AdaBound-Tensorflow
AdaBound-Tensorflow copied to clipboard
In line 85, beta power1 is None type, causing errors.
beta1_power = math_ops.cast(self._get_non_slot_variable("beta1_power", graph=graph), var.dtype.base_dtype)
No configuration changes on my end, throwing an error that beta power1 is None.
Looks like at some point eager execution is getting turned off. Not sure why though...