{"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)\nimport io\nimport cv2\nfrom tqdm import tqdm_notebook as tqdm\nimport zipfile\nimport io\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport warnings\nimport keras\nfrom keras import layers\nfrom keras.applications import DenseNet201\nfrom keras.callbacks import Callback, ModelCheckpoint\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.layers import Dense, Dropout, Activation, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom keras.models import Sequential\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix, f1_score, precision_score, recall_score\nimport gc\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nfrom tensorflow import keras\nimport matplotlib.image as mpimg\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Model\nfrom keras.models import clone_model\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization, Input\nfrom keras.optimizers import Adam\nfrom 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\nimport seaborn as sns\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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# let's start to analyse te each gievn csv\ntrain_df=pd.read_csv(\"/kaggle/input/bengaliai-cv19/train.csv\")\n\nclass_map=pd.read_csv(\"/kaggle/input/bengaliai-cv19/class_map.csv\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_map.groupby(\"component_type\")[\"component\"].nunique() # we have this much of image in each class\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_map.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import gc\ngc.collect()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ndata0 = pd.read_feather('/kaggle/input/bengali-preprocessed-dataset/train_data_0.feather')\ndata1 = pd.read_feather('/kaggle/input/bengali-preprocessed-dataset/train_data_1.feather')\ndata2 = pd.read_feather('/kaggle/input/bengali-preprocessed-dataset/train_data_2.feather')\ndata3 = pd.read_feather('/kaggle/input/bengali-preprocessed-dataset/train_data_3.feather')\ndata_full = pd.concat([data0,data1,data2,data3],ignore_index=True)\ndata = pd.merge(data_full, train_df, on='image_id').drop(['image_id'], axis=1).drop(['grapheme'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data0.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# delete all the data variable for memory issue be carefull.\ndel data0,data1,data2,data3,data_full","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 64\nWIDTH = 64\n\nN_CHANNELS=1\n\n# we can do for one class only (vowel_diacritic)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del data[\"grapheme_root\"]\ndel data[\"consonant_diacritic\"]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vowel_target=data[\"vowel_diacritic\"]\ndel data[\"vowel_diacritic\"]\nx_train=data\ndel data","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":"vowel_target=pd.get_dummies(vowel_target).values\ntype(vowel_target)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n    featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import ReduceLROnPlateau\nlearning_rate_reduction_vowel = ReduceLROnPlateau(monitor='loss', \n                                            patience=5, \n                                            verbose=1,\n                                            factor=0.2, \n                                            )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_SIZE=64","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inputs = Input(shape = (IMG_SIZE, IMG_SIZE, 1))\n\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu', input_shape=(IMG_SIZE, IMG_SIZE, 1))(inputs)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=32, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=64, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=128, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=256, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.9)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Flatten()(model)\nmodel = Dense(1024, activation = \"relu\")(model)\nmodel = Dropout(rate=0.3)(model)\ndense = Dense(512, activation = \"relu\")(model)\nhead_vowel = Dense(11, activation = 'softmax')(dense)\nmodel = Model(inputs=inputs, outputs=[head_vowel])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])","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":"x_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.values.reshape(-1,64,64,1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(vowel_target.shape,x_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size=128\nepochs=100\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Fit the model\nhistory = model.fit_generator(datagen.flow(x_train,vowel_target , batch_size=batch_size),\n                          epochs = epochs,\n                          steps_per_epoch=x_train.shape[0] // batch_size, \n                          callbacks=[learning_rate_reduction_vowel])\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%matplotlib inline\ndef plot_loss(his, epoch, title):\n    plt.style.use('ggplot')\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history['loss'], label='train_loss')\n    plt.title(title)\n    plt.xlabel('Epoch #')\n    plt.ylabel('Loss')\n    plt.legend(loc='upper right')\n    plt.show()\n\ndef plot_acc(his, epoch, title):\n    plt.style.use('ggplot')\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history['accuracy'], label='train_vowel_loss')\n    plt.title(title)\n    plt.xlabel('Epoch #')\n    plt.ylabel('Accuracy')\n    plt.legend(loc='upper right')\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_loss(history, epochs, f'Training Loss')\nplot_acc(history, epochs, f'Training Accuracy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save('simple_cnn_vowel_100_epoch.h5')","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":1}