{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "5l2FJZk75s_m"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras import layers, models, optimizers\n",
        "import numpy as np\n",
        "import os"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_dir = '/content/drive/MyDrive/deeplearning/potato2/train'\n",
        "cat_dir = os.path.join(data_dir, 'cats')\n",
        "dog_dir = os.path.join(data_dir, 'dogs')"
      ],
      "metadata": {
        "id": "lkkzHPEQ5_xF"
      },
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# data_dir = '/content/drive/MyDrive/deeplearning/potato2/train'\n",
        "# cat_dir = os.path.join(data_dir, 'cats')\n",
        "# dog_dir = os.path.join(data_dir, 'dogs')"
      ],
      "metadata": {
        "id": "LGEucVf88g9l"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "cat_dir"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "cI-K0GqX8jNN",
        "outputId": "54c84384-0882-4e26-9d4d-bf5f3ee3a2b9"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/content/drive/MyDrive/deeplearning/potato2/train/cats'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# data_dir = 'data'\n",
        "# cat_dir = os.path.join(data_dir, 'cats')\n",
        "# dog_dir = os.path.join(data_dir, 'dogs')\n",
        "\n",
        "num_cats = 1000\n",
        "num_dogs = 1000\n",
        "\n",
        "image_width = 150\n",
        "image_height = 150\n",
        "batch_size = 64\n",
        "\n",
        "# 이미지 데이터를 로드하고 전처리합니다.\n",
        "def load_and_preprocess_data(data_dir, cat_dir, dog_dir, image_width, image_height, batch_size):\n",
        "    # 이미지 파일 경로 생성\n",
        "    cat_images = [os.path.join(cat_dir, file) for file in os.listdir(cat_dir)][:num_cats]\n",
        "    dog_images = [os.path.join(dog_dir, file) for file in os.listdir(dog_dir)][:num_dogs]\n",
        "\n",
        "    # # 이미지 데이터를 NumPy 배열로 로드하고 크기를 조정합니다.\n",
        "    # cat_images = np.array([np.array(tf.image.decode_jpeg(tf.io.read_file(file), channels=3))\n",
        "    #                       for file in cat_images])\n",
        "    # cat_images = np.array([tf.image.resize(image, [image_width, image_height]) for image in cat_images])\n",
        "\n",
        "    # dog_images = np.array([np.array(tf.image.decode_jpeg(tf.io.read_file(file), channels=3))\n",
        "    #                       for file in dog_images])\n",
        "    # dog_images = np.array([tf.image.resize(image, [image_width, image_height]) for image in dog_images])\n",
        "\n",
        "# # 이미지 데이터를 로드하고 전처리합니다.\n",
        "# def load_and_preprocess_data(data_dir, cat_dir, dog_dir, image_width, image_height, batch_size):\n",
        "#     # ... (이전 코드 생략)\n",
        "\n",
        "    # 이미지 데이터를 로드하고 크기를 조정합니다.\n",
        "    cat_images = [tf.image.decode_jpeg(tf.io.read_file(file), channels=3) for file in cat_images]\n",
        "    cat_images = [tf.image.resize(image, [image_width, image_height]) for image in cat_images]\n",
        "\n",
        "    dog_images = [tf.image.decode_jpeg(tf.io.read_file(file), channels=3) for file in dog_images]\n",
        "    dog_images = [tf.image.resize(image, [image_width, image_height]) for image in dog_images]\n",
        "\n",
        "    # ... (나머지 코드 생략)\n",
        "\n",
        "    # 레이블을 할당합니다.\n",
        "    cat_labels = np.zeros((num_cats,))\n",
        "    dog_labels = np.ones((num_dogs,))\n",
        "\n",
        "    # 데이터를 섞습니다.\n",
        "    permutation = np.random.permutation(num_cats + num_dogs)\n",
        "    cat_images = cat_images[permutation[:num_cats]]\n",
        "    cat_labels = cat_labels[permutation[:num_cats]]\n",
        "    dog_images = dog_images[permutation[num_cats:]]\n",
        "    dog_labels = dog_labels[permutation[num_cats:]]\n",
        "\n",
        "    # 데이터를 배치로 분할합니다.\n",
        "    dataset = tf.data.Dataset.from_tensor_slices(({'input_image': cat_images[:num_cats] + dog_images[:num_dogs]},\n",
        "                                                 {'output': cat_labels[:num_cats] + dog_labels[:num_dogs]}))\n",
        "    dataset = dataset.shuffle(num_cats + num_dogs).batch(batch_size)\n",
        "\n",
        "    return dataset"
      ],
      "metadata": {
        "id": "VHIMj5ju5w-t"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# CNN 모델을 정의합니다.\n",
        "def create_model(image_width, image_height):\n",
        "    model = models.Sequential()\n",
        "    model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(image_width, image_height, 3)))\n",
        "    model.add(layers.MaxPooling2D((2, 2)))\n",
        "    model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n",
        "    model.add(layers.MaxPooling2D((2, 2)))\n",
        "    model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n",
        "    model.add(layers.Flatten())\n",
        "    model.add(layers.Dense(64, activation='relu'))\n",
        "    model.add(layers.Dense(1, activation='sigmoid'))\n",
        "\n",
        "    model.compile(optimizer=optimizers.Adam(),\n",
        "                  loss='binary_crossentropy',\n",
        "                  metrics=['accuracy'])\n",
        "\n",
        "    return model"
      ],
      "metadata": {
        "id": "Xvt6mJoh5w76"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "# # 이미지 파일 경로 생성\n",
        "# cat_images = [os.path.join(cat_dir, file) for file in os.listdir(cat_dir)][:num_cats]\n",
        "# dog_images = [os.path.join(dog_dir, file) for file in os.listdir(dog_dir)][:num_dogs]\n",
        "\n",
        "# # 이 수정으로 파일 경로가 올바르게 설정되어야 합니다."
      ],
      "metadata": {
        "id": "6l6NYChH8aom"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 데이터를 로드하고 모델을 훈련시킵니다.\n",
        "dataset = load_and_preprocess_data(data_dir, cat_dir, dog_dir, image_width, image_height, batch_size)\n",
        "\n",
        "model = create_model(image_width, image_height)\n",
        "model.summary()\n",
        "\n",
        "epochs = 10\n",
        "history = model.fit(dataset, epochs=epochs)\n",
        "\n",
        "# 훈련 결과를 플로팅합니다.\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.plot(history.history['accuracy'])\n",
        "plt.title('모델 정확도')\n",
        "plt.ylabel('정확도')\n",
        "plt.xlabel('에포크')\n",
        "plt.show()\n",
        "\n",
        "plt.plot(history.history['loss'])\n",
        "plt.title('모델 손실')\n",
        "plt.ylabel('손실')\n",
        "plt.xlabel('에포크')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 406
        },
        "id": "zY6nlzt35w45",
        "outputId": "23cc2127-edf7-4b84-9da4-3ad95281aa33"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "error",
          "ename": "InvalidArgumentError",
          "evalue": "{{function_node __wrapped__DecodeJpeg_device_/job:localhost/replica:0/task:0/device:CPU:0}} Input is empty. [Op:DecodeJpeg]",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mInvalidArgumentError\u001b[0m                      Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-17-06d5268810d8>\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# 데이터를 로드하고 모델을 훈련시킵니다.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_and_preprocess_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcat_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdog_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcreate_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msummary\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m<ipython-input-13-f5a68afb907c>\u001b[0m in \u001b[0;36mload_and_preprocess_data\u001b[0;34m(data_dir, cat_dir, dog_dir, image_width, image_height, batch_size)\u001b[0m\n\u001b[1;32m     33\u001b[0m     \u001b[0mcat_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mimage\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mcat_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     34\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 35\u001b[0;31m     \u001b[0mdog_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode_jpeg\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchannels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mfile\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdog_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     36\u001b[0m     \u001b[0mdog_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mimage\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdog_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     37\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m<ipython-input-13-f5a68afb907c>\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     33\u001b[0m     \u001b[0mcat_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mimage\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mcat_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     34\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 35\u001b[0;31m     \u001b[0mdog_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode_jpeg\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchannels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mfile\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdog_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     36\u001b[0m     \u001b[0mdog_images\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mimage_width\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_height\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mimage\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdog_images\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     37\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    151\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    152\u001b[0m       \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 153\u001b[0;31m       \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwith_traceback\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiltered_tb\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    154\u001b[0m     \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    155\u001b[0m       \u001b[0;32mdel\u001b[0m \u001b[0mfiltered_tb\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     51\u001b[0m   \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     52\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 53\u001b[0;31m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0m\u001b[1;32m     54\u001b[0m                                         inputs, attrs, num_outputs)\n\u001b[1;32m     55\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mInvalidArgumentError\u001b[0m: {{function_node __wrapped__DecodeJpeg_device_/job:localhost/replica:0/task:0/device:CPU:0}} Input is empty. [Op:DecodeJpeg]"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# # 이미지 데이터를 로드하고 전처리합니다.\n",
        "# def load_and_preprocess_data(data_dir, cat_dir, dog_dir, image_width, image_height, batch_size):\n",
        "#     # ... (이전 코드 생략)\n",
        "\n",
        "#     # 이미지 데이터를 로드하고 크기를 조정합니다.\n",
        "#     cat_images = [tf.image.decode_jpeg(tf.io.read_file(file), channels=3) for file in cat_images]\n",
        "#     cat_images = [tf.image.resize(image, [image_width, image_height]) for image in cat_images]\n",
        "\n",
        "#     dog_images = [tf.image.decode_jpeg(tf.io.read_file(file), channels=3) for file in dog_images]\n",
        "#     dog_images = [tf.image.resize(image, [image_width, image_height]) for image in dog_images]\n",
        "\n",
        "#     # ... (나머지 코드 생략)"
      ],
      "metadata": {
        "id": "SeRfZXGd5w17"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "bTKLWeyG5wzE"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}