Closed ig248 closed 3 years ago
Before this change, training with epochs=0 (valid in keras and useful for getting a loss baseline/debugging) would lead to errors in the HistoryLogger.
epochs=0
After this change, suitable defaults are substituted.
Before this change, training with
epochs=0
(valid in keras and useful for getting a loss baseline/debugging) would lead to errors in the HistoryLogger.After this change, suitable defaults are substituted.