{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c2686b93",
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.datasets import mnist \n",
    "from tensorflow.keras.utils import to_categorical\n",
    "import numpy as np\n",
    "\n",
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
    "\n",
    "x_train = x_train.astype(\"float32\") / 255.0\n",
    "x_test = x_test.astype(\"float32\") / 255.0\n",
    "\n",
    "x_train = x_train[..., np.newaxis]\n",
    "x_test = x_test[..., np.newaxis]\n",
    "\n",
    "y_train = to_categorical(y_train, 10)\n",
    "y_test = to_categorical(y_test, 10)\n",
    "\n",
    "images_to__check = x_test[:10]\n",
    "labels_to_check = y_test[:10]\n",
    "\n",
    "x_test = x_test[:10]\n",
    "y_test = y_test[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c3a48662",
   "metadata": {},
   "source": [
    "Zadanie 2 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7221a138",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:TensorFlow GPU support is not available on native Windows for TensorFlow >= 2.11. Even if CUDA/cuDNN are installed, GPU will not be used. Please use WSL2 or the TensorFlow-DirectML plugin.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\13-19lat\\AppData\\Roaming\\Python\\Python313\\site-packages\\keras\\src\\layers\\convolutional\\base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m64s\u001b[0m 32ms/step - accuracy: 0.9408 - loss: 0.1982 - val_accuracy: 1.0000 - val_loss: 0.0180\n",
      "Epoch 2/10\n",
      "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m59s\u001b[0m 32ms/step - accuracy: 0.9725 - loss: 0.0902 - val_accuracy: 1.0000 - val_loss: 0.0107\n",
      "Epoch 3/10\n",
      "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 33ms/step - accuracy: 0.9771 - loss: 0.0730 - val_accuracy: 1.0000 - val_loss: 8.4896e-04\n",
      "Epoch 4/10\n",
      "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 33ms/step - accuracy: 0.9810 - loss: 0.0617 - val_accuracy: 1.0000 - val_loss: 0.0048\n",
      "Epoch 5/10\n",
      "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m62s\u001b[0m 33ms/step - accuracy: 0.9827 - loss: 0.0563 - val_accuracy: 1.0000 - val_loss: 0.0123\n",
      "Epoch 6/10\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n",
    "import time\n",
    "start = time.time()\n",
    "\n",
    "model = Sequential([\n",
    "    #Pierwszy blok konwoucyjny \n",
    "    Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(28,28,1)),\n",
    "    BatchNormalization(),\n",
    "    MaxPooling2D((2,2)),\n",
    "    Dropout(0.25),\n",
    "\n",
    "    #Drugi blok konwoucyjny \n",
    "    Conv2D(64, (3, 3), activation='relu', padding='same'),\n",
    "    BatchNormalization(),\n",
    "    MaxPooling2D((2,2)),\n",
    "    Dropout(0.25),\n",
    "\n",
    "    #blok gęsty\n",
    "    Flatten(),\n",
    "    Dense(128, activation='relu'),\n",
    "    BatchNormalization(),\n",
    "    Dropout(0.5),\n",
    "    Dense(10, activation='softmax')\n",
    "])\n",
    "\n",
    "model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])\n",
    "\n",
    "history = model.fit(x_train, y_train, epochs=10, batch_size=32, validation_data=(x_test, y_test))\n",
    "\n",
    "loss, accuracy = model.evaluate(x_test, y_test, verbose=0)\n",
    "print(f\"Strata: {loss:.4f}, Dokładność: {accuracy:.4f}\")\n",
    "\n",
    "end = time.time()\n",
    "\n",
    "print(f\"Czas wykonania: {end - start:.2f} sekundy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "db83b75f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.13.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}