Cannot change the activation function for the LDC

Dear All,
I am using Nvidia modulus 22.09
I am trying to change the activation function for the LDC problem.

But When I import the required library as shown in the tutorial:

from modulus.models.layers.layers import Activation

I get this error
No module named ‘modulus.models.layers.layers’

Thanks in advance

Hi @omarkhaledsallam

Please try from modulus.models.layers import Activation

Which tutorial are you referring to here? Please provide the link if you can and we will get it fixed. Thank you!

Thanks for you reply

I get this from the tutorial link below:

In the (Changing Activation Functions) section

I changed the the import to
from modulus.models.layers import Activation

and it worked :)

Hi @ngeneva

I wanted to change the activation function as well and I already changed the path.

However, I get following error:

Error executing job with overrides: []
Traceback (most recent call last):
  File "/software/modulus/22.09/lib/python3.8/site-packages/modulus-22.9-py3.8.egg/modulus/hydra/", line 200, in instantiate_arch
    model, param = model_arch.from_config(model_cfg)
  File "/software/modulus/22.09/lib/python3.8/site-packages/modulus-22.9-py3.8.egg/modulus/models/", line 500, in from_config
    cfg["activation_fn"] = Activation[cfg["activation_fn"]]
  File "/software/modulus/22.09/lib/python3.8/site-packages/modulus-22.9-py3.8.egg/modulus/models/layers/", line 16, in __getitem__
    return super().__getitem__(name.upper())
AttributeError: 'Activation' object has no attribute 'upper'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "", line 85, in run
    flow_net = instantiate_arch(
  File "/software/modulus/22.09/lib/python3.8/site-packages/modulus-22.9-py3.8.egg/modulus/hydra/", line 210, in instantiate_arch
    raise Exception(fail) from e
Exception: Failed to initialize architecture.
 {'input_keys': [x, y], 'output_keys': [u, v, p], 'detach_keys': [???], 'scaling': None, 'layer_size': 512, 'nr_layers': 6, 'skip_connections': False, 'activation_fn': <Activation.SILU: 9>, 'adaptive_activations': False, 'weight_norm': True}

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 121742) of binary: /software/modulus/22.09/bin/python3.8
Traceback (most recent call last):
  File "/software/modulus/22.09/bin/torchrun", line 8, in <module>
  File "/software/modulus/22.09/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/", line 346, in wrapper
    return f(*args, **kwargs)
  File "/software/modulus/22.09/lib/python3.8/site-packages/torch/distributed/", line 762, in main
  File "/software/modulus/22.09/lib/python3.8/site-packages/torch/distributed/", line 753, in run
  File "/software/modulus/22.09/lib/python3.8/site-packages/torch/distributed/launcher/", line 132, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/software/modulus/22.09/lib/python3.8/site-packages/torch/distributed/launcher/", line 246, in launch_agent
    raise ChildFailedError(

How can fix this issue?

Many thanks in advance.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.