{"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom glob import glob\nimport time, gc\nimport datetime\nimport cv2\nimport matplotlib.image as mpimg\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.models import clone_model\nfrom tensorflow.keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization, Input\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport PIL.Image as Image, PIL.ImageDraw as ImageDraw, PIL.ImageFont as ImageFont\nfrom matplotlib import pyplot as plt\nfrom tensorflow.keras.utils import plot_model\nimport seaborn as sns\nfrom tensorflow.python.keras.layers.core import Reshape,Dense,Dropout,Activation,Flatten\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.\nIMG_SIZE=64\nN_CHANNELS=1\nHEIGHT = 137\nWIDTH = 236\nSIZE = 64\nCROP_SIZE = 64\n\ndef resize(df, size=64):\n    resized = {}\n    resize_size=64    \n    for i in range(df.shape[0]):\n        image=df.loc[df.index[i]].values.reshape(137,236)\n        _, thresh = cv2.threshold(image, 30, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)\n        contours, _ = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)[-2:]\n        idx = 0 \n        ls_xmin = []\n        ls_ymin = []\n        ls_xmax = []\n        ls_ymax = []\n        for cnt in contours:\n            idx += 1\n            x,y,w,h = cv2.boundingRect(cnt)\n            ls_xmin.append(x)\n            ls_ymin.append(y)\n            ls_xmax.append(x + w)\n            ls_ymax.append(y + h)\n        xmin = min(ls_xmin)\n        ymin = min(ls_ymin)\n        xmax = max(ls_xmax)\n        ymax = max(ls_ymax)\n\n        roi = image[ymin:ymax,xmin:xmax]\n        resized_roi = cv2.resize(roi, (resize_size, resize_size),interpolation=cv2.INTER_AREA)\n        resized[df.index[i]] = resized_roi.reshape(-1)\n    resized = pd.DataFrame(resized).T\n    return resized\n\ndef get_dummies(df):\n    cols = []\n    for col in df:\n        cols.append(pd.get_dummies(df[col].astype(str)))\n    return pd.concat(cols, axis=1)\n\nmodel = tf.keras.models.load_model('/kaggle/input/resnetfinal/resnet_final.h5')\nmodel.load_weights('/kaggle/input/resnetfinal/resnet_final.h5')\npreds_dict = {\n    'grapheme_root': [],\n    'vowel_diacritic': [],\n    'consonant_diacritic': []\n}\ncomponents = ['consonant_diacritic', 'grapheme_root', 'vowel_diacritic']\ntarget=[] # model predictions placeholder\nrow_id=[] # row_id place holder\nfor i in range(4):\n    df_test_img = pd.read_parquet('/kaggle/input/bengaliai-cv19/test_image_data_{}.parquet'.format(i)) \n    df_test_img.set_index('image_id', inplace=True)\n\n    X_test = resize(df_test_img)/255\n    X_test = X_test.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\n    \n    preds = model.predict(X_test)\n\n    for i, p in enumerate(preds_dict):\n        preds_dict[p] = np.argmax(preds[i], axis=1)\n\n    for k,id in enumerate(df_test_img.index.values):  \n        for i,comp in enumerate(components):\n            id_sample=id+'_'+comp\n            row_id.append(id_sample)\n            target.append(preds_dict[comp][k])\n    del df_test_img\n    del X_test\n    gc.collect()\n\ndf_sample = pd.DataFrame(\n    {\n        'row_id': row_id,\n        'target':target\n    },\n    columns = ['row_id','target'] \n)\ndf_sample.to_csv('submission.csv',index=False)\n        ","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}