The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf
Hello, when reproducing your code, the results printed out include the top-1 and top-5 accuracies for each epoch, is this the accuracy of the student network or the teacher network or the distilled student network? At the end, a best_acc is also given, whose best_acc is this result?I would be grateful for your reply.
Hello, when reproducing your code, the results printed out include the top-1 and top-5 accuracies for each epoch, is this the accuracy of the student network or the teacher network or the distilled student network? At the end, a best_acc is also given, whose best_acc is this result?I would be grateful for your reply.