{ "cells": [ { "cell_type": "markdown", "metadata": { "slideshow": { "slide_type": "-" } }, "source": [ "### AITech — Uczenie maszynowe — laboratoria\n", "# 11. Sieci neuronowe (Keras)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Keras to napisany w języku Python interfejs do platformy TensorFlow, służącej do uczenia maszynowego.\n", "\n", "Aby z niego korzystać, trzeba zainstalować bibliotekę TensorFlow:\n", " * `pip`: https://www.tensorflow.org/install\n", " * `conda`: https://docs.anaconda.com/anaconda/user-guide/tasks/tensorflow" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Przykład implementacji sieci neuronowej do rozpoznawania cyfr ze zbioru MNIST, według https://keras.io/examples/vision/mnist_convnet" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2023-05-25 10:52:05.523296: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n", "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", "2023-05-25 10:52:06.689624: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n", "2023-05-25 10:52:06.689658: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n", "2023-05-25 10:52:09.444585: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n", "2023-05-25 10:52:09.444822: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n", "2023-05-25 10:52:09.444839: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n" ] } ], "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": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "x_train shape: (60000, 784)\n", "60000 train samples\n", "10000 test samples\n" ] } ], "source": [ "# Przygotowanie danych\n", "\n", "num_classes = 10 # liczba klas\n", "input_shape = (784,) # wymiary wejścia\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 pikseli do przedziału [0, 1]\n", "x_train = x_train.astype(\"float32\") / 255\n", "x_test = x_test.astype(\"float32\") / 255\n", "# spłaszczenie dwuwymiarowych obrazów do jednowymiarowych wektorów\n", "x_train = x_train.reshape(60000, 784) # 784 = 28 * 28\n", "x_test = x_test.reshape(10000, 784)\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": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", " Layer (type) Output Shape Param # \n", "=================================================================\n", " dense (Dense) (None, 512) 401920 \n", " \n", " dense_1 (Dense) (None, 256) 131328 \n", " \n", " dense_2 (Dense) (None, 10) 2570 \n", " \n", "=================================================================\n", "Total params: 535,818\n", "Trainable params: 535,818\n", "Non-trainable params: 0\n", "_________________________________________________________________\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "2023-05-25 10:52:13.751127: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory\n", "2023-05-25 10:52:13.752395: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)\n", "2023-05-25 10:52:13.752552: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (ELLIOT): /proc/driver/nvidia/version does not exist\n", "2023-05-25 10:52:13.755949: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n", "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" ] } ], "source": [ "# Stworzenie modelu\n", "\n", "model = keras.Sequential(\n", " [\n", " keras.Input(shape=input_shape), # warstwa wejściowa\n", " layers.Dense(512, activation=\"relu\", input_shape=(784,)), # warstwa ukryta 1\n", " layers.Dense(256, activation=\"relu\"), # warstwa ukryta 2\n", " layers.Dense(num_classes, activation=\"softmax\"), # warstwa wyjściowa\n", " ]\n", ")\n", "\n", "model.summary() # wyświetlmy podsumowanie modelu" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n", "422/422 [==============================] - 9s 18ms/step - loss: 0.2402 - accuracy: 0.9290 - val_loss: 0.1133 - val_accuracy: 0.9652\n", "Epoch 2/10\n", "422/422 [==============================] - 7s 16ms/step - loss: 0.0878 - accuracy: 0.9728 - val_loss: 0.0776 - val_accuracy: 0.9763\n", "Epoch 3/10\n", "422/422 [==============================] - 7s 18ms/step - loss: 0.0552 - accuracy: 0.9829 - val_loss: 0.0688 - val_accuracy: 0.9792\n", "Epoch 4/10\n", "422/422 [==============================] - 7s 16ms/step - loss: 0.0381 - accuracy: 0.9881 - val_loss: 0.0632 - val_accuracy: 0.9823\n", "Epoch 5/10\n", "422/422 [==============================] - 7s 17ms/step - loss: 0.0286 - accuracy: 0.9908 - val_loss: 0.0782 - val_accuracy: 0.9788\n", "Epoch 6/10\n", "422/422 [==============================] - 7s 17ms/step - loss: 0.0227 - accuracy: 0.9926 - val_loss: 0.0733 - val_accuracy: 0.9807\n", "Epoch 7/10\n", "422/422 [==============================] - 7s 17ms/step - loss: 0.0167 - accuracy: 0.9944 - val_loss: 0.0824 - val_accuracy: 0.9798\n", "Epoch 8/10\n", "422/422 [==============================] - 11s 26ms/step - loss: 0.0158 - accuracy: 0.9948 - val_loss: 0.0765 - val_accuracy: 0.9823\n", "Epoch 9/10\n", "422/422 [==============================] - 8s 18ms/step - loss: 0.0154 - accuracy: 0.9950 - val_loss: 0.0761 - val_accuracy: 0.9802\n", "Epoch 10/10\n", "422/422 [==============================] - 7s 17ms/step - loss: 0.0115 - accuracy: 0.9963 - val_loss: 0.0924 - val_accuracy: 0.9768\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Kompilacja modelu\n", "model.compile(\n", " loss=\"categorical_crossentropy\", # standardowa funkcja kosztu dla kalsyfikacji wieloklasowej\n", " optimizer=\"adam\", # optymalizator\n", " metrics=[\"accuracy\"], # lista metryk\n", ")\n", "\n", "# Uczenie modelu\n", "model.fit(\n", " x_train,\n", " y_train,\n", " batch_size=128, # wielkość wsadu (paczki)\n", " epochs=10, # liczba epok\n", " validation_split=0.1, # wielkość zbioru walidacyjnego\n", ")" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Test loss: 0.10677255690097809\n", "Test accuracy: 0.9757000207901001\n" ] } ], "source": [ "# Ewaluacja modelu\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 (ipykernel)", "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": "3.10.6" }, "livereveal": { "start_slideshow_at": "selected", "theme": "amu" } }, "nbformat": 4, "nbformat_minor": 4 }