{"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_minor":4,"nbformat":4,"cells":[{"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        pass\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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nprint(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2\nimport re\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.preprocessing.image import img_to_array, load_img\nfrom tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions, ResNet50\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D\nfrom tensorflow.keras.layers import Dropout, Flatten, Dense, Activation\nfrom tensorflow.keras.models import Sequential \nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras import optimizers\nfrom tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.applications.vgg19 import VGG19\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras import backend as K\nimport pandas as pd\nimport numpy as np\nimport os\nimport tensorflow as tf\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sam_sub = pd.read_csv('/kaggle/input/plant-pathology-2021-fgvc8/sample_submission.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sam_sub","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir = '/kaggle/input/plant-pathology-2021-fgvc8/train_images'\ntest_dir = '/kaggle/input/plant-pathology-2021-fgvc8/test_images'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/plant-pathology-2021-fgvc8/train.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# traincom= train.join(pd.get_dummies(train.labels))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# traindum = traincom.drop('labels', axis = 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# traindum","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#get ids in order in the directory\n#get train file paths\ntest_filepaths = []\n\ntest_ids = []\n\nfor dirname, _, filenames in os.walk(test_dir):\n    for filename in filenames:\n        test_ids.append(filename)\n        test_filepaths.append(os.path.join(dirname, filename))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df = pd.DataFrame(test_ids,columns = ['image'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_datagen_sub = ImageDataGenerator(\n    rotation_range=20,\n    width_shift_range=0.1,\n    height_shift_range=0.1,\n    horizontal_flip=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_generator_sub = train_datagen_sub.flow_from_dataframe(\n        train,\n        directory = train_dir,\n        x_col = 'image',\n        y_col = 'labels',\n        target_size = (432, 648),\n        batch_size = 16,\n    \n        class_mode = 'categorical')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_datagen = ImageDataGenerator()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_generator = test_datagen.flow_from_dataframe(\n    dataframe=test_df,\n    directory=test_dir,\n    x_col=\"image\",\n    target_size=(432, 648),\n    batch_size=1,\n    class_mode=None,\n    shuffle=False,\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# trained_model_sub = tf.keras.models.load_model('../input/pp21model/pp21_sub')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\ndef recall_m(y_true, y_pred):\n    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))\n    recall = true_positives / (possible_positives + K.epsilon())\n    return recall\n\ndef precision_m(y_true, y_pred):\n    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))\n    precision = true_positives / (predicted_positives + K.epsilon())\n    return precision\n\ndef f1_m(y_true, y_pred):\n    precision = precision_m(y_true, y_pred)\n    recall = recall_m(y_true, y_pred)\n    return 2*((precision*recall)/(precision+recall+K.epsilon()))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#trained_model_sub = tf.keras.models.load_model('../input/effnet/pp21_effnet_subh')\n#trained_model_sub = tf.keras.models.load_model('../input/effnet2/pp21_top_fit_sub_effnet2')\n#trained_model_sub = tf.keras.models.load_model('../input/effnet5/pp21_effnet_sub5')\ntrained_model_sub = tf.keras.models.load_model('../input/effnettop/pp21_top_fit_effnet10',custom_objects = {'f1_m':f1_m})","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = trained_model_sub.predict(test_generator)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred_idxs = [np.argmax(i) for i in y_pred]\n# y_pred_idxs","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predicted_class_indices = np.argmax(y_pred, axis = 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = train_generator_sub.class_indices\nlabels = dict((v,k) for k,v in labels.items())\npredictions = [labels[k] for k in predicted_class_indices]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.DataFrame({'image': test_ids, 'labels': predictions})","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred_max = y_pred.copy()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# for i in range(len(y_pred_idxs)):\n#     y_pred_max[i][y_pred_idxs[i]] = 1\n#     for j in range(12):\n#         if y_pred_max[i][j] != 1:\n#             y_pred_max[i][j] = 0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred_df_max = pd.DataFrame(y_pred_max, index = test_ids, columns=traindum.set_index('image').columns, dtype='int64')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred_df_max","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sub_df = pd.DataFrame(y_pred_df_max.idxmax(1)).reset_index()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sub_df.columns = ['image', 'labels']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sub_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sub_df.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}