{"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\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","execution":{"iopub.status.busy":"2023-09-20T18:18:00.785005Z","iopub.execute_input":"2023-09-20T18:18:00.785390Z","iopub.status.idle":"2023-09-20T18:18:01.169487Z","shell.execute_reply.started":"2023-09-20T18:18:00.785333Z","shell.execute_reply":"2023-09-20T18:18:01.168414Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Import libraries ","metadata":{}},{"cell_type":"code","source":"\nimport numpy as np \nimport pandas as pd \n\nimport matplotlib.pyplot as plt\n\nimport random\nimport tensorflow as tf\nfrom keras.models import Sequential\nfrom tensorflow.keras import layers\nfrom keras.layers import InputLayer, Dense, Flatten, Lambda\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\nfrom keras.callbacks import EarlyStopping,ModelCheckpoint\nfrom keras.layers import Convolution2D , MaxPooling2D\n","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:34:18.203561Z","iopub.execute_input":"2023-09-20T18:34:18.203958Z","iopub.status.idle":"2023-09-20T18:34:18.210927Z","shell.execute_reply.started":"2023-09-20T18:34:18.203928Z","shell.execute_reply":"2023-09-20T18:34:18.209707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load train and test data","metadata":{}},{"cell_type":"code","source":"\ntrain = pd.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\n\n\ntrain_full_X = (train.iloc[:,1:].values).astype('float32') \ntrain_full_y = train.iloc[:,0].values.astype('int32') \ntest_X = (test.iloc[:,1:].values).astype('float32')\n\n\ntrain_full_X = train_full_X.reshape(train_full_X.shape[0], 28, 28,1)\ntest_X = test_X.reshape(test_X.shape[0], 28, 28,1)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:11.142367Z","iopub.execute_input":"2023-09-20T18:18:11.143568Z","iopub.status.idle":"2023-09-20T18:18:16.992823Z","shell.execute_reply.started":"2023-09-20T18:18:11.143523Z","shell.execute_reply":"2023-09-20T18:18:16.991750Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Display Data","metadata":{}},{"cell_type":"code","source":"# Create a figure with 10 subplots arranged vertically\nfig, axes = plt.subplots(1, 10, figsize=(15, 5))  \nfor i in range(10): \n    axes[i].imshow(train_full_X[i], cmap='gray')  \n    axes[i].set_title(f'Number {i}') \n    axes[i].axis('off')  \nplt.tight_layout()\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:16.997387Z","iopub.execute_input":"2023-09-20T18:18:16.997684Z","iopub.status.idle":"2023-09-20T18:18:17.815173Z","shell.execute_reply.started":"2023-09-20T18:18:16.997659Z","shell.execute_reply":"2023-09-20T18:18:17.814205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create CNN Model","metadata":{}},{"cell_type":"code","source":"\nmodel = Sequential(\n    [\n        InputLayer(input_shape=(28,28,1)),\n        \n     \n        layers.Conv2D(64,6,padding='same',activation='relu',),\n        layers.MaxPool2D(),\n        # layers.Dropout(0.50),\n\n\n        layers.Conv2D(32,3,padding='same',activation='relu',),\n        layers.MaxPool2D(),\n        # layers.Dropout(0.50),\n\n\n        layers.Conv2D(16,3,padding='same',activation='relu',),\n        layers.MaxPool2D(),\n        # layers.Dropout(0.50),\n        layers.Conv2D(8,1,padding='same',activation='relu',),\n        layers.MaxPool2D(),\n        # layers.Dropout(0.50),\n     \n        layers.Flatten(),\n     \n        layers.Dense(200 , activation='relu'),\n        layers.Dense(128 , activation='relu'),\n        layers.Dense(64 , activation='relu'),\n        layers.Dense(32 , activation='relu'),     \n        layers.Dense(16 , activation='relu'),\n        layers.Dense(10 , activation='softmax'),\n    ]\n)\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:17.817011Z","iopub.execute_input":"2023-09-20T18:18:17.817777Z","iopub.status.idle":"2023-09-20T18:18:22.882835Z","shell.execute_reply.started":"2023-09-20T18:18:17.817743Z","shell.execute_reply":"2023-09-20T18:18:22.882024Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Compile the network","metadata":{}},{"cell_type":"code","source":"model.compile(\n    optimizer = 'adam',\n    loss = tf.keras.losses.SparseCategoricalCrossentropy(),\n    metrics = ['accuracy']\n)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:22.884021Z","iopub.execute_input":"2023-09-20T18:18:22.884430Z","iopub.status.idle":"2023-09-20T18:18:22.919505Z","shell.execute_reply.started":"2023-09-20T18:18:22.884393Z","shell.execute_reply":"2023-09-20T18:18:22.918409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Split the data","metadata":{}},{"cell_type":"code","source":"train_X, val_X, train_y, val_y = train_test_split(train_full_X, train_full_y, test_size=0.10, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:22.921092Z","iopub.execute_input":"2023-09-20T18:18:22.921756Z","iopub.status.idle":"2023-09-20T18:18:23.452306Z","shell.execute_reply.started":"2023-09-20T18:18:22.921721Z","shell.execute_reply":"2023-09-20T18:18:23.451234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Create Callbacks","metadata":{}},{"cell_type":"code","source":"es =EarlyStopping(\n    monitor='val_loss',\n    mode='min',\n    verbose=1,\npatience=5,\nrestore_best_weights=True\n)\n\nmc=ModelCheckpoint(\n    'best_weights.h5',\n    monitor='val_accuracy',\n    moed='max',\n    verbose=1,\n    save_best_only=True\n)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:23.454001Z","iopub.execute_input":"2023-09-20T18:18:23.454392Z","iopub.status.idle":"2023-09-20T18:18:23.461531Z","shell.execute_reply.started":"2023-09-20T18:18:23.454357Z","shell.execute_reply":"2023-09-20T18:18:23.460369Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train the model","metadata":{}},{"cell_type":"code","source":"his = model.fit(\n    train_X, train_y,\n    validation_data=(val_X, val_y),\n epochs = 200,\n batch_size = 512,\n    verbose=0,\n    callbacks=[es,mc]\n)\nprint( \"The Accuracy is: \"+str(int((his.history['accuracy'][-1])*100))+'%')","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:18:23.463466Z","iopub.execute_input":"2023-09-20T18:18:23.463809Z","iopub.status.idle":"2023-09-20T18:19:01.977832Z","shell.execute_reply.started":"2023-09-20T18:18:23.463777Z","shell.execute_reply":"2023-09-20T18:19:01.976661Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = model.predict(test_X)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:20:49.308104Z","iopub.execute_input":"2023-09-20T18:20:49.308527Z","iopub.status.idle":"2023-09-20T18:20:50.166761Z","shell.execute_reply.started":"2023-09-20T18:20:49.308494Z","shell.execute_reply":"2023-09-20T18:20:50.165645Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Test the model","metadata":{}},{"cell_type":"code","source":"\nfig, axes = plt.subplots(1, 10, figsize=(15, 5))  \nfor _ in range(10): \n    i = random.randint(0, 4999)\n    axes[_].imshow(test_X[i], cmap='gray')  \n    axes[_].set_title(f'Number {np.argmax(predictions[i])}')  \n    axes[_].axis('off')  \n\nfig.suptitle('Ten Random nums', fontsize=16)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-09-20T18:35:48.332663Z","iopub.execute_input":"2023-09-20T18:35:48.333102Z","iopub.status.idle":"2023-09-20T18:35:49.583011Z","shell.execute_reply.started":"2023-09-20T18:35:48.333064Z","shell.execute_reply":"2023-09-20T18:35:49.582101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"output = pd.DataFrame({'id': test.id, 'label': np.argmax(predictions, axis=1)})\noutput.to_csv('submission.csv', index=False)\nprint(\"submission was successfully saved!\")","metadata":{},"execution_count":null,"outputs":[]}]}