uczenie-maszynowe/lab/CNN_Keras.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "-"
    }
   },
   "source": [
    "### AITech — Uczenie maszynowe — laboratoria\n",
    "# 11. Sieci neuronowe (Keras)"
   ]
  },
  {
   "attachments": {},
   "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"
   ]
  },
  {
   "attachments": {},
   "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": 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": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
      "11493376/11490434 [==============================] - 1s 0us/step\n",
      "x_train shape: (60000, 28, 28, 1)\n",
      "60000 train samples\n",
      "10000 test samples\n"
     ]
    }
   ],
   "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 obrazów 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": [
       "<tensorflow.python.keras.callbacks.History at 0x1a50b35a070>"
      ]
     },
     "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 (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
}