{"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":3649,"databundleVersionId":46718,"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":"2024-09-13T08:10:05.387665Z","iopub.execute_input":"2024-09-13T08:10:05.388130Z","iopub.status.idle":"2024-09-13T08:10:05.873947Z","shell.execute_reply.started":"2024-09-13T08:10:05.388085Z","shell.execute_reply":"2024-09-13T08:10:05.872492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Importamos las librerías necesarias\nimport tensorflow as tf\nfrom tensorflow.keras import layers, models\nfrom tensorflow.keras.applications import VGG16\nimport matplotlib.pyplot as plt\n\n#Cargar el dataset CIFAR-10\n(X_train, y_train), (X_test, y_test) = tf.keras.datasets.cifar10.load_data()\n\n#Clases de CIFAR-10\nclass_names = ['Avión', 'Automóvil', 'Pájaro', 'Gato', 'Ciervo', \n               'Perro', 'Rana', 'Caballo', 'Barco', 'Camión']\n\n#Normalizar los valores de las imágenes entre 0 y 1\nX_train, X_test = X_train / 255.0, X_test / 255.0\n\n#Visualización de 5 imágenes con sus etiquetas\ndef visualizar_imagenes(X, y, class_names, num_imagenes=5):\n    plt.figure(figsize=(10, 2))\n    for i in range(num_imagenes):\n        plt.subplot(1, num_imagenes, i+1)\n        plt.imshow(X[i])\n        plt.title(class_names[y[i][0]])\n        plt.axis('off')\n    plt.show()\n\nvisualizar_imagenes(X_train, y_train, class_names)\n\n#Cargar el modelo VGG16 preentrenado con los pesos de ImageNet\n#y sacar la capa superior (include_top=False)\nbase_model = VGG16(weights='imagenet', include_top=False, input_shape=(32, 32, 3))\n\n#Congelar las capas convolucionales del modelo base (no se entrenarán)\nbase_model.trainable = False\n\n#Crear el modelo añadiendo capas propias encima del VGG16\nmodel = models.Sequential([\n    base_model,  # Modelo VGG16 preentrenado\n    layers.Flatten(),  # Aplanar las características\n    layers.Dense(256, activation='relu'),  # Capa densa añadida\n    layers.Dropout(0.5),  # Regularización para evitar overfitting\n    layers.Dense(10, activation='softmax')  # Capa de salida para clasificación en 10 clases\n])\n\n#Compilar el modelo con optimizador Adam y entropía cruzada categórica\nmodel.compile(optimizer='adam',\n              loss='sparse_categorical_crossentropy',\n              metrics=['accuracy'])\n\n#Entrenar el modelo\nhistory = model.fit(X_train, y_train, epochs=10, \n                    validation_data=(X_test, y_test))\n\n#Evaluar el modelo en el conjunto de prueba\ntest_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)\nprint(f'\\nPrecisión en el conjunto de prueba: {test_acc:.2f}')\n\n#Visualizar los resultados de entrenamiento\nplt.plot(history.history['accuracy'], label='Precisión de entrenamiento')\nplt.plot(history.history['val_accuracy'], label='Precisión de validación')\nplt.xlabel('Época')\nplt.ylabel('Precisión')\nplt.legend(loc='lower right')\nplt.show()\n\n","metadata":{"execution":{"iopub.status.busy":"2024-09-13T08:11:15.348051Z","iopub.execute_input":"2024-09-13T08:11:15.348691Z","iopub.status.idle":"2024-09-13T09:13:50.284228Z","shell.execute_reply.started":"2024-09-13T08:11:15.348643Z","shell.execute_reply":"2024-09-13T09:13:50.282916Z"},"trusted":true},"execution_count":null,"outputs":[]}]}