{ "cells": [ { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "-" } }, "source": [ "### Uczenie maszynowe — zastosowania\n", "# Sieci neuronowe (Keras)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "[Keras](https://keras.io) to napisany w języku Python interfejs do platformy [TensorFlow](https://www.tensorflow.org), służącej do uczenia maszynowego.\n", "\n", "Aby z niego korzystać, trzeba zainstalować bibliotekę TensorFlow.\n", "\n", "Instrukcja dla skryptów Pythona (pliki *.py*):\n", " * `pip`: https://www.tensorflow.org/install\n", " * `conda`: https://docs.anaconda.com/anaconda/user-guide/tasks/tensorflow" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Aby uruchomić TensorFlow w środowisku Jupyter, należy wykonać następujące czynności:\n", "\n", "#### Przed pierwszym uruchomieniem (wystarczy wykonać tylko raz)\n", "\n", "Instalacja biblioteki TensorFlow w środowisku Anaconda:\n", "\n", "1. Uruchom *Anaconda Navigator*\n", "1. Wybierz kafelek *CMD.exe Prompt*\n", "1. Kliknij przycisk *Launch*\n", "1. Pojawi się konsola. Wpisz następujące polecenia, każde zatwierdzając wciśnięciem klawisza Enter:\n", "```\n", "conda create -n tf tensorflow\n", "conda activate tf\n", "conda install pandas matplotlib\n", "jupyter notebook\n", "```\n", "\n", "#### Przed każdym uruchomieniem\n", "\n", "Jeżeli chcemy korzystać z biblioteki TensorFlow, to środowisko Jupyter Notebook należy uruchomić w następujący sposób:\n", "\n", "1. Uruchom *Anaconda Navigator*\n", "1. Wybierz kafelek *CMD.exe Prompt*\n", "1. Kliknij przycisk *Launch*\n", "1. Pojawi się konsola. Wpisz następujące polecenia, każde zatwierdzając wciśnięciem klawisza Enter:\n", "```\n", "conda activate tf\n", "jupyter notebook\n", "```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Przykład implementacji sieci neuronowej do rozpoznawania cyfr ze zbioru [MNIST](https://en.wikipedia.org/wiki/MNIST_database), według https://keras.io/examples/vision/mnist_convnet" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "# Konieczne importy\n", "\n", "import numpy as np\n", "from tensorflow import keras\n", "from tensorflow.keras import layers" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'keras' is not defined", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;31m# podział danych na zbiory uczący i testowy\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 7\u001b[1;33m \u001b[1;33m(\u001b[0m\u001b[0mx_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mx_test\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdatasets\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmnist\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 8\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 9\u001b[0m \u001b[1;31m# skalowanie wartości pikseli do przedziału [0, 1]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mNameError\u001b[0m: name 'keras' is not defined" ] } ], "source": [ "# Przygotowanie danych\n", "\n", "num_classes = 10\n", "input_shape = (28, 28, 1)\n", "\n", "# podział danych na zbiory uczący i testowy\n", "(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()\n", "\n", "# skalowanie wartości pikseli do przedziału [0, 1]\n", "x_train = x_train.astype(\"float32\") / 255\n", "x_test = x_test.astype(\"float32\") / 255\n", "# upewnienie się, że obrazy mają wymiary (28, 28, 1)\n", "x_train = np.expand_dims(x_train, -1)\n", "x_test = np.expand_dims(x_test, -1)\n", "print(\"x_train shape:\", x_train.shape)\n", "print(x_train.shape[0], \"train samples\")\n", "print(x_test.shape[0], \"test samples\")\n", "\n", "# konwersja danych kategorycznych na binarne\n", "y_train = keras.utils.to_categorical(y_train, num_classes)\n", "y_test = keras.utils.to_categorical(y_test, num_classes)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "conv2d (Conv2D) (None, 26, 26, 32) 320 \n", "_________________________________________________________________\n", "max_pooling2d (MaxPooling2D) (None, 13, 13, 32) 0 \n", "_________________________________________________________________\n", "conv2d_1 (Conv2D) (None, 11, 11, 64) 18496 \n", "_________________________________________________________________\n", "max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64) 0 \n", "_________________________________________________________________\n", "flatten (Flatten) (None, 1600) 0 \n", "_________________________________________________________________\n", "dropout (Dropout) (None, 1600) 0 \n", "_________________________________________________________________\n", "dense (Dense) (None, 10) 16010 \n", "=================================================================\n", "Total params: 34,826\n", "Trainable params: 34,826\n", "Non-trainable params: 0\n", "_________________________________________________________________\n" ] } ], "source": [ "# Stworzenie modelu\n", "\n", "model = keras.Sequential(\n", " [\n", " keras.Input(shape=input_shape),\n", " layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n", " layers.MaxPooling2D(pool_size=(2, 2)),\n", " layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n", " layers.MaxPooling2D(pool_size=(2, 2)),\n", " layers.Flatten(),\n", " layers.Dropout(0.5),\n", " layers.Dense(num_classes, activation=\"softmax\"),\n", " ]\n", ")\n", "\n", "model.summary()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "422/422 [==============================] - 38s 91ms/step - loss: 0.0556 - accuracy: 0.9826 - val_loss: 0.0412 - val_accuracy: 0.9893\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Uczenie modelu\n", "\n", "batch_size = 128\n", "epochs = 15\n", "\n", "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n", "\n", "model.fit(x_train, y_train, epochs=1, batch_size=batch_size, epochs=epochs, validation_split=0.1)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Test loss: 0.03675819933414459\n", "Test accuracy: 0.988099992275238\n" ] } ], "source": [ "# Ewaluacja modelu\n", "\n", "score = model.evaluate(x_test, y_test, verbose=0)\n", "print(\"Test loss:\", score[0])\n", "print(\"Test accuracy:\", score[1])" ] } ], "metadata": { "celltoolbar": "Slideshow", "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.3" }, "livereveal": { "start_slideshow_at": "selected", "theme": "amu" } }, "nbformat": 4, "nbformat_minor": 4 }