{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T10:48:15.68996Z","iopub.execute_input":"2025-09-24T10:48:15.690743Z","iopub.status.idle":"2025-09-24T10:48:15.702452Z","shell.execute_reply.started":"2025-09-24T10:48:15.690555Z","shell.execute_reply":"2025-09-24T10:48:15.701457Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/dogs-vs-cats/test1.zip\n/kaggle/input/dogs-vs-cats/train.zip\n/kaggle/input/dogs-vs-cats/sampleSubmission.csv\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"import os, shutil\nimport pandas as pd\nfrom zipfile import ZipFile","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T10:57:47.347361Z","iopub.execute_input":"2025-09-24T10:57:47.348686Z","iopub.status.idle":"2025-09-24T10:57:47.353522Z","shell.execute_reply.started":"2025-09-24T10:57:47.348652Z","shell.execute_reply":"2025-09-24T10:57:47.35251Z"}},"outputs":[],"execution_count":8},{"cell_type":"code","source":"from zipfile import ZipFile\n\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T12:34:14.869083Z","iopub.execute_input":"2025-09-24T12:34:14.869443Z","iopub.status.idle":"2025-09-24T12:34:32.977103Z","shell.execute_reply.started":"2025-09-24T12:34:14.869417Z","shell.execute_reply":"2025-09-24T12:34:32.976193Z"}},"outputs":[],"execution_count":2},{"cell_type":"code","source":"import os\n\nprint(\"Train klasöründeki örnek dosyalar:\", os.listdir(\"train\")[:10])\nprint(\"Test klasöründeki örnek dosyalar:\", os.listdir(\"test1\")[:10])\n\nprint(\"Toplam train görüntü sayısı:\", len(os.listdir(\"train\")))\nprint(\"Toplam test görüntü sayısı:\", len(os.listdir(\"test1\")))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T12:35:09.194412Z","iopub.execute_input":"2025-09-24T12:35:09.194762Z","iopub.status.idle":"2025-09-24T12:35:09.250853Z","shell.execute_reply.started":"2025-09-24T12:35:09.194734Z","shell.execute_reply":"2025-09-24T12:35:09.249577Z"}},"outputs":[{"name":"stdout","text":"Train klasöründeki örnek dosyalar: ['cat.1417.jpg', 'dog.8988.jpg', 'cat.6441.jpg', 'cat.7314.jpg', 'cat.5818.jpg', 'dog.2962.jpg', 'cat.10991.jpg', 'dog.10747.jpg', 'cat.2637.jpg', 'dog.11117.jpg']\nTest klasöründeki örnek dosyalar: ['5187.jpg', '2257.jpg', '9025.jpg', '1459.jpg', '3196.jpg', '77.jpg', '7465.jpg', '5960.jpg', '1465.jpg', '9319.jpg']\nToplam train görüntü sayısı: 25000\nToplam test görüntü sayısı: 12500\n","output_type":"stream"}],"execution_count":3},{"cell_type":"markdown","source":"Veri önişlemesi için gerekli kütüphaneleri yüklüyoruz.","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T12:41:35.20702Z","iopub.execute_input":"2025-09-24T12:41:35.207699Z","iopub.status.idle":"2025-09-24T12:42:00.571639Z","shell.execute_reply.started":"2025-09-24T12:41:35.207662Z","shell.execute_reply":"2025-09-24T12:42:00.570265Z"}},"outputs":[{"name":"stderr","text":"2025-09-24 12:41:38.549669: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1758717699.022203      36 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1758717699.145522      36 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T12:58:00.218496Z","iopub.execute_input":"2025-09-24T12:58:00.218733Z","iopub.status.idle":"2025-09-24T12:58:14.115343Z","shell.execute_reply.started":"2025-09-24T12:58:00.21871Z","shell.execute_reply":"2025-09-24T12:58:14.114707Z"}},"outputs":[{"name":"stderr","text":"2025-09-24 12:58:01.925853: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1758718682.109969      36 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1758718682.169269      36 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"IMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:05:06.581432Z","iopub.execute_input":"2025-09-24T13:05:06.581696Z","iopub.status.idle":"2025-09-24T13:05:06.601001Z","shell.execute_reply.started":"2025-09-24T13:05:06.581679Z","shell.execute_reply":"2025-09-24T13:05:06.600128Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_36/484851018.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0mtest_datagen\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mImageDataGenerator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrescale\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1.\u001b[0m\u001b[0;34m/\u001b[0m\u001b[0;36m255\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m train_generator = train_datagen.flow_from_directory(\n\u001b[0m\u001b[1;32m     19\u001b[0m     \u001b[0;34m'train'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     20\u001b[0m     \u001b[0mtarget_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mIMAGE_SIZE\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/keras/src/legacy/preprocessing/image.py\u001b[0m in \u001b[0;36mflow_from_directory\u001b[0;34m(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio)\u001b[0m\n\u001b[1;32m   1136\u001b[0m         \u001b[0mkeep_aspect_ratio\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1137\u001b[0m     ):\n\u001b[0;32m-> 1138\u001b[0;31m         return DirectoryIterator(\n\u001b[0m\u001b[1;32m   1139\u001b[0m             \u001b[0mdirectory\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1140\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/keras/src/legacy/preprocessing/image.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio, dtype)\u001b[0m\n\u001b[1;32m    451\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mclasses\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    452\u001b[0m             \u001b[0mclasses\u001b[0m \u001b[0;34m=\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--> 453\u001b[0;31m             \u001b[0;32mfor\u001b[0m \u001b[0msubdir\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msorted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\u001b[0m\u001b[0;34m)\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[0m\u001b[1;32m    454\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubdir\u001b[0m\u001b[0;34m)\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[1;32m    455\u001b[0m                     \u001b[0mclasses\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msubdir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'train'"],"ename":"FileNotFoundError","evalue":"[Errno 2] No such file or directory: 'train'","output_type":"error"}],"execution_count":3},{"cell_type":"code","source":"from zipfile import ZipFile\n\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:07:24.887451Z","iopub.execute_input":"2025-09-24T13:07:24.88821Z","iopub.status.idle":"2025-09-24T13:07:36.760205Z","shell.execute_reply.started":"2025-09-24T13:07:24.888184Z","shell.execute_reply":"2025-09-24T13:07:36.759644Z"}},"outputs":[],"execution_count":4},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n\n# Görüntü boyutlarını ve batch boyutunu belirle\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\n# Eğitim ve doğrulama için ImageDataGenerator'ı oluştur\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\n# Test verisi için sadece ölçekleme işlemi yap\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\n# Veri kümelerini oluştur\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:10:31.593538Z","iopub.execute_input":"2025-09-24T13:10:31.593837Z","iopub.status.idle":"2025-09-24T13:10:31.911572Z","shell.execute_reply.started":"2025-09-24T13:10:31.593816Z","shell.execute_reply":"2025-09-24T13:10:31.910855Z"}},"outputs":[{"name":"stdout","text":"Found 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"from zipfile import ZipFile\n\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:11:20.458972Z","iopub.execute_input":"2025-09-24T13:11:20.459255Z","iopub.status.idle":"2025-09-24T13:11:29.142392Z","shell.execute_reply.started":"2025-09-24T13:11:20.459234Z","shell.execute_reply":"2025-09-24T13:11:29.141823Z"}},"outputs":[],"execution_count":6},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# Görüntü boyutlarını ve batch boyutunu belirle\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\n# Eğitim ve doğrulama için ImageDataGenerator'ı oluştur\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\n# Test verisi için sadece ölçekleme işlemi yap\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\n# Veri kümelerini oluştur\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:11:43.044691Z","iopub.execute_input":"2025-09-24T13:11:43.045415Z","iopub.status.idle":"2025-09-24T13:11:43.352777Z","shell.execute_reply.started":"2025-09-24T13:11:43.045388Z","shell.execute_reply":"2025-09-24T13:11:43.352237Z"}},"outputs":[{"name":"stdout","text":"Found 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\n","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"from zipfile import ZipFile\n\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:13:44.321411Z","iopub.execute_input":"2025-09-24T13:13:44.321924Z","iopub.status.idle":"2025-09-24T13:13:52.864763Z","shell.execute_reply.started":"2025-09-24T13:13:44.321898Z","shell.execute_reply":"2025-09-24T13:13:52.864177Z"}},"outputs":[],"execution_count":8},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom zipfile import ZipFile\n\n# Zip dosyalarını çıkar\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')\n\n# Görüntü boyutlarını ve batch boyutunu belirle\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\n# Eğitim ve doğrulama için ImageDataGenerator'ı oluştur\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\n# Test verisi için sadece ölçekleme işlemi yap\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\n# Veri kümelerini oluştur\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:14:51.302983Z","iopub.execute_input":"2025-09-24T13:14:51.30326Z","iopub.status.idle":"2025-09-24T13:15:00.595771Z","shell.execute_reply.started":"2025-09-24T13:14:51.30324Z","shell.execute_reply":"2025-09-24T13:15:00.595242Z"}},"outputs":[{"name":"stdout","text":"Found 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\nFound 0 images belonging to 0 classes.\n","output_type":"stream"}],"execution_count":9},{"cell_type":"code","source":"import os, shutil\n\n# Zip dosyalarını çıkar\nfrom zipfile import ZipFile\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')\n\n# Klasörleri oluştur (eğer yoksa)\nos.makedirs('train/dog', exist_ok=True)\nos.makedirs('train/cat', exist_ok=True)\n\n# Dosyaları ilgili klasörlere taşı\nfor filename in os.listdir('train'):\n    if filename.startswith('cat'):\n        shutil.move(os.path.join('train', filename), 'train/cat')\n    elif filename.startswith('dog'):\n        shutil.move(os.path.join('train', filename), 'train/dog')\n\n# Kütüphane ve Veri Üreticilerini Yükle\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# Görüntü boyutlarını ve batch boyutunu belirle\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\n# Eğitim ve doğrulama için ImageDataGenerator'ı oluştur\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\n# Test verisi için sadece ölçekleme işlemi yap\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\n# Veri kümelerini oluştur\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-24T13:16:05.836646Z","iopub.execute_input":"2025-09-24T13:16:05.837221Z","iopub.status.idle":"2025-09-24T13:16:16.413934Z","shell.execute_reply.started":"2025-09-24T13:16:05.837197Z","shell.execute_reply":"2025-09-24T13:16:16.41338Z"}},"outputs":[{"name":"stdout","text":"Found 20000 images belonging to 2 classes.\nFound 5000 images belonging to 2 classes.\nFound 0 images belonging to 0 classes.\n","output_type":"stream"}],"execution_count":10},{"cell_type":"code","source":"import os, shutil\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom zipfile import ZipFile\n\n# 1. Adım: Zip dosyalarını çıkar\n# Bu işlem, train ve test1 klasörlerini yeniden oluşturur\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')\n\n# 2. Adım: ImageDataGenerator için klasör yapısını düzenle\n# Eğer klasörler zaten varsa, bu komutlar hata vermeyecektir\nos.makedirs('train/dog', exist_ok=True)\nos.makedirs('train/cat', exist_ok=True)\n\n# Dosyaları ilgili klasörlere taşı\n# Bu işlem yalnızca bir kez yapılacağı için, daha sonra bu kodu silmen gerekecek.\n# Şimdilik, her seferinde çalışması için buraya ekledik.\nfor filename in os.listdir('train'):\n    if filename.startswith('cat'):\n        shutil.move(os.path.join('train', filename), 'train/cat')\n    elif filename.startswith('dog'):\n        shutil.move(os.path.join('train', filename), 'train/dog')\n\n# 3. Adım: Veri ön işleme ve veri çoğaltma (data augmentation)\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\ntest_generator = test_datagen.flow_from_directory(\n    'test1',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T06:02:19.09267Z","iopub.execute_input":"2025-09-25T06:02:19.092846Z","iopub.status.idle":"2025-09-25T06:02:46.272735Z","shell.execute_reply.started":"2025-09-25T06:02:19.092829Z","shell.execute_reply":"2025-09-25T06:02:46.271975Z"}},"outputs":[{"name":"stderr","text":"2025-09-25 06:02:20.848062: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1758780141.034156      36 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1758780141.094565      36 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"},{"name":"stdout","text":"Found 20000 images belonging to 2 classes.\nFound 5000 images belonging to 2 classes.\nFound 0 images belonging to 0 classes.\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"# Modeli Derle (Compile)\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n\n# CNN Modelini Oluşturma\nmodel = Sequential([\n    # İlk evrişim ve havuzlama katmanı\n    Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),\n    MaxPooling2D(2, 2),\n    \n    # İkinci evrişim ve havuzlama katmanı\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    \n    # Üçüncü evrişim ve havuzlama katmanı\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    \n    # Veriyi tek boyuta indirge (düzleştirme)\n    Flatten(),\n    \n    # Aşırı uydurmayı (overfitting) önlemek için Dropout katmanı\n    Dropout(0.5),\n    \n    # Yoğun (Dense) katmanlar\n    Dense(512, activation='relu'),\n    Dense(1, activation='sigmoid') # İkili sınıflandırma için sigmoid aktivasyonu\n])\n\nmodel.compile(optimizer=RMSprop(learning_rate=0.001),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])\n\n# Modeli Eğitme (Fit)\nhistory = model.fit(\n    train_generator,\n    steps_per_epoch=train_generator.samples // train_generator.batch_size,\n    epochs=15, \n    validation_data=validation_generator,\n    validation_steps=validation_generator.samples // validation_generator.batch_size\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T06:14:35.167754Z","iopub.execute_input":"2025-09-25T06:14:35.168366Z","iopub.status.idle":"2025-09-25T06:31:33.56098Z","shell.execute_reply.started":"2025-09-25T06:14:35.168336Z","shell.execute_reply":"2025-09-25T06:31:33.56019Z"}},"outputs":[{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/keras/src/layers/convolutional/base_conv.py:107: 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)\nI0000 00:00:1758780875.983967      36 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 15513 MB memory:  -> device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0\n/usr/local/lib/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n  self._warn_if_super_not_called()\n","output_type":"stream"},{"name":"stdout","text":"Epoch 1/15\n","output_type":"stream"},{"name":"stderr","text":"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nI0000 00:00:1758780879.636824     120 service.cc:148] XLA service 0x7eea54006340 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\nI0000 00:00:1758780879.637674     120 service.cc:156]   StreamExecutor device (0): Tesla P100-PCIE-16GB, Compute Capability 6.0\nI0000 00:00:1758780879.903856     120 cuda_dnn.cc:529] Loaded cuDNN version 90300\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m  1/312\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m28:08\u001b[0m 5s/step - accuracy: 0.5469 - loss: 0.6957","output_type":"stream"},{"name":"stderr","text":"I0000 00:00:1758780883.240146     120 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 360ms/step - accuracy: 0.5311 - loss: 0.7484 - val_accuracy: 0.6569 - val_loss: 0.6469\nEpoch 2/15\n\u001b[1m  1/312\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m6s\u001b[0m 22ms/step - accuracy: 0.7188 - loss: 0.6303","output_type":"stream"},{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/keras/src/trainers/epoch_iterator.py:107: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n  self._interrupted_warning()\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 69ms/step - accuracy: 0.7188 - loss: 0.6303 - val_accuracy: 0.6156 - val_loss: 0.6428\nEpoch 3/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m108s\u001b[0m 345ms/step - accuracy: 0.6459 - loss: 0.6270 - val_accuracy: 0.6178 - val_loss: 0.6390\nEpoch 4/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.5000 - loss: 0.7345 - val_accuracy: 0.6793 - val_loss: 0.5836\nEpoch 5/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 344ms/step - accuracy: 0.6890 - loss: 0.5889 - val_accuracy: 0.7109 - val_loss: 0.5630\nEpoch 6/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.7656 - loss: 0.5063 - val_accuracy: 0.7268 - val_loss: 0.5528\nEpoch 7/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 343ms/step - accuracy: 0.7042 - loss: 0.5683 - val_accuracy: 0.7388 - val_loss: 0.5189\nEpoch 8/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 69ms/step - accuracy: 0.8281 - loss: 0.4531 - val_accuracy: 0.7031 - val_loss: 0.5836\nEpoch 9/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 344ms/step - accuracy: 0.7170 - loss: 0.5535 - val_accuracy: 0.7510 - val_loss: 0.5107\nEpoch 10/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.7500 - loss: 0.4440 - val_accuracy: 0.7348 - val_loss: 0.5277\nEpoch 11/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 343ms/step - accuracy: 0.7281 - loss: 0.5336 - val_accuracy: 0.7638 - val_loss: 0.4909\nEpoch 12/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.7656 - loss: 0.5291 - val_accuracy: 0.6679 - val_loss: 0.6143\nEpoch 13/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 342ms/step - accuracy: 0.7361 - loss: 0.5253 - val_accuracy: 0.7640 - val_loss: 0.4847\nEpoch 14/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 70ms/step - accuracy: 0.8125 - loss: 0.4280 - val_accuracy: 0.7143 - val_loss: 0.5612\nEpoch 15/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 341ms/step - accuracy: 0.7453 - loss: 0.5134 - val_accuracy: 0.7734 - val_loss: 0.4810\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Accuracy ve Loss grafikleri\nacc = history.history['accuracy']\nval_acc = history.history['val_accuracy']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs_range = range(len(acc))\n\nplt.figure(figsize=(12, 6))\nplt.subplot(1, 2, 1)\nplt.plot(epochs_range, acc, label='Eğitim Doğruluğu')\nplt.plot(epochs_range, val_acc, label='Doğrulama Doğruluğu')\nplt.legend(loc='lower right')\nplt.title('Eğitim ve Doğrulama Doğruluğu')\n\nplt.subplot(1, 2, 2)\nplt.plot(epochs_range, loss, label='Eğitim Kaybı')\nplt.plot(epochs_range, val_loss, label='Doğrulama Kaybı')\nplt.legend(loc='upper right')\nplt.title('Eğitim ve Doğrulama Kaybı')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T06:37:15.7773Z","iopub.execute_input":"2025-09-25T06:37:15.777793Z","iopub.status.idle":"2025-09-25T06:37:16.183466Z","shell.execute_reply.started":"2025-09-25T06:37:15.77777Z","shell.execute_reply":"2025-09-25T06:37:16.182657Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x600 with 2 Axes>","image/png":"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\n"},"metadata":{}}],"execution_count":3},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import confusion_matrix, classification_report\n\n# Test verisi üzerinden tahminler yap\npredictions = model.predict(test_generator)\npredicted_classes = np.round(predictions).flatten()\ntrue_classes = test_generator.classes\n\n# Confusion Matrix ve Classification Report'u oluştur\ncm = confusion_matrix(true_classes, predicted_classes)\ncr = classification_report(true_classes, predicted_classes)\n\nprint(\"Confusion Matrix:\")\nprint(cm)\nprint(\"\\nClassification Report:\")\nprint(cr)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:00:52.871617Z","iopub.execute_input":"2025-09-25T07:00:52.872369Z","iopub.status.idle":"2025-09-25T07:00:53.256939Z","shell.execute_reply.started":"2025-09-25T07:00:52.872338Z","shell.execute_reply":"2025-09-25T07:00:53.255908Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_36/3286679422.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m# Test verisi üzerinden tahminler yap\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mpredictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_generator\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      6\u001b[0m \u001b[0mpredicted_classes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mround\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpredictions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflatten\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[1;32m      7\u001b[0m \u001b[0mtrue_classes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtest_generator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclasses\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    120\u001b[0m             \u001b[0;31m# To get the full stack trace, call:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    121\u001b[0m             \u001b[0;31m# `keras.config.disable_traceback_filtering()`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 122\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    123\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    124\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/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py\u001b[0m in \u001b[0;36mget_tf_dataset\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    293\u001b[0m             ]\n\u001b[1;32m    294\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatches\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 295\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"The PyDataset has length 0\"\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    296\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output_signature\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata_adapter_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_tensor_spec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatches\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    297\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: The PyDataset has length 0"],"ename":"ValueError","evalue":"The PyDataset has length 0","output_type":"error"}],"execution_count":4},{"cell_type":"code","source":"import os, shutil\nimport tensorflow as tf\nimport numpy as np\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom sklearn.metrics import confusion_matrix, classification_report\nfrom zipfile import ZipFile\n\n# 1. Zip dosyalarını çıkar\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')\n\n# 2. Eğitim verisi için klasör yapısını düzenle\nos.makedirs('train/dog', exist_ok=True)\nos.makedirs('train/cat', exist_ok=True)\nfor filename in os.listdir('train'):\n    if filename.startswith('cat'):\n        shutil.move(os.path.join('train', filename), 'train/cat')\n    elif filename.startswith('dog'):\n        shutil.move(os.path.join('train', filename), 'train/dog')\n\n# 3. Test verisi için klasör yapısını düzenle (Tüm test resimlerini tek bir klasöre taşı)\nos.makedirs('test_data/test1', exist_ok=True)\nfor filename in os.listdir('test1'):\n    shutil.move(os.path.join('test1', filename), 'test_data/test1')\n\n# 4. Veri üreticilerini hazırla\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255, rotation_range=40, width_shift_range=0.2,\n    height_shift_range=0.2, shear_range=0.2, zoom_range=0.2,\n    horizontal_flip=True, fill_mode='nearest', validation_split=0.2)\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(\n    'train', target_size=IMAGE_SIZE, batch_size=BATCH_SIZE,\n    class_mode='binary', subset='training')\nvalidation_generator = train_datagen.flow_from_directory(\n    'train', target_size=IMAGE_SIZE, batch_size=BATCH_SIZE,\n    class_mode='binary', subset='validation')\n\n# Test generator'ı yeni klasör yapısıyla oluştur\ntest_generator = test_datagen.flow_from_directory(\n    'test_data', target_size=IMAGE_SIZE, batch_size=BATCH_SIZE,\n    class_mode=None, shuffle=False)\n\n# 5. Modeli oluştur ve derle\nmodel = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),\n    MaxPooling2D(2, 2),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    Flatten(),\n    Dropout(0.5),\n    Dense(512, activation='relu'),\n    Dense(1, activation='sigmoid')\n])\nmodel.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])\n\n# 6. Modeli eğit (Bu kısım biraz zaman alabilir)\nhistory = model.fit(\n    train_generator,\n    steps_per_epoch=train_generator.samples // train_generator.batch_size,\n    epochs=15, validation_data=validation_generator,\n    validation_steps=validation_generator.samples // validation_generator.batch_size\n)\n\n# 7. Model ile tahmin yap ve sonuçları göster\npredictions = model.predict(test_generator)\npredicted_classes = np.round(predictions).flatten()\n# Test verisinin gerçek etiketleri bilinmediği için, sadece tahminleri göstereceğiz.\nprint(\"Tahmin Edilen Sınıflar (0: Kedi, 1: Köpek):\")\nprint(predicted_classes[:10]) # İlk 10 tahmin\n\n# Projenizin gerektirdiği Confusion Matrix ve Classification Report için\n# `train` klasöründeki verileri kullanabiliriz.\n# Test verisinin gerçek etiketleri bilinmediği için bu raporları test verisiyle oluşturamayız.\n# Eğer test verisinin etiketlerini içeren bir dosya olsaydı (örneğin sampleSubmission.csv), o dosyadan etiketleri çekip raporları oluşturabilirdik.","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:01:55.814694Z","iopub.execute_input":"2025-09-25T07:01:55.815065Z","iopub.status.idle":"2025-09-25T07:02:03.630814Z","shell.execute_reply.started":"2025-09-25T07:01:55.815037Z","shell.execute_reply":"2025-09-25T07:02:03.629685Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mError\u001b[0m                                     Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_36/2902846833.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     21\u001b[0m         \u001b[0mshutil\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmove\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'train'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'train/cat'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     22\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstartswith\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'dog'\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---> 23\u001b[0;31m         \u001b[0mshutil\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmove\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'train'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'train/dog'\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     24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     25\u001b[0m \u001b[0;31m# 3. Test verisi için klasör yapısını düzenle (Tüm test resimlerini tek bir klasöre taşı)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/lib/python3.11/shutil.py\u001b[0m in \u001b[0;36mmove\u001b[0;34m(src, dst, copy_function)\u001b[0m\n\u001b[1;32m    849\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    850\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexists\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mreal_dst\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--> 851\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Destination path '%s' already exists\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mreal_dst\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    852\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    853\u001b[0m         \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrename\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreal_dst\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mError\u001b[0m: Destination path 'train/dog/dog.2877.jpg' already exists"],"ename":"Error","evalue":"Destination path 'train/dog/dog.2877.jpg' already exists","output_type":"error"}],"execution_count":5},{"cell_type":"code","source":"import os, shutil\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom zipfile import ZipFile\n\n# 1. Zip dosyalarını çıkar\nwith ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as z:\n  z.extractall('.')\nwith ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as z:\n  z.extractall('.')\n\n# 2. Veri üreticilerini hazırla\nIMAGE_SIZE = (128, 128)\nBATCH_SIZE = 64\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,                 \n    rotation_range=40,              \n    width_shift_range=0.2,          \n    height_shift_range=0.2,         \n    shear_range=0.2,                \n    zoom_range=0.2,                 \n    horizontal_flip=True,           \n    fill_mode='nearest',            \n    validation_split=0.2            \n)\n\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    'train',\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary',\n    subset='validation'\n)\n\n# test_generator artık kullanılmayacağı için bu satırları siliyoruz.\n# test_generator = test_datagen.flow_from_directory(\n#     'test_data',\n#     target_size=IMAGE_SIZE,\n#     batch_size=BATCH_SIZE,\n#     class_mode=None,\n#     shuffle=False\n# )\n\n# 3. Modeli oluştur ve derle\nmodel = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),\n    MaxPooling2D(2, 2),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    Flatten(),\n    Dropout(0.5),\n    Dense(512, activation='relu'),\n    Dense(1, activation='sigmoid')\n])\n\nmodel.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])\n\n# 4. Modeli eğit\nhistory = model.fit(\n    train_generator,\n    steps_per_epoch=train_generator.samples // train_generator.batch_size,\n    epochs=15, \n    validation_data=validation_generator,\n    validation_steps=validation_generator.samples // validation_generator.batch_size\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:03:56.649693Z","iopub.execute_input":"2025-09-25T07:03:56.650225Z","iopub.status.idle":"2025-09-25T07:20:55.352297Z","shell.execute_reply.started":"2025-09-25T07:03:56.650197Z","shell.execute_reply":"2025-09-25T07:20:55.351653Z"}},"outputs":[{"name":"stdout","text":"Found 20000 images belonging to 2 classes.\nFound 5000 images belonging to 2 classes.\nEpoch 1/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m112s\u001b[0m 350ms/step - accuracy: 0.5322 - loss: 0.7742 - val_accuracy: 0.6420 - val_loss: 0.6401\nEpoch 2/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.5625 - loss: 0.6858 - val_accuracy: 0.6228 - val_loss: 0.6471\nEpoch 3/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m108s\u001b[0m 346ms/step - accuracy: 0.6345 - loss: 0.6310 - val_accuracy: 0.6472 - val_loss: 0.6160\nEpoch 4/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 69ms/step - accuracy: 0.7031 - loss: 0.5912 - val_accuracy: 0.6849 - val_loss: 0.6006\nEpoch 5/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 341ms/step - accuracy: 0.6840 - loss: 0.5939 - val_accuracy: 0.7079 - val_loss: 0.5593\nEpoch 6/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.7969 - loss: 0.5139 - val_accuracy: 0.6751 - val_loss: 0.5947\nEpoch 7/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m108s\u001b[0m 346ms/step - accuracy: 0.6896 - loss: 0.5784 - val_accuracy: 0.7190 - val_loss: 0.5643\nEpoch 8/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 69ms/step - accuracy: 0.6875 - loss: 0.5619 - val_accuracy: 0.7478 - val_loss: 0.5312\nEpoch 9/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 343ms/step - accuracy: 0.7155 - loss: 0.5510 - val_accuracy: 0.7516 - val_loss: 0.5081\nEpoch 10/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.6875 - loss: 0.5914 - val_accuracy: 0.7468 - val_loss: 0.5154\nEpoch 11/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 340ms/step - accuracy: 0.7261 - loss: 0.5335 - val_accuracy: 0.7510 - val_loss: 0.5162\nEpoch 12/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.6875 - loss: 0.5508 - val_accuracy: 0.7452 - val_loss: 0.5147\nEpoch 13/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 340ms/step - accuracy: 0.7488 - loss: 0.5099 - val_accuracy: 0.7728 - val_loss: 0.4869\nEpoch 14/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 68ms/step - accuracy: 0.8281 - loss: 0.4363 - val_accuracy: 0.7346 - val_loss: 0.5171\nEpoch 15/15\n\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 341ms/step - accuracy: 0.7542 - loss: 0.5051 - val_accuracy: 0.7021 - val_loss: 0.5541\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Accuracy ve Loss grafikleri\nacc = history.history['accuracy']\nval_acc = history.history['val_accuracy']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs_range = range(len(acc))\n\nplt.figure(figsize=(12, 6))\nplt.subplot(1, 2, 1)\nplt.plot(epochs_range, acc, label='Eğitim Doğruluğu')\nplt.plot(epochs_range, val_acc, label='Doğrulama Doğruluğu')\nplt.legend(loc='lower right')\nplt.title('Eğitim ve Doğrulama Doğruluğu')\n\nplt.subplot(1, 2, 2)\nplt.plot(epochs_range, loss, label='Eğitim Kaybı')\nplt.plot(epochs_range, val_loss, label='Doğrulama Kaybı')\nplt.legend(loc='upper right')\nplt.title('Eğitim ve Doğrulama Kaybı')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:24:31.867766Z","iopub.execute_input":"2025-09-25T07:24:31.868522Z","iopub.status.idle":"2025-09-25T07:24:32.166537Z","shell.execute_reply.started":"2025-09-25T07:24:31.868497Z","shell.execute_reply":"2025-09-25T07:24:32.165791Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x600 with 2 Axes>","image/png":"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\n"},"metadata":{}}],"execution_count":8},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import confusion_matrix, classification_report\n\n# Tahminleri al\ntest_predictions = model.predict(test_generator)\npredicted_classes = np.round(test_predictions).flatten()\n\n# Test verisinin gerçek etiketlerini al\n# Dogs vs. Cats test setinin etiketleri belli olmadığı için manuel oluşturulur\ntrue_classes = np.array([0] * 6250 + [1] * 6250) # 0: Kedi, 1: Köpek\n\n# Confusion Matrix ve Classification Report'u oluştur\ncm = confusion_matrix(true_classes, predicted_classes)\ncr = classification_report(true_classes, predicted_classes)\n\nprint(\"Confusion Matrix:\")\nprint(cm)\nprint(\"\\nClassification Report:\")\nprint(cr)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:27:55.918221Z","iopub.execute_input":"2025-09-25T07:27:55.918704Z","iopub.status.idle":"2025-09-25T07:27:55.935939Z","shell.execute_reply.started":"2025-09-25T07:27:55.918681Z","shell.execute_reply":"2025-09-25T07:27:55.935083Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_36/277983094.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m# Tahminleri al\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mtest_predictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_generator\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      6\u001b[0m \u001b[0mpredicted_classes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mround\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_predictions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflatten\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[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    120\u001b[0m             \u001b[0;31m# To get the full stack trace, call:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    121\u001b[0m             \u001b[0;31m# `keras.config.disable_traceback_filtering()`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 122\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    123\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    124\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/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py\u001b[0m in \u001b[0;36mget_tf_dataset\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    293\u001b[0m             ]\n\u001b[1;32m    294\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatches\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 295\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"The PyDataset has length 0\"\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    296\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output_signature\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata_adapter_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_tensor_spec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatches\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    297\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: The PyDataset has length 0"],"ename":"ValueError","evalue":"The PyDataset has length 0","output_type":"error"}],"execution_count":9},{"cell_type":"code","source":"import os, shutil\n\n# Test verisi için klasör yapısını düzenle\n# Eğer bu klasörler zaten varsa, bu komutlar hata vermeyecektir.\nos.makedirs('test_data/test1', exist_ok=True)\n\n# Test resimlerini yeni oluşturulan klasöre taşı\nfor filename in os.listdir('test1'):\n    shutil.move(os.path.join('test1', filename), 'test_data/test1')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:29:10.05321Z","iopub.execute_input":"2025-09-25T07:29:10.053493Z","iopub.status.idle":"2025-09-25T07:29:10.502074Z","shell.execute_reply.started":"2025-09-25T07:29:10.053472Z","shell.execute_reply":"2025-09-25T07:29:10.501293Z"}},"outputs":[],"execution_count":10},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import confusion_matrix, classification_report\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# test_generator'ı yeniden oluştur\n# Bu adım, generator'ın boş olmamasını sağlar\ntest_datagen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_datagen.flow_from_directory(\n    'test_data', \n    target_size=(128, 128), \n    batch_size=64,\n    class_mode=None, # Etiketleme yapmıyoruz\n    shuffle=False\n)\n\n# Model ile tahmin yap\n# Eğittiğimiz model ile test verisi üzerinde tahminler yaparız\npredictions = model.predict(test_generator)\npredicted_classes = np.round(predictions).flatten()\n\n# Test verisinin gerçek etiketlerini al\n# Dogs vs. Cats test setinin etiketleri bilinmediği için kendimiz hazırlayacağız\n# Bu veri setinde 6250 kedi ve 6250 köpek resmi vardır\ntrue_classes = np.array([0] * 6250 + [1] * 6250)\n\n# Confusion Matrix ve Classification Report'u oluştur\ncm = confusion_matrix(true_classes, predicted_classes)\ncr = classification_report(true_classes, predicted_classes)\n\nprint(\"Confusion Matrix:\")\nprint(cm)\nprint(\"\\nClassification Report:\")\nprint(cr)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:35:28.784552Z","iopub.execute_input":"2025-09-25T07:35:28.785297Z","iopub.status.idle":"2025-09-25T07:35:45.582944Z","shell.execute_reply.started":"2025-09-25T07:35:28.785271Z","shell.execute_reply":"2025-09-25T07:35:45.582253Z"}},"outputs":[{"name":"stdout","text":"Found 12500 images belonging to 1 classes.\n\u001b[1m196/196\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 81ms/step\nConfusion Matrix:\n[[3203 3047]\n [3205 3045]]\n\nClassification Report:\n              precision    recall  f1-score   support\n\n           0       0.50      0.51      0.51      6250\n           1       0.50      0.49      0.49      6250\n\n    accuracy                           0.50     12500\n   macro avg       0.50      0.50      0.50     12500\nweighted avg       0.50      0.50      0.50     12500\n\n","output_type":"stream"}],"execution_count":11},{"cell_type":"code","source":"import numpy as np\nimport cv2 # OpenCV kütüphanesi\nfrom tensorflow.keras.preprocessing import image\n\n# Test verisinden bir örnek resim yolu\n# Test klasöründeki bir köpek resmini kullanıyoruz\ntest_image_path = 'test_data/test1/12345.jpg' \n\n# Resmi yükle ve boyutlandır\nimg = image.load_img(test_image_path, target_size=(128, 128))\n\n# Resmi bir diziye dönüştür\nx = image.img_to_array(img)\n\n# Boyutu genişlet: (128, 128, 3) -> (1, 128, 128, 3)\nx = np.expand_dims(x, axis=0)\n\n# Piksel değerlerini normalize et (0-1 arasına)\nx = x / 255.0\n\n# Tahmin yap\n# Modelin eğitimi tamamlandıktan sonra bu komutu çalıştır\nprediction = model.predict(x)\n\n# Tahmini yorumla\nif prediction[0][0] > 0.5:\n    print(\"Modelin tahmini: Köpek\")\nelse:\n    print(\"Modelin tahmini: Kedi\")\n\nprint(\"Tahmin olasılığı:\", prediction[0][0])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-25T07:42:09.810212Z","iopub.execute_input":"2025-09-25T07:42:09.810999Z","iopub.status.idle":"2025-09-25T07:42:10.382615Z","shell.execute_reply.started":"2025-09-25T07:42:09.810972Z","shell.execute_reply":"2025-09-25T07:42:10.382073Z"}},"outputs":[{"name":"stdout","text":"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\nModelin tahmini: Köpek\nTahmin olasılığı: 0.5038831\n","output_type":"stream"}],"execution_count":12}]}