GitHub / iuliaoltean11 / Catastrophic-Forgetting-in-Incremental-Learning-using-Unlabeled-Data

The project leverages a pre-trained teacher model (SimpleCNN) to guide the training of a student model (CTNet). The training process combines cross-entropy loss for true labels with KL divergence loss for soft targets provided by the teacher model.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iuliaoltean11%2FCatastrophic-Forgetting-in-Incremental-Learning-using-Unlabeled-Data

Topics: incremental-learning, python, torch

• Files
• Readme
• Dependencies