{"cells":[{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\nimport os\n\nimport cv2\nfrom PIL import Image\nimport numpy as np\nfrom keras import layers\nfrom keras.applications import DenseNet121\nfrom keras.callbacks import Callback, ModelCheckpoint\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.optimizers import Adam\nimport matplotlib.pyplot as plt\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import cohen_kappa_score, accuracy_score\nimport scipy\nimport tensorflow as tf\nfrom tqdm import tqdm\n\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/aptos2019-blindness-detection/train.csv')\ntest_df = pd.read_csv('../input/aptos2019-blindness-detection/test.csv')\nprint(train_df.shape)\nprint(test_df.shape)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def preprocess_image(image_path, desired_size=224):\n    im = Image.open(image_path)\n    im = im.resize((desired_size, )*2, resample=Image.LANCZOS)\n    \n    return im","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = train_df.shape[0]\nx_train = np.empty((N, 224, 224, 3), dtype=np.uint8)\n\nfor i, image_id in enumerate(tqdm(train_df['id_code'])):\n    x_train[i, :, :, :] = preprocess_image(\n        f'../input/aptos2019-blindness-detection/train_images/{image_id}.png'\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = test_df.shape[0]\nx_test = np.empty((N, 224, 224, 3), dtype=np.uint8)\n\nfor i, image_id in enumerate(tqdm(test_df['id_code'])):\n    x_test[i, :, :, :] = preprocess_image(\n        f'../input/aptos2019-blindness-detection/test_images/{image_id}.png'\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = pd.get_dummies(train_df['diagnosis']).values\n\nprint(x_train.shape)\nprint(y_train.shape)\nprint(x_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train_multi = np.empty(y_train.shape, dtype=y_train.dtype)\ny_train_multi[:, 4] = y_train[:, 4]\n\nfor i in range(3, -1, -1):\n    y_train_multi[:, i] = np.logical_or(y_train[:, i], y_train_multi[:, i+1])\n\nprint(\"Original y_train:\", y_train.sum(axis=0))\nprint(\"Multilabel version:\", y_train_multi.sum(axis=0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, axs = plt.subplots(1,5,figsize=(15, 4),sharey=True)\nfor i,item in enumerate(range(5)):\n    axs[i].imshow(x_train[i])\n    axs[i].set_title(y_train[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train2=[]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# image processing , here we processing the images and we using blending technique \nfor image in x_train:\n    img=cv2.cvtColor(image,cv2.COLOR_BGR2RGB)\n    processed_image=cv2.addWeighted ( img,4, cv2.GaussianBlur( img, (0,0) , 250/10) ,-4 ,128) # blending technique \n    x_train2.append(processed_image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, axs = plt.subplots(1,5,figsize=(15, 4),sharey=True)\nfor i,item in enumerate(range(5)):\n    axs[i].imshow(x_train2[i])\n    axs[i].set_title(y_train[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train2=np.array(x_train2)  # converting into numpy array ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#splitting the data \nX_train, X_val, y_train, y_val = train_test_split(\n    x_train2, y_train_multi, \n    test_size=0.15, \n    random_state=2019\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train2.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train_multi.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#we can also import the resnet \ndensenet = DenseNet121(\n    weights=\"imagenet\",\n    include_top=False,\n    input_shape=(224,224,3)\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model():\n    model = Sequential()\n    model.add(densenet)\n    model.add(layers.GlobalAveragePooling2D())\n    model.add(layers.Dropout(0.5))\n    model.add(layers.Dense(2024,activation=\"relu\"))  # we can increase the layer for higher accuracy \n    model.add(layers.Dropout(0.5))\n    model.add(layers.Dense(5, activation='sigmoid'))\n    \n    model.compile(\n        loss='binary_crossentropy',\n        optimizer=Adam(lr=0.00005),\n        metrics=['accuracy']\n    )\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator    # data augmentation \n\ntrain_datagen = ImageDataGenerator(\n      #rotation_range=30,\n      shear_range=0.1,\n      zoom_range=[0.3,0.5],\n      #width_shift_range=0.4,\n      #height_shift_range=0.4,\n      horizontal_flip=True,\n      vertical_flip=True,\n  \n      fill_mode='nearest')\n\n\ntest_datagen=ImageDataGenerator()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_set=train_datagen.flow(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_set=test_datagen.flow(X_val,y_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history=model.fit_generator(\n         train_set,\n        validation_data=test_set,\n        epochs=5,\n        verbose=1\n     )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save(\"messidor_analyzer.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(X_val,y_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred=model.predict(X_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred=np.sum(pred,axis=1)     # summing the prediction so that we can see the output ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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":4}