Closed nspope closed 2 years ago
Hi, thanks for developing this intuitive and useful tool.
With python 3.69, tensorflow 1.14.0, keras 2.3.1: weights from the trained model are not saved. This is fixed by changing monitor = 'val_acc' to monitor = 'val_accuracy' at:
python 3.69
tensorflow 1.14.0
keras 2.3.1
monitor = 'val_acc'
monitor = 'val_accuracy'
https://github.com/kern-lab/diploSHIC/blob/7d55417af438e321c374dadc2f7e58f56107443e/diploSHIC.py#L250
For early stopping to work, the same change needs to made at:
https://github.com/kern-lab/diploSHIC/blob/7d55417af438e321c374dadc2f7e58f56107443e/diploSHIC.py#L243
Perhaps due to a recent change in keras or documentation thereof? (See https://github.com/tensorflow/tensorflow/issues/33163)
Nate
sorry just seeing this issue? is this still affecting things?
closing this issue as it seems stale. feel free to reopen
Hi, thanks for developing this intuitive and useful tool.
With
python 3.69
,tensorflow 1.14.0
,keras 2.3.1
: weights from the trained model are not saved. This is fixed by changingmonitor = 'val_acc'
tomonitor = 'val_accuracy'
at:https://github.com/kern-lab/diploSHIC/blob/7d55417af438e321c374dadc2f7e58f56107443e/diploSHIC.py#L250
For early stopping to work, the same change needs to made at:
https://github.com/kern-lab/diploSHIC/blob/7d55417af438e321c374dadc2f7e58f56107443e/diploSHIC.py#L243
Perhaps due to a recent change in keras or documentation thereof? (See https://github.com/tensorflow/tensorflow/issues/33163)
Nate