-
Notifications
You must be signed in to change notification settings - Fork 490
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Added test for uno horizontal_skips_map when None, and make validate_scaling_factor to return None if all scalings are 1 for eff. #273
base: main
Are you sure you want to change the base?
Conversation
… skips_map are the same
… the swap of for loops for skip
…n fno block. This error was blocking the uno to use the scaling factor, as the validate_scaling_factor was giving None
…uno, and modify validate_scaling_factor to accept list of list
…aling_factto None when all scaling are 1 for efficiency
) | ||
|
||
|
||
def apply_complex(fr, fi, x, dtype=torch.cfloat): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could we make the variable names clearer? e.g. expand f
, use real and imag etc.
neuralop/layers/complex_utils.py
Outdated
into a module that operates on complex-valued spatial data. | ||
""" | ||
|
||
def __init__(self, mod): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
def __init__(self, mod): | |
def __init__(self, module): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
updated.
neuralop/layers/complex_utils.py
Outdated
def __init__(self, mod): | ||
super(ComplexValued, self).__init__() | ||
self.fr = deepcopy(mod) | ||
self.fi = deepcopy(mod) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is the deep copy needed? Are we expecting the module to be used somewhere else before conversion?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This line of code is from @dhpitt. I am not sure if deepcopy is necessary.
Co-authored-by: Jean Kossaifi <jean.kossaifi@gmail.com>
The latest update here is about complex FNO (main changes are in the spectral convolution). I have also added pytest when the data is complex. |
No description provided.