Closed ismael-elatifi closed 4 years ago
Hello, thank you for the comment. I think it is just a different logic for loss extraction. Our implementation is a little bit different than the original bootstrap loss. Here is our logic:
Ok I see, my bad. So indeed it is not a bug. I close the issue which is actually not one :-)
In loss.py in function _bootstrap_xentropy_single, there is a bug in the following code portion :
Because with your current code, if the Kth loss value is below threshold it will be kept (else clause), whereas you don't want that.