{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Deep Learning with Keras\n\n* Bu projemizde MNIST veri setini kullanarak 0 dan 9 a kadar olan sayıları sınıflandıracağız.(Çoklu sınıflandırma)","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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)\nfrom matplotlib import pyplot as plt\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Verileri ve etiketleri koda tanımlıyoruz.\n\n# eğitim verileri\nx_train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\n\n# eğitim verileri etiketi\ny_train = x_train['label']\n\n# eğitim verilerinden etiket sütununu siliyoruz\nx_train = x_train.drop(labels=['label'], axis=1)\n\n# test verileri\nx_test = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\n\n# test verileri etiketleri\ny_test = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')\n\ny_test = y_test['Label']\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# eğitim verisi 42000 adet 784 pixel\nprint(x_train.shape)\n\n# test verisi 28000 adet 784 pixel\nprint(x_test.shape)\n\n# eğitim verilerinin etiketi\nprint(y_train.shape)\n\n# test verilerinin etiketleri\nprint(y_test.shape)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Eğitim verilerinin ilk beşi.\n\nx_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 100. indexdeki rakamın görsel hali.\n\nplt.figure(figsize=(7,7))\nrow_index = 100\ngrid_data = np.array(x_train.iloc[row_index]).reshape(28,28)\nplt.imshow(grid_data, interpolation = 'none', cmap= \"gray\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils import to_categorical\n\ntrain_images = x_train.values.reshape((42000, 28, 28, 1))\ntrain_images = train_images.astype('float32') / 255\n\ntest_images = x_test.values.reshape((28000, 28, 28, 1))\ntest_images = test_images.astype('float32') / 255\n\ntrain_labels = to_categorical(y_train)\ntest_labels = to_categorical(y_test)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import layers\nfrom keras import models\nfrom keras.utils import to_categorical\n\ntrain_labels = to_categorical(y_train)\ntest_labels = to_categorical(y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# modelimiz.\nmodel = models.Sequential()\n\n# evrişimli sinir ağları\nmodel.add(layers.Conv2D(32, (3,3), activation=\"relu\", input_shape=(28,28,1)))\n# enbüyükleri biriktirme\nmodel.add(layers.MaxPooling2D((2,2)))\nmodel.add(layers.Conv2D(64, (3,3), activation=\"relu\"))\nmodel.add(layers.MaxPooling2D((2,2)))\nmodel.add(layers.Conv2D(64, (3,3), activation=\"relu\"))\n\n# 3B çıktıları 1B vektörlere dönüştürmek.\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(64, activation=\"relu\"))\nmodel.add(layers.Dense(10, activation=\"softmax\"))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# modeli derleme işlemi\nmodel.compile(optimizer='rmsprop',\n              loss='categorical_crossentropy',\n              metrics=['accuracy'])\n\n# eğitim\nmodel.fit(train_images, train_labels, epochs=8, batch_size=128)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Model doğruluğu 0.99\n# Model kaybı 0.01","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}