Open shasso2s opened 1 year ago
Hi there,
I assume you mean https://github.com/YuanGongND/ast/blob/3f53567ed2aa9bf9305eb89f86dbbef17343695a/src/traintest.py#L311-L327
Please refer to this paper, Section VI.B.1 Checkpoint Averaging. This function implement the above algorithm that 1) save checkpoint model of every epoch (or start from a specific epoch), 2) use each model checkpoint to do an inference on the data, and 3) average the prediction of each check point model. For this, you don't need to train multiple times, but just train once and ensemble the checkpoint models. Note: though it saves training cost compared with normal ensemble, it performs worse. See the above paper for details.
-Yuan
hallo , i don't understand this method(validate_ensemble(args, epoch):) can you plz explain it to me