{"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\n#for 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 20GB 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":{"trusted":true},"cell_type":"code","source":"BASE_DIR = \"/kaggle/input/cassava-leaf-disease-classification/\"\nTRAIN_DIR = \"/kaggle/input/cassava-leaf-disease-classification/train_images/\"\nTEST_DIR = \"/kaggle/input/cassava-leaf-disease-classification/test_images/\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nimport matplotlib.pyplot as plt\nimport json\nimport cv2\nfrom PIL import Image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open(os.path.join(BASE_DIR, \"label_num_to_disease_map.json\")) as file:\n    map_classes = json.loads(file.read())\n    \nprint(json.dumps(map_classes, indent=2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_list = [int(key) for key in map_classes.keys()]\nlabel_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_files = os.listdir(os.path.join(BASE_DIR, \"train_images\"))\nprint(f\"Number of train images: {len(input_files)}\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_HEIGHT = 400\nIMG_WIDTH = 400\nbatch_size = 32\nPRE_TRAINED_MODEL = '../input/resnet50v02/Cassava_Best_ResNet50_Model_V02.hdf5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_filenames = os.listdir(TEST_DIR)\ntest_df = pd.DataFrame({\n    'image_id': test_filenames\n})\ntest_samples = test_df.shape[0]\ntest_samples","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nimport tensorflow as tf\n\nkeras.backend.clear_session() # clearing session\nnp.random.seed(42) # generating random see\ntf.random.set_seed(42) # set.seed function helps reuse same set of random variables","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import load_model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = load_model(PRE_TRAINED_MODEL)\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#predict = model.predict(test_gen, steps=np.ceil(test_samples/batch_size))\n#predict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_augmented_images(image_id):\n    image_path = os.path.join(TEST_DIR, image_id)\n    image_data = Image.open(image_path)\n    image_data = image_data.resize((IMG_HEIGHT, IMG_WIDTH), Image.ANTIALIAS)\n    image_data = np.expand_dims(image_data, axis = 0)\n    \n    #print(\"Shape of Image :: {}\".format(image_data.shape))\n    \n    test_datagen = ImageDataGenerator(validation_split = 0.2,\n                                     rotation_range = 45,\n                                     zoom_range = 0.4,\n                                     horizontal_flip = True,\n                                     vertical_flip = True,\n                                     fill_mode = 'nearest',\n                                     shear_range = 0.1,\n                                     height_shift_range = 0.1,\n                                     width_shift_range = 0.1)\n    \n    test_datagen = ImageDataGenerator(rescale=1.0/255, validation_split = 0.2,\n                                     rotation_range = 45,\n                                     zoom_range = 0.4,\n                                     horizontal_flip = True,\n                                     vertical_flip = True,\n                                     fill_mode = 'nearest',\n                                     shear_range = 0.1,\n                                     height_shift_range = 0.1,\n                                     width_shift_range = 0.1,\n                                     featurewise_center = True,\n                                     featurewise_std_normalization = True)\n    \n    test_datagen.fit(image_data)\n    \n    it = test_datagen.flow(image_data, batch_size=1)\n    image_list = []\n    image_list.append(image_data)\n    for i in range(5):\n        batch = it.next()\n        #print(\"Shape of Augmented Image :: {}\".format(batch.shape))\n        image_list.append(batch)\n    \n    #print(\"Number of augmented images :: {}\".format(len(image_list)))\n    return image_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_results_list = []\nfor image_id in test_df[\"image_id\"]:\n    image_list = get_augmented_images(image_id)\n    \n    predict_list = []\n    for image_data in image_list:\n        predict_class_1 = model.predict(image_data)\n        print(\"Probabilities :: {}, :: Predicted Class : {}\".format(predict_class_1[0],np.argmax(predict_class_1[0])))\n        predict_list.append(predict_class_1[0])\n    predict_array = np.array(predict_list)\n    predict_class = np.mean(predict_array, axis=0)\n    print(\"Augmented Probabilities :: {}, :: Augmented Predicted Class : {}\".format(predict_class,np.argmax(predict_class)))\n    test_results_dict = {}\n    test_results_dict[\"image_id\"] = image_id\n    test_results_dict[\"label\"] = np.argmax(predict_class)\n    test_results_list.append(test_results_dict)\n\ntest_results_df = pd.DataFrame(test_results_list)\ntest_results_df.to_csv(\"submission.csv\" ,index = False)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv(\"submission.csv\")\nsubmission.head(3)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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}