{"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":30786,"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":"2024-10-28T05:52:59.611564Z","iopub.execute_input":"2024-10-28T05:52:59.611999Z","iopub.status.idle":"2024-10-28T05:53:00.08266Z","shell.execute_reply.started":"2024-10-28T05:52:59.611956Z","shell.execute_reply":"2024-10-28T05:53:00.08134Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/cifar-10/trainLabels.csv\n/kaggle/input/cifar-10/sampleSubmission.csv\n/kaggle/input/cifar-10/test.7z\n/kaggle/input/cifar-10/train.7z\n","output_type":"stream"}]},{"cell_type":"code","source":"# Import libraries for building and training the model\nimport tensorflow as tf\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom tensorflow.keras.applications import MobileNet\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\nimport matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:00.084168Z","iopub.execute_input":"2024-10-28T05:53:00.08472Z","iopub.status.idle":"2024-10-28T05:53:03.913077Z","shell.execute_reply.started":"2024-10-28T05:53:00.084674Z","shell.execute_reply":"2024-10-28T05:53:03.911833Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"# Load CIFAR-10 dataset\n(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:03.914826Z","iopub.execute_input":"2024-10-28T05:53:03.915523Z","iopub.status.idle":"2024-10-28T05:53:04.885681Z","shell.execute_reply.started":"2024-10-28T05:53:03.915478Z","shell.execute_reply":"2024-10-28T05:53:04.884242Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"# Normalize the pixel values to the range [0, 1]\nx_train, x_test = x_train / 255.0, x_test / 255.0","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:04.888948Z","iopub.execute_input":"2024-10-28T05:53:04.889378Z","iopub.status.idle":"2024-10-28T05:53:05.410011Z","shell.execute_reply.started":"2024-10-28T05:53:04.889336Z","shell.execute_reply":"2024-10-28T05:53:05.40855Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"# Convert labels to categorical (one-hot encoding)\ny_train = tf.keras.utils.to_categorical(y_train, 10)\ny_test = tf.keras.utils.to_categorical(y_test, 10)","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:05.411589Z","iopub.execute_input":"2024-10-28T05:53:05.412048Z","iopub.status.idle":"2024-10-28T05:53:05.423Z","shell.execute_reply.started":"2024-10-28T05:53:05.412004Z","shell.execute_reply":"2024-10-28T05:53:05.421701Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"# Define a function to create the model with modifications\ndef create_modified_mobilenet(dropout_rate=0.5):\n    # Load the base MobileNet model without the top layers\n    base_model = MobileNet(input_shape=(32, 32, 3), include_top=False, weights=None)\n    x = base_model.output\n    x = GlobalAveragePooling2D()(x)\n    x = Dropout(dropout_rate)(x)  # Added dropout layer\n    x = Dense(128, activation='relu')(x)  # Added dense layer with 128 units\n    x = Dropout(dropout_rate)(x)  # Second dropout layer\n    predictions = Dense(10, activation='softmax')(x)  # Output layer for 10 classes\n    model = Model(inputs=base_model.input, outputs=predictions)\n    return model","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:05.424659Z","iopub.execute_input":"2024-10-28T05:53:05.425477Z","iopub.status.idle":"2024-10-28T05:53:05.434084Z","shell.execute_reply.started":"2024-10-28T05:53:05.425421Z","shell.execute_reply":"2024-10-28T05:53:05.432783Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"# Define hyperparameters for tuning\nlearning_rates = [0.001, 0.0001, 0.00001]\nbatch_sizes = [32, 64]\nepochs = 5","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:05.43557Z","iopub.execute_input":"2024-10-28T05:53:05.436064Z","iopub.status.idle":"2024-10-28T05:53:05.449048Z","shell.execute_reply.started":"2024-10-28T05:53:05.436015Z","shell.execute_reply":"2024-10-28T05:53:05.447486Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"# Train and evaluate the model with different hyperparameters\nfor lr in learning_rates:\n    for batch_size in batch_sizes:\n        print(f\"\\nTraining with learning rate={lr}, batch size={batch_size}\")","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:05.450758Z","iopub.execute_input":"2024-10-28T05:53:05.451281Z","iopub.status.idle":"2024-10-28T05:53:05.463599Z","shell.execute_reply.started":"2024-10-28T05:53:05.451223Z","shell.execute_reply":"2024-10-28T05:53:05.462065Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stdout","text":"\nTraining with learning rate=0.001, batch size=32\n\nTraining with learning rate=0.001, batch size=64\n\nTraining with learning rate=0.0001, batch size=32\n\nTraining with learning rate=0.0001, batch size=64\n\nTraining with learning rate=1e-05, batch size=32\n\nTraining with learning rate=1e-05, batch size=64\n","output_type":"stream"}]},{"cell_type":"code","source":"# Create and compile the model\nmodel = create_modified_mobilenet(dropout_rate=0.5)\nmodel.compile(optimizer=Adam(learning_rate=lr), loss='categorical_crossentropy', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:05.465244Z","iopub.execute_input":"2024-10-28T05:53:05.465686Z","iopub.status.idle":"2024-10-28T05:53:06.139888Z","shell.execute_reply.started":"2024-10-28T05:53:05.465601Z","shell.execute_reply":"2024-10-28T05:53:06.138535Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"# Early stopping to prevent overfitting\nearly_stopping = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:06.141488Z","iopub.execute_input":"2024-10-28T05:53:06.142018Z","iopub.status.idle":"2024-10-28T05:53:06.148973Z","shell.execute_reply.started":"2024-10-28T05:53:06.141955Z","shell.execute_reply":"2024-10-28T05:53:06.14754Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"# Train the model\nhistory = model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(x_test, y_test), callbacks=[early_stopping],verbose=2)","metadata":{"execution":{"iopub.status.busy":"2024-10-28T05:53:06.15098Z","iopub.execute_input":"2024-10-28T05:53:06.151501Z","iopub.status.idle":"2024-10-28T06:23:36.490566Z","shell.execute_reply.started":"2024-10-28T05:53:06.151433Z","shell.execute_reply":"2024-10-28T06:23:36.489015Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"Epoch 1/5\n782/782 - 375s - 480ms/step - accuracy: 0.1036 - loss: 3.0380 - val_accuracy: 0.1061 - val_loss: 2.3372\nEpoch 2/5\n782/782 - 360s - 461ms/step - accuracy: 0.1119 - loss: 2.6413 - val_accuracy: 0.1284 - val_loss: 2.2892\nEpoch 3/5\n782/782 - 356s - 455ms/step - accuracy: 0.1150 - loss: 2.4805 - val_accuracy: 0.1313 - val_loss: 2.2801\nEpoch 4/5\n782/782 - 382s - 489ms/step - accuracy: 0.1174 - loss: 2.3953 - val_accuracy: 0.1284 - val_loss: 2.2788\nEpoch 5/5\n782/782 - 355s - 455ms/step - accuracy: 0.1217 - loss: 2.3524 - val_accuracy: 0.1302 - val_loss: 2.2806\n","output_type":"stream"}]},{"cell_type":"code","source":" # Plot training and validation accuracy for each configuration\nplt.plot(history.history['accuracy'], label='train accuracy')\nplt.plot(history.history['val_accuracy'], label='val accuracy')\nplt.title(f'Learning Rate={lr}, Batch Size={batch_size}')\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-10-28T06:23:36.492828Z","iopub.execute_input":"2024-10-28T06:23:36.49332Z","iopub.status.idle":"2024-10-28T06:23:36.896119Z","shell.execute_reply.started":"2024-10-28T06:23:36.493274Z","shell.execute_reply":"2024-10-28T06:23:36.894851Z"},"trusted":true},"execution_count":12,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"# Evaluate the model on the test set\ntest_loss, test_acc = model.evaluate(x_test, y_test, verbose=0)\nprint(f\"Test Accuracy with learning rate={lr}, batch size={batch_size}: {test_acc:.4f}\")","metadata":{"execution":{"iopub.status.busy":"2024-10-28T06:23:36.900124Z","iopub.execute_input":"2024-10-28T06:23:36.900646Z","iopub.status.idle":"2024-10-28T06:23:44.021678Z","shell.execute_reply.started":"2024-10-28T06:23:36.900581Z","shell.execute_reply":"2024-10-28T06:23:44.020434Z"},"trusted":true},"execution_count":13,"outputs":[{"name":"stdout","text":"Test Accuracy with learning rate=1e-05, batch size=64: 0.1284\n","output_type":"stream"}]}]}