3 Commits (d9932c08b5108989f94ca1029a439d2487d1f3b3)

Author	SHA1	Message	Date
Francisco Massa	8eae3269da	Add Knowledge-Distillation (#42) ... * Add knowledge distillation * Bugfix * Bugfix * Make names more readable and use single torch.cat call * Remove criterion.train() in engine The teacher should stay in eval mode * Change default argument for teacher-model * Return the average of classifiers during inference * Cleanup unused code * Add docstring for DistillationLoss * Remove warnings from newer PyTorch Also uses more stable variant, instead of using softmax + log, use directly log_softmax	2021-01-13 14:19:23 +01:00
Francisco Massa	0c4b8f60bd	Change LICENSE to Apache 2.0	2021-01-08 10:51:58 +01:00
Francisco Massa	1d38fa4c37	Initial commit	2020-12-23 10:47:58 -08:00