{"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":"import sys\nimport keras\nimport keras as ks\nimport matplotlib\nfrom matplotlib import pyplot\nfrom keras.datasets import cifar10\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dropout\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import Adam","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:44:53.355083Z","iopub.execute_input":"2022-02-13T20:44:53.355431Z","iopub.status.idle":"2022-02-13T20:44:53.362234Z","shell.execute_reply.started":"2022-02-13T20:44:53.355399Z","shell.execute_reply":"2022-02-13T20:44:53.361256Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Loading the Dataset","metadata":{}},{"cell_type":"code","source":"(X_train,Y_train),(X_test,Y_test) = cifar10.load_data()\n\n# Ananlyzing the shape of the data(Should be the first step of training)\nprint(\"shape of X_train and Y_train \"+ str(X_train.shape)+\" \"+str(Y_train.shape))\nprint(\"shape of X_test and Y_test \"+ str(X_test.shape)+\" \"+str(Y_test.shape))","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:44:53.369084Z","iopub.execute_input":"2022-02-13T20:44:53.369689Z","iopub.status.idle":"2022-02-13T20:45:07.651611Z","shell.execute_reply.started":"2022-02-13T20:44:53.369653Z","shell.execute_reply":"2022-02-13T20:45:07.650673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Looking at the first 5 images and their classes","metadata":{}},{"cell_type":"code","source":"for i in range(5):\n pyplot.subplot(330 + 1 + i)\n pyplot.imshow(X_train[i])\n print(Y_train[i])\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:07.653709Z","iopub.execute_input":"2022-02-13T20:45:07.654062Z","iopub.status.idle":"2022-02-13T20:45:08.368985Z","shell.execute_reply.started":"2022-02-13T20:45:07.654029Z","shell.execute_reply":"2022-02-13T20:45:08.367688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Function 1 : load() --> X_train,Y_train,X_test,Y_test\n### As this is Categorical Data, we use one_hot_encoding on it\nThis creates multiple columns of different categories (As this data is in 0-9 form). So, this is performed on Y_test and Y_train.
This is done using to_categorical of keras.utils
So, finally load function to load and encode data","metadata":{}},{"cell_type":"code","source":"def load():\n (X_train,Y_train),(X_test,Y_test) = cifar10.load_data()\n Y_train=ks.utils.to_categorical(Y_train)\n Y_test=ks.utils.to_categorical(Y_test)\n return X_train,Y_train,X_test,Y_test","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.370723Z","iopub.execute_input":"2022-02-13T20:45:08.371058Z","iopub.status.idle":"2022-02-13T20:45:08.377906Z","shell.execute_reply.started":"2022-02-13T20:45:08.371025Z","shell.execute_reply":"2022-02-13T20:45:08.376453Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Function 2: normalize(train,test) --> trainNorm,testNorm\n### Normalizing Images\nWe need the data to be scaled properly (0-255). So, we normalize it from 0-1","metadata":{}},{"cell_type":"code","source":"def normalize(train,test):\n trainNorm=train/255.0\n testNorm=test/255.0\n return trainNorm,testNorm","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.379836Z","iopub.execute_input":"2022-02-13T20:45:08.380222Z","iopub.status.idle":"2022-02-13T20:45:08.392362Z","shell.execute_reply.started":"2022-02-13T20:45:08.38019Z","shell.execute_reply":"2022-02-13T20:45:08.391466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Function 3: model()--> model\nWithout Dropout => 70%
\nNow we define model and change it as per our needs
\nAdded Dropout!
\nAdded Adam Optimizer","metadata":{}},{"cell_type":"code","source":"def getmodel():\n # Adding sequential to add layers sequentially as per our needs.\n model = ks.Sequential()\n model.add(Conv2D(32,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same', input_shape=(32, 32, 3)))\n model.add(Conv2D(32,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same'))\n model.add(MaxPooling2D((2,2)))\n model.add(Conv2D(64,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same'))\n model.add(Conv2D(64,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same'))\n model.add(MaxPooling2D((2,2)))\n model.add(Conv2D(128,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same'))\n model.add(Conv2D(128,(3,3),activation='relu',kernel_initializer='he_uniform', padding='same'))\n model.add(MaxPooling2D((2,2)))\n \n model.add(Flatten())\n model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n model.add(Dense(10, activation='softmax'))\n \n opt = Adam(learning_rate=0.01,name=\"Adam\")\n model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])\n return model","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.39471Z","iopub.execute_input":"2022-02-13T20:45:08.395238Z","iopub.status.idle":"2022-02-13T20:45:08.410159Z","shell.execute_reply.started":"2022-02-13T20:45:08.395183Z","shell.execute_reply":"2022-02-13T20:45:08.408912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Now we fit our model and code for visualizing it","metadata":{}},{"cell_type":"code","source":"def summarize_diagnostics(history):\n # plot loss\n pyplot.subplot(211)\n pyplot.title('Cross Entropy Loss')\n pyplot.plot(history.history['loss'], color='blue', label='train')\n pyplot.plot(history.history['val_loss'], color='orange', label='test')\n # plot accuracy\n pyplot.subplot(212)\n pyplot.title('Classification Accuracy')\n pyplot.plot(history.history['accuracy'], color='blue', label='train')\n pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n # save plot to file\n filename = sys.argv[0].split('/')[-1]\n pyplot.savefig(filename + '_plot.png')\n pyplot.close()","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.411513Z","iopub.execute_input":"2022-02-13T20:45:08.411882Z","iopub.status.idle":"2022-02-13T20:45:08.431696Z","shell.execute_reply.started":"2022-02-13T20:45:08.411849Z","shell.execute_reply":"2022-02-13T20:45:08.430579Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def trainModel():\n X_train,Y_train,X_test,Y_test=load()\n X_train,X_test=normalize(X_train,X_test)\n model=getmodel()\n history=model.fit(X_train,Y_train,epochs=100,batch_size=64, validation_data=(X_test, Y_test), verbose=0)\n summarize_diagnostics(history)\n _, acc = model.evaluate(X_test, Y_test, verbose=0)\n print('> %.3f' % (acc * 100.0))","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.433682Z","iopub.execute_input":"2022-02-13T20:45:08.434669Z","iopub.status.idle":"2022-02-13T20:45:08.446207Z","shell.execute_reply.started":"2022-02-13T20:45:08.434618Z","shell.execute_reply":"2022-02-13T20:45:08.444915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"trainModel()","metadata":{"execution":{"iopub.status.busy":"2022-02-13T20:45:08.447702Z","iopub.execute_input":"2022-02-13T20:45:08.448027Z","iopub.status.idle":"2022-02-13T20:47:01.171475Z","shell.execute_reply.started":"2022-02-13T20:45:08.447987Z","shell.execute_reply":"2022-02-13T20:47:01.166968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}