Fashion_CNN_Model

• The CNN models were fine-tuned to achieve the highest possible accuracy of 96% in predicting labels for a fashion collection dataset. After evaluation, the best performing model was selected for further analysis. • An Intermediate layer of a deep learning model was used to extract encoding features from a dataset of fashion items. The extracted features were then used to apply clustering and visualization techniques, including PCA, DBSCAN, K-means, and t-SNE, to identify patterns and relationships within the dataset and determine the appropriate labels for each item.