Dataset and Code for Fine-tuning Neural Networks via Transfer Learning on Image Classification Tasks

This dataset contains results from experiments where transfer learning was applied to neural network models pre-trained on the ImageNet dataset. The final fully connected layer of 1000 units was replaced with an 8-unit layer to fit the specific classification tasks in this study. The models were fine-tuned with a custom dataset to optimize performance for categorization, while core layers remained unchanged. Fine-tuning was conducted across the network based on the configurations of pre-existing model parameters. This process aimed at enhancing the model's adaptability for specialized tasks.