{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30761,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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","execution":{"iopub.status.busy":"2024-09-12T14:10:49.738577Z","iopub.execute_input":"2024-09-12T14:10:49.739121Z","iopub.status.idle":"2024-09-12T14:10:50.232310Z","shell.execute_reply.started":"2024-09-12T14:10:49.739056Z","shell.execute_reply":"2024-09-12T14:10:50.230920Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\nimport shutil\n\n# Descomprime los archivos de entrenamiento y prueba\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/train')\n\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/test')\n\n# Lista los primeros archivos de entrenamiento\ntrain_dir = '/kaggle/working/train/train/'\ntrain_files = os.listdir(train_dir)\nprint(train_files[:10])  # Muestra los primeros 10 archivos","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:11:28.995288Z","iopub.execute_input":"2024-09-12T14:11:28.995901Z","iopub.status.idle":"2024-09-12T14:11:46.094413Z","shell.execute_reply.started":"2024-09-12T14:11:28.995848Z","shell.execute_reply":"2024-09-12T14:11:46.093354Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport cv2\n\n# Crear listas para almacenar las rutas de las imágenes y las etiquetas\nimage_paths = []\nlabels = []\n\n# Recorrer los archivos y asignar etiquetas\nfor file in os.listdir(train_dir):\n    if file.startswith('cat'):\n        labels.append('cat')\n    elif file.startswith('dog'):\n        labels.append('dog')\n    image_paths.append(os.path.join(train_dir, file))\n\n# Crear un DataFrame\ndf = pd.DataFrame({\n    'image_path': image_paths,\n    'label': labels\n})\n\n# Mostrar las primeras filas del DataFrame\nprint(df.head())\n\n# Función para mostrar algunas imágenes aleatorias\ndef show_images(df, num_images=5):\n    plt.figure(figsize=(15, 5))\n    for i in range(num_images):\n        img_path = df.sample(1).iloc[0]['image_path']\n        img = cv2.imread(img_path)\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n        plt.subplot(1, num_images, i + 1)\n        plt.imshow(img)\n        plt.title(img_path.split('/')[-1])\n        plt.axis('off')\n    plt.show()\n\n# Visualizar 5 imágenes aleatorias\nshow_images(df, num_images=5)","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:11:51.810192Z","iopub.execute_input":"2024-09-12T14:11:51.810624Z","iopub.status.idle":"2024-09-12T14:11:53.232847Z","shell.execute_reply.started":"2024-09-12T14:11:51.810582Z","shell.execute_reply":"2024-09-12T14:11:53.231637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# División de los datos en entrenamiento (80%) y validación (20%)\ntrain_df, val_df = train_test_split(df, test_size=0.2, stratify=df['label'], random_state=42)\n\n# Parámetros básicos\nimg_height, img_width = 100, 100  # Tamaño de las imágenes\nbatch_size = 16  # Tamaño del lote para la red neuronal\n\n# Crear generadores de imágenes para entrenamiento y validación\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,             # Normalización de las imágenes\n    rotation_range=20,          # Rotación aleatoria de las imágenes\n    width_shift_range=0.2,      # Desplazamiento horizontal\n    height_shift_range=0.2,     # Desplazamiento vertical\n    shear_range=0.2,            # Transformación de corte\n    zoom_range=0.2,             # Zoom aleatorio\n    horizontal_flip=True,       # Inversión horizontal\n    fill_mode='nearest'         # Estrategia de relleno\n)\n\nval_datagen = ImageDataGenerator(rescale=1./255)  # Solo normalización\n\n# Crear flujos de datos para las imágenes de entrenamiento y validación\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df,\n    x_col='image_path',\n    y_col='label',\n    target_size=(img_height, img_width),\n    batch_size=batch_size,\n    class_mode='binary'\n)\n\nval_generator = val_datagen.flow_from_dataframe(\n    val_df,\n    x_col='image_path',\n    y_col='label',\n    target_size=(img_height, img_width),\n    batch_size=batch_size,\n    class_mode='binary'\n)","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:12:19.083053Z","iopub.execute_input":"2024-09-12T14:12:19.083511Z","iopub.status.idle":"2024-09-12T14:12:36.339256Z","shell.execute_reply.started":"2024-09-12T14:12:19.083466Z","shell.execute_reply":"2024-09-12T14:12:36.337671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom tensorflow.keras.optimizers import Adam\n\n# Definir el modelo CNN\nmodel = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Flatten(),\n    Dense(512, activation='relu'),\n    Dropout(0.5),\n    Dense(1, activation='sigmoid')  # Salida binaria\n])\n\n# Compilar el modelo\nmodel.compile(\n    optimizer=Adam(learning_rate=0.001),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\n# Entrenar el modelo\nhistory = model.fit(\n    train_generator,\n    steps_per_epoch=train_generator.samples // batch_size,\n    epochs=1,\n    validation_data=val_generator,\n    validation_steps=val_generator.samples // batch_size\n)\n\n# Guardar el modelo\nmodel.save('model_dogs_vs_cats.h5')","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:12:54.266283Z","iopub.execute_input":"2024-09-12T14:12:54.267071Z","iopub.status.idle":"2024-09-12T14:17:42.485569Z","shell.execute_reply.started":"2024-09-12T14:12:54.267022Z","shell.execute_reply":"2024-09-12T14:17:42.484075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport numpy as np\n\n# Evaluar el modelo en el conjunto de validación\nval_loss, val_accuracy = model.evaluate(val_generator, steps=val_generator.samples // batch_size)\nprint(f'Pérdida en validación: {val_loss:.4f}')\nprint(f'Precisión en validación: {val_accuracy:.4f}')\n\n# Visualizar las curvas de precisión y pérdida\ndef plot_training_history(history):\n    plt.figure(figsize=(12, 4))\n    \n    # Pérdida\n    plt.subplot(1, 2, 1)\n    plt.plot(history.history['loss'], label='Pérdida de Entrenamiento')\n    plt.plot(history.history['val_loss'], label='Pérdida de Validación')\n    plt.title('Pérdida durante el Entrenamiento')\n    plt.xlabel('Épocas')\n    plt.ylabel('Pérdida')\n    plt.legend()\n    \n    # Precisión\n    plt.subplot(1, 2, 2)\n    plt.plot(history.history['accuracy'], label='Precisión de Entrenamiento')\n    plt.plot(history.history['val_accuracy'], label='Precisión de Validación')\n    plt.title('Precisión durante el Entrenamiento')\n    plt.xlabel('Épocas')\n    plt.ylabel('Precisión')\n    plt.legend()\n    \n    plt.show()\n\nplot_training_history(history)\n\n# Realizar predicciones en nuevas imágenes\ndef predict_image(img_path):\n    img = cv2.imread(img_path)\n    img = cv2.resize(img, (img_height, img_width))\n    img = img.astype('float32') / 255  # Normalización\n    img = np.expand_dims(img, axis=0)  # Añadir dimensión de lote\n    \n    prediction = model.predict(img)\n    return 'dog' if prediction[0][0] > 0.5 else 'cat'","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:19:56.613304Z","iopub.execute_input":"2024-09-12T14:19:56.613795Z","iopub.status.idle":"2024-09-12T14:20:17.782000Z","shell.execute_reply.started":"2024-09-12T14:19:56.613746Z","shell.execute_reply":"2024-09-12T14:20:17.780642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir = '/kaggle/working/test/test1'\ntrain_files = os.listdir(train_dir)\nprint(train_files[:10]) ","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:20:40.747911Z","iopub.execute_input":"2024-09-12T14:20:40.748402Z","iopub.status.idle":"2024-09-12T14:20:40.767094Z","shell.execute_reply.started":"2024-09-12T14:20:40.748352Z","shell.execute_reply":"2024-09-12T14:20:40.765270Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\n# Carga la imagen\nimg = mpimg.imread('/kaggle/working/test/test1/4764.jpg')\n\n# Muestra la imagen\nplt.imshow(img)\nplt.axis('off')  # Opcional, para quitar los ejes\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:20:48.251811Z","iopub.execute_input":"2024-09-12T14:20:48.252307Z","iopub.status.idle":"2024-09-12T14:20:48.468449Z","shell.execute_reply.started":"2024-09-12T14:20:48.252259Z","shell.execute_reply":"2024-09-12T14:20:48.466880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Probar con una imagen de ejemplo\ntest_image_path = '/kaggle/working/test/test1/4764.jpg'  # Cambia esta ruta a una imagen de prueba\npredicted_label = predict_image(test_image_path)\nprint(f'La imagen es un: {predicted_label}')","metadata":{"execution":{"iopub.status.busy":"2024-09-12T14:21:03.041704Z","iopub.execute_input":"2024-09-12T14:21:03.042170Z","iopub.status.idle":"2024-09-12T14:21:03.226697Z","shell.execute_reply.started":"2024-09-12T14:21:03.042125Z","shell.execute_reply":"2024-09-12T14:21:03.225386Z"},"trusted":true},"execution_count":null,"outputs":[]}]}