{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"#Import Libraries\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nimport keras\nfrom tensorflow.keras import datasets,models,layers\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\n# Adding TF Cifar10 Data ..\n(X_train, y_train), (X_test, y_test) = tf.keras.datasets.cifar10.load_data()\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('X Train Shape is : ' , X_train.shape)\nprint('X Train  is : ' , X_train[5])\nprint('---------------------------------------- ')\nprint('X Test Shape is : ' , X_test.shape)\nprint('X Test  is : ' , X_test[5])\nprint('---------------------------------------- ')\nprint('y Train Shape is : ' , y_train.shape)\nprint('y Train is : ' , y_train[5])\nprint('---------------------------------------- ')\nprint('y Test Shape is : ' , y_test.shape)\nprint('y Test  is : ' , y_test[5])\nprint('---------------------------------------- ')\nprint('All y is : ' , np.unique(y_train))\nprint('---------------------------------------- ')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Drawing sample . \nplt.imshow(X_train[5])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Normalize the data .\nX_train = X_train.astype('float32')\nX_test = X_test.astype('float32')\nX_train /= 255.0\nX_test /= 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = keras.utils.to_categorical(y_train, 10)\ny_test = keras.utils.to_categorical(y_test, 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.models import Sequential\nfrom keras.layers import Dense\nfrom keras.layers import Dropout\nfrom keras.layers import Flatten\nfrom keras.constraints import maxnorm\n# STEP 1 : Building the Model \n\nmodel=Sequential()\nmodel.add(Conv2D(32,(3,3),input_shape=(32,32,3),\n    padding='same',activation='relu',\n    kernel_constraint=maxnorm(3)))\nmodel.add(Dropout(0.2))\nmodel.add(Conv2D(32,(3,3),activation='relu',padding='same',kernel_constraint=maxnorm(3)))\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Flatten())\nmodel.add(Dense(512,activation='relu',kernel_constraint=maxnorm(3)))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation='softmax'))\n\n\n# STEP 2 : Compiling the Model  \n\nmodel.compile(optimizer ='adam',loss='categorical_crossentropy',metrics=['accuracy'])\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Step 3 : Training   \n\nhistory = model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test))\n\nprint('Model Details are : ')\nprint(model.summary())\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# STEP 4 : Predicting   \n\ny_pred = model.predict(X_train)\n\nprint('Prediction Shape is {}'.format(y_pred.shape))\nprint('Prediction items are {}'.format(y_pred[:5]))\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# STEP 5 : Evaluating   \n\nModelLoss, ModelAccuracy = model.evaluate(X_train, y_train)\n\nprint('Model Loss is {}'.format(ModelLoss))\nprint('Model Accuracy is {}'.format(ModelAccuracy ))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def plotmodelhistory(history): \n    fig, axs = plt.subplots(1,2,figsize=(15,5)) \n    # summarize history for accuracy\n    axs[0].plot(history.history['accuracy']) \n    axs[0].plot(history.history['val_accuracy']) \n    axs[0].set_title('Model Accuracy')\n    axs[0].set_ylabel('Accuracy') \n    axs[0].set_xlabel('Epoch')\n    \n    axs[0].legend(['train', 'validate'], loc='upper left')\n    # summarize history for loss\n    axs[1].plot(history.history['loss']) \n    axs[1].plot(history.history['val_loss']) \n    axs[1].set_title('Model Loss')\n    axs[1].set_ylabel('Loss') \n    axs[1].set_xlabel('Epoch')\n    axs[1].legend(['train', 'validate'], loc='upper left')\n    plt.show()\n\n# list all data in history\nprint(history.history.keys())\nplotmodelhistory(history)\n","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}