Feature request add an option to pass activation function to TTA
ternaus opened this issue · 1 comments
ternaus commented
https://github.com/BloodAxe/pytorch-toolbelt/blob/develop/pytorch_toolbelt/inference/tta.py#L135
In many cases averaging logits works worse than averaging probabilities => would be nice to be able to pass user-defined activation function. For example softmax or sigmoid.
ternaus commented
A better option would be to apply desired functions on the model itself: