{"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":"markdown","source":"1. <a href=\"#load\"> Loading Data </a>\n2. <a href=\"#prep\"> Pre-processing </a>\n3. <a href=\"#bmod\"> Build Model </a>\n4. <a href=\"#eval\"> Evaluate Model </a>\n5. <a href=\"#pred\"> Predict </a>","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, MaxPool2D, Flatten, Dropout\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom sklearn.metrics import classification_report, confusion_matrix","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <a id=\"load\">Loading Data</a>","metadata":{}},{"cell_type":"markdown","source":"CIFAR-10 is a dataset of 50,000 32x32 color training images, labeled over 10 classes","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.datasets import cifar10\n\n(x_train, y_train), (x_test, y_test) = cifar10.load_data()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(x_train.shape)\nprint(y_train.shape)\nprint(x_test.shape)\nprint(y_test.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nfig = plt.figure(figsize=(8, 8))\ncolumns = 6\nrows = 4\nfor i in range(1, columns*rows +1):\n    img = x_train[i]\n    fig.add_subplot(rows, columns, i)\n    plt.axis('off')\n    plt.imshow(img)\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <a id=\"prep\"> Pre-processing </a>","metadata":{}},{"cell_type":"code","source":"print(x_train.max())\nprint(x_test.max())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train = x_train/225\nx_test = x_test/255","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_cat_train = to_categorical(y_train, 10)\ny_cat_test = to_categorical(y_test,10)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <a id=\"bmod\"> Build Model </a>","metadata":{}},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters=32, kernel_size=(4,4),input_shape=(32, 32, 3), activation='relu',))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(filters=32, kernel_size=(4,4), activation='relu',))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(32, activation='relu'))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(10, activation='softmax'))\n\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer='adam',\n              metrics=['accuracy'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"early_stop = EarlyStopping(monitor='val_loss',patience=3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(x_train,\n          y_cat_train,\n          batch_size=128,\n          epochs=20,\n          validation_data=(x_test,y_cat_test),\n          callbacks=[early_stop])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"losses = pd.DataFrame(model.history.history)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"losses[['loss','val_loss']].plot()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"losses[['accuracy','val_accuracy']].plot()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <a id=\"eval\"> Evaluate Model </a>","metadata":{}},{"cell_type":"code","source":"print(model.metrics_names)\nprint(model.evaluate(x_test,y_cat_test,verbose=0))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = np.argmax(model.predict(x_test), axis=-1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(classification_report(y_test,predictions))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"confusion_matrix(y_test,predictions)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <a id=\"pred\"> Predict </a>","metadata":{}},{"cell_type":"code","source":"classes = [0,1,2,3,4,5,6,7,8,9]\nclass_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n# https://www.cs.toronto.edu/~kriz/cifar.html\n\nd = dict(zip(classes, class_names))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_image = x_test[20]\n\nplt.imshow(my_image)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"input_img = my_image.reshape(1,32,32,3)\n\npredictions = np.argmax(model.predict(input_img), axis=-1)[0]\n\nprint(f\"True class: {d[y_test[20][0]]} \\n\\nPredicted class: {d[predictions]}\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}