n# convolution kernel size\nnb_conv = 3\n(X, y) = (train_data[0],train_data[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\n# STEP 1: split X and y into training and testing sets\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4)\n\nprint(X_train.shape)\nprint(X_test.shape)\n\n#X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)\n#X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)\n\nX_train = X_train.reshape(X_train.shape[0], img_cols, img_rows, 1)\nX_test = X_test.reshape(X_test.shape[0], img_cols, img_rows, 1)\n\nX_train = X_train.astype('float32')\nX_test = X_test.astype('float32')\n\nX_train /= 255\nX_test /= 255\n\nprint('X_train shape:', X_train.shape)\nprint(X_train.shape[0], 'train samples')\nprint(X_test.shape[0], 'test samples')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.utils import np_utils\n\n# convert class vectors to binary class matrices\nY_train = np_utils.to_categorical(y_train, nb_classes)\nY_test = np_utils.to_categorical(y_test, nb_classes)\n\ni = 100\nplt.imshow(X_train[i, 0], interpolation='nearest')\nprint(\"label : \", Y_train[i,:])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers.core import Dense, Dropout, Activation, Flatten\nfrom keras.layers.convolutional import Convolution2D, MaxPooling2D\nfrom keras.optimizers import SGD,RMSprop,adam\n\nmodel = Sequential()\nmodel.add(Convolution2D(nb_filters, nb_conv, nb_conv,\n                        border_mode='valid',\n                        input_shape=(img_cols, img_rows, 1)))\nconvout1 = Activation('relu')\nmodel.add(convout1)\nmodel.add(Convolution2D(nb_filters, nb_conv, nb_conv))\nconvout2 = Activation('relu')\nmodel.add(convout2)\nmodel.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))\nmodel.add(Dropout(0.5))\nmodel.add(Flatten())\nmodel.add(Dense(128))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(nb_classes))\nmodel.add(Activation('softmax'))\nmodel.compile(loss='categorical_crossentropy', optimizer='adadelta')\n\nfrom keras.models import Sequential\nfrom keras.layers.core import Dense, Dropout, Activation, Flatten\nfrom keras.layers.convolutional import Convolution2D, MaxPooling2D\nfrom keras.optimizers import SGD,RMSprop,adam\n\nmodel = Sequential()\nmodel.add(Convolution2D(nb_filters, nb_conv, nb_conv,\n                        border_mode='valid',\n                        input_shape=(img_cols, img_rows, 1)))\nconvout1 = Activation('relu')\nmodel.add(convout1)\nmodel.add(Convolution2D(nb_filters, nb_conv, nb_conv))\nconvout2 = Activation('relu')\nmodel.add(convout2)\nmodel.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))\nmodel.add(Dropout(0.5))\nmodel.add(Flatten())\nmodel.add(Dense(128))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(nb_classes))\nmodel.add(Activation('softmax'))\nmodel.compile(loss='categorical_crossentropy', optimizer='adadelta')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(model.summary())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\n# create generators  - training data will be augmented images\nvalidationdatagenerator = ImageDataGenerator()\ntraindatagenerator = ImageDataGenerator(width_shift_range=0.1,height_shift_range=0.1,rotation_range=15,zoom_range=0.1 )\n\nbatchsize=8\ntrain_generator=traindatagenerator.flow(X_train, Y_train, batch_size=batchsize) \nvalidation_generator=validationdatagenerator.flow(X_test, Y_test,batch_size=batchsize)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit_generator(train_generator, steps_per_epoch=int(len(X_train)/batchsize), epochs=3, validation_data=validation_generator, validation_steps=int(len(X_test)/batchsize))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"scores = model.evaluate(X_test, Y_test)\nprint(scores)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}