Portfolio

Overview:

This project focuses on music labeling by predicting music categories based on audio data. The model is built using a neural network with specific layers, including ReLU and Sigmoid activation functions, to classify the music genres effectively. The model is trained over 300 epochs with a batch size of 50.

Screenshots

Key Features:

1. Neural Network Architecture:

The model uses layers with ReLU and Sigmoid activation functions to classify audio data into music categories. Dense(512) units provide complexity, while Dropout(0.5) helps prevent overfitting by randomly dropping units during training.

2. Training Process:

The model is trained over 300 epochs with a batch size of 50, which balances the computational load and ensures the model learns from sufficient iterations of the dataset.

3. Performance Metrics:

Accuracy and loss are measured for both training and test datasets to evaluate model performance and avoid overfitting.

4. Model Validation:

After training, the model is validated to ensure that it can generalize well to unseen audio data, measuring both accuracy and loss.

Category:

Tags:

Links:

• GitHub