Closed BraveDrXuTF closed 9 months ago
NotImplementedError: <tensorflow_addons.optimizers.weight_decay_optimizers.AdamW object at 0x00000136F434F6D0> to be implemented for backend tensorflow.compat.v1. in src\darcy_rectangular_pwc\deeponet.py.
model.compile( tfa.optimizers.AdamW(1e-4, learning_rate=3e-4), lr=3e-4, decay=("inverse time", 1, 1e-4), metrics=["mean l2 relative error"], )
where I have add lr=3e-4, if I use the original code
lr=3e-4
model.compile( tfa.optimizers.AdamW(1e-4, learning_rate=3e-4), decay=("inverse time", 1, 1e-4), metrics=["mean l2 relative error"], )
I got anther error ValueError: No learning rate for <tensorflow_addons.optimizers.weight_decay_optimizers.AdamW object at 0x00000284AC2BF100>.
ValueError: No learning rate for <tensorflow_addons.optimizers.weight_decay_optimizers.AdamW object at 0x00000284AC2BF100>.
Use tensorflow 2.x backend.
I have solved it. Thank you!
NotImplementedError: <tensorflow_addons.optimizers.weight_decay_optimizers.AdamW object at 0x00000136F434F6D0> to be implemented for backend tensorflow.compat.v1. in src\darcy_rectangular_pwc\deeponet.py.
where I have add
lr=3e-4
, if I use the original codeI got anther error
ValueError: No learning rate for <tensorflow_addons.optimizers.weight_decay_optimizers.AdamW object at 0x00000284AC2BF100>.