Closed Lobotomy92 closed 5 years ago
In line 173 the m is computed as m = math.ceil(len(testset) / cf.batch_size) However, it is in the training function, should it be len(trainset)? Because usually the test set should not be seen in the training phase.
Hi @Lobotomy92 ,
It was a typo in the latest commit. Thanks for raising the issue. Noted and changed.
In line 173 the m is computed as m = math.ceil(len(testset) / cf.batch_size) However, it is in the training function, should it be len(trainset)? Because usually the test set should not be seen in the training phase.