{"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":"2021-12-06T11:46:03.635149Z","iopub.execute_input":"2021-12-06T11:46:03.636032Z","iopub.status.idle":"2021-12-06T11:46:03.678640Z","shell.execute_reply.started":"2021-12-06T11:46:03.635781Z","shell.execute_reply":"2021-12-06T11:46:03.677628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"raw","source":"\n%config Completer.use_jedi = False # for help during caling libraries and paramenters\n\n","metadata":{}},{"cell_type":"code","source":"# importing data sets and other libraries\nfrom keras.datasets import cifar10\nfrom keras import models\nfrom keras import layers\nfrom keras import Sequential\n","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:03.682099Z","iopub.execute_input":"2021-12-06T11:46:03.682377Z","iopub.status.idle":"2021-12-06T11:46:09.163203Z","shell.execute_reply.started":"2021-12-06T11:46:03.682351Z","shell.execute_reply":"2021-12-06T11:46:09.162162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# global parameters'\nepochs=10\n","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:09.164712Z","iopub.execute_input":"2021-12-06T11:46:09.165058Z","iopub.status.idle":"2021-12-06T11:46:09.170086Z","shell.execute_reply.started":"2021-12-06T11:46:09.165015Z","shell.execute_reply":"2021-12-06T11:46:09.168957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"(x_train, y_train), (x_test, y_test) = cifar10.load_data()","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:09.174338Z","iopub.execute_input":"2021-12-06T11:46:09.175109Z","iopub.status.idle":"2021-12-06T11:46:17.800247Z","shell.execute_reply.started":"2021-12-06T11:46:09.175062Z","shell.execute_reply":"2021-12-06T11:46:17.798944Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# merging the training and test sets so that we can apply cross validation\nX_combined = np.r_[x_train, x_test]\ny_combined = np.r_[y_train, y_test]","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:17.802046Z","iopub.execute_input":"2021-12-06T11:46:17.802548Z","iopub.status.idle":"2021-12-06T11:46:17.906486Z","shell.execute_reply.started":"2021-12-06T11:46:17.802502Z","shell.execute_reply":"2021-12-06T11:46:17.904319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.layers import Dense, Dropout, Activation, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:17.912784Z","iopub.execute_input":"2021-12-06T11:46:17.915776Z","iopub.status.idle":"2021-12-06T11:46:17.923268Z","shell.execute_reply.started":"2021-12-06T11:46:17.915731Z","shell.execute_reply":"2021-12-06T11:46:17.921547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# norimalising the data \nX_combined = X_combined.astype('float32')\ny_combined = y_combined.astype('float32')\nX_combined /= 255\ny_combined /= 255","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:17.928679Z","iopub.execute_input":"2021-12-06T11:46:17.930345Z","iopub.status.idle":"2021-12-06T11:46:18.362162Z","shell.execute_reply.started":"2021-12-06T11:46:17.929821Z","shell.execute_reply":"2021-12-06T11:46:18.360972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def build_model():\n    model=Sequential()\n    model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))\n    model.add(Activation('relu'))\n    model.add(Conv2D(32, (3, 3)))\n    model.add(Activation('relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(layers.Flatten())\n    model.add(layers.Dense(512, activation='relu'))\n    model.add(layers.Dense(1, activation='sigmoid'))\n    model.add(Dropout(0.25))\n    model.compile(optimizer='rmsprop', loss='mse', metrics=['accuracy'])\n    return model\n    \n    \n    ","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:18.368326Z","iopub.execute_input":"2021-12-06T11:46:18.368801Z","iopub.status.idle":"2021-12-06T11:46:18.385147Z","shell.execute_reply.started":"2021-12-06T11:46:18.368759Z","shell.execute_reply":"2021-12-06T11:46:18.383532Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''model.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\n'''","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:18.390496Z","iopub.execute_input":"2021-12-06T11:46:18.391172Z","iopub.status.idle":"2021-12-06T11:46:18.412710Z","shell.execute_reply.started":"2021-12-06T11:46:18.390872Z","shell.execute_reply":"2021-12-06T11:46:18.411357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''\nmodel=Sequential()\n# CONV => RELU => CONV => RELU => POOL => DROPOUT\nmodel.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))\nmodel.add(Activation('relu'))\nmodel.add(Conv2D(32, (3, 3)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\n# CONV => RELU => CONV => RELU => POOL => DROPOUT\nmodel.add(Conv2D(64, (3, 3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(Conv2D(64, (3, 3)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\n# FLATTERN => DENSE => RELU => DROPOUT\nmodel.add(Flatten())\nmodel.add(Dense(512))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\n# a softmax classifier\nmodel.add(Dense(10))\nmodel.add(Activation('softmax'))\n'''","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:18.416803Z","iopub.execute_input":"2021-12-06T11:46:18.417524Z","iopub.status.idle":"2021-12-06T11:46:18.427940Z","shell.execute_reply.started":"2021-12-06T11:46:18.417480Z","shell.execute_reply":"2021-12-06T11:46:18.425966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# k fold cross validation \nfrom sklearn.model_selection import KFold\nkfold=KFold(n_splits=10,random_state=12,shuffle=True)\nscores=[]\n\n    \n    ","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:18.430111Z","iopub.execute_input":"2021-12-06T11:46:18.431389Z","iopub.status.idle":"2021-12-06T11:46:19.117228Z","shell.execute_reply.started":"2021-12-06T11:46:18.431328Z","shell.execute_reply":"2021-12-06T11:46:19.116211Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# one hot encoding of the lablels\nfrom tensorflow.keras.utils import to_categorical\n\ny_combined = to_categorical(y_combined, 10)","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.118765Z","iopub.execute_input":"2021-12-06T11:46:19.120135Z","iopub.status.idle":"2021-12-06T11:46:19.491649Z","shell.execute_reply.started":"2021-12-06T11:46:19.120100Z","shell.execute_reply":"2021-12-06T11:46:19.490658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"###model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.493966Z","iopub.execute_input":"2021-12-06T11:46:19.494433Z","iopub.status.idle":"2021-12-06T11:46:19.501186Z","shell.execute_reply.started":"2021-12-06T11:46:19.494392Z","shell.execute_reply":"2021-12-06T11:46:19.499531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''for train ,test in kfold.split(X_combined,y_combined):\n    \n    model=build_model()\n    # Fit the model\n    model.fit(X_combined[train], y_combined[train], epochs=25, batch_size=10, verbose=2)\n    # evaluate the model\n    scores = model.evaluate(X_combined[test], y_combined[test], verbose=2)\n    print(\"%s: %.2f%%\" % (model.metrics_names[1], scores[1]*100))\n    cv_scores.append(scores[1] * 100)\n    '''","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.503006Z","iopub.execute_input":"2021-12-06T11:46:19.503296Z","iopub.status.idle":"2021-12-06T11:46:19.520520Z","shell.execute_reply.started":"2021-12-06T11:46:19.503269Z","shell.execute_reply":"2021-12-06T11:46:19.519219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test \n# manual k fold using fc \nk=10\nvalidation_samples=int(len(X_combined)/k)\n\nvalidation_scores=[]\nnumber_of_epochs=20\n\n\n","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.522533Z","iopub.execute_input":"2021-12-06T11:46:19.523245Z","iopub.status.idle":"2021-12-06T11:46:19.531525Z","shell.execute_reply.started":"2021-12-06T11:46:19.523109Z","shell.execute_reply":"2021-12-06T11:46:19.529922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_samples","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.532594Z","iopub.execute_input":"2021-12-06T11:46:19.532846Z","iopub.status.idle":"2021-12-06T11:46:19.543562Z","shell.execute_reply.started":"2021-12-06T11:46:19.532817Z","shell.execute_reply":"2021-12-06T11:46:19.542354Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in range(k):\n    print('processing fold #', i)\n    x_test= X_combined[i * validation_samples: (i + 1) * validation_samples]\n    y_test = y_combined[i * validation_samples: (i + 1) * validation_samples]\n    x_train = np.concatenate([X_combined[:i * validation_samples],X_combined[(i + 1) * validation_samples:]],axis=0)\n    y_train = np.concatenate([y_combined[:i * validation_samples],y_combined[(i + 1) * validation_samples:]],axis=0)\n    model = build_model()\n    model.fit(x_train, y_train,epochs=2, batch_size=1, verbose=2)\n    val_mse, val_mae = model.evaluate(x_test, y_test, verbose=2)\n    validation_scores.append(val_mae)","metadata":{"execution":{"iopub.status.busy":"2021-12-06T11:46:19.545669Z","iopub.execute_input":"2021-12-06T11:46:19.546095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}