How to create model with custom BatchNorm arguments?

[MichaelMonashev]

I tried model = timm.create_model('efficientnetv2_s', norm_layer=partial(torch.nn.BatchNorm2d, affine=False)) but got error:

>>> model = timm.create_model('efficientnetv2_s', norm_layer=partial(torch.nn.BatchNorm2d, affine=False))
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/xxxx/.local/lib/python3.8/site-packages/timm/models/factory.py", line 81, in create_model
    model = create_fn(pretrained=pretrained, **kwargs)
  File "/home/xxxx/.local/lib/python3.8/site-packages/timm/models/efficientnet.py", line 1513, in efficientnetv2_s
    model = _gen_efficientnetv2_s('efficientnetv2_s', pretrained=pretrained, **kwargs)
  File "/home/xxxx/.local/lib/python3.8/site-packages/timm/models/efficientnet.py", line 962, in _gen_efficientnetv2_s
    model_kwargs = dict(
TypeError: type object got multiple values for keyword argument 'norm_layer'