{"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 sklearn.model_selection import train_test_split\nimport tensorflow.keras\nfrom tensorflow.keras.preprocessing.image import img_to_array\nimport cv2\nimport tensorflow\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D \nfrom tensorflow.keras.layers import MaxPooling2D \nfrom tensorflow.keras.layers import Activation \nfrom tensorflow.keras.layers import Flatten \nfrom tensorflow.keras.layers import Dense \nfrom tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.layers import Dropout\nfrom tensorflow.keras.layers import Input\nfrom tensorflow.keras import backend as K\nfrom tensorflow.keras.optimizers import SGD\nfrom tensorflow.keras.optimizers import Adam\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.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_ = pd.read_csv('/kaggle/input/bengaliai-cv19/train.csv')\ntest_df_ = pd.read_csv('/kaggle/input/bengaliai-cv19/test.csv')\nclass_map_df = pd.read_csv('/kaggle/input/bengaliai-cv19/class_map.csv')\nsample_sub_df = pd.read_csv('/kaggle/input/bengaliai-cv19/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_ = train_df_.drop(['grapheme'], axis=1, inplace=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']] = train_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']].astype('uint8')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"width=64\nheight=64\ndepth=1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(4):\n    train_df = pd.merge(pd.read_parquet(f'/kaggle/input/bengaliai-cv19/train_image_data_{i}.parquet'), train_df_, on='image_id').drop(['image_id'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train_df.drop(['grapheme_root', 'vowel_diacritic', 'consonant_diacritic'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train_root = pd.get_dummies(train_df['grapheme_root']).values\nY_train_vowel = pd.get_dummies(train_df['vowel_diacritic']).values\nY_train_consonant = pd.get_dummies(train_df['consonant_diacritic']).values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f'Training images: {X.shape}')\nprint(f'Training labels root: {Y_train_root.shape}')\nprint(f'Training labels vowel: {Y_train_vowel.shape}')\nprint(f'Training labels consonants: {Y_train_consonant.shape}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.iloc[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def preprocess(image):\n    image = cv2.resize(image,(width,height),interpolation=cv2.INTER_AREA)\n    return img_to_array(image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data=[]\nfor i in range(X.shape[0]):\n    preprocess_image = preprocess(X.iloc[i].values) \n    data.append(preprocess_image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del X\ndel train_df\ndel train_df_","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = np.array(data).astype(\"float\") / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train_root, y_test_root, y_train_vowel, y_test_vowel, y_train_consonant, y_test_consonant = train_test_split(data, Y_train_root, Y_train_vowel, Y_train_consonant, test_size=0.1)","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":"#del data\ndel Y_train_root, Y_train_vowel, Y_train_consonant","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_category(inputs, numCategories,catname, finalAct=\"softmax\", chanDim=-1):\n\n    #CONV => RELU => POOL\n    x = Conv2D(32, (3, 3), padding=\"same\")(inputs)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization(axis=chanDim)(x)\n    x = MaxPooling2D(pool_size=(3, 3))(x)\n    x = Dropout(0.25)(x)\n    x = Conv2D(64, (3, 3), padding=\"same\")(x)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization(axis=chanDim)(x)\n    x = Conv2D(64, (3, 3), padding=\"same\")(x)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization(axis=chanDim)(x)\n    x = MaxPooling2D(pool_size=(2, 2))(x)\n    x = Dropout(0.25)(x)\n    x = Conv2D(128, (3, 3), padding=\"same\")(x)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization(axis=chanDim)(x)\n    x = Conv2D(128, (3, 3), padding=\"same\")(x)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization(axis=chanDim)(x)\n    x = MaxPooling2D(pool_size=(2, 2))(x)\n    x = Dropout(0.25)(x)\n    x = Flatten()(x)\n    x = Dense(256)(x)\n    x = Activation(\"relu\")(x)\n    x = BatchNormalization()(x)\n    x = Dropout(0.5)(x)\n    x = Dense(numCategories)(x)\n    x = Activation(finalAct, name=catname)(x)\n    # return the category prediction sub-network\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inputShape = (height, width, 1)\ninputs=Input(shape=inputShape)\nroot = build_category(inputs,168,'cat_root')\nvowel = build_category(inputs,11,'cat_vowel')\nconsonant = build_category(inputs,7,'cat_consonant')\n\nmodel=Model(inputs=inputs, outputs=[root,vowel,consonant],name=\"bengaliai\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"INIT_LR=0.1\nEPOCHS=40\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"losses = {\"cat_root\": \"categorical_crossentropy\",\"cat_vowel\": \"categorical_crossentropy\",\"cat_consonant\": \"categorical_crossentropy\"}\nlossWeights = {\"cat_root\": 1.0, \"cat_vowel\": 1.0, \"cat_consonant\":1.0}\n\nopt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)\nmodel.compile(optimizer=opt, loss=losses, loss_weights=lossWeights,metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"H=model.fit(x_train, {\"cat_root\":y_train_root,\"cat_vowel\":y_train_vowel, \"cat_consonant\":y_train_consonant}, \n           validation_data=(x_test,{\"cat_root\":y_test_root,\"cat_vowel\":y_test_vowel, \"cat_consonant\":y_test_consonant}),\n           epochs=EPOCHS,\n           verbose=1)","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}