torchdiffeq icon indicating copy to clipboard operation
torchdiffeq copied to clipboard
verified publisher icon rtqichen

Adjoint support for complex dtypes.

Open gitvicky opened this issue 1 year ago • 0 comments

While deploying an FNO in a an ajoint neural ODE setup, we run into this error of dtype mismatch: RuntimeError: mat1 and mat2 must have the same dtype, but got ComplexFloat and Float Would there be further support for complex dtypes possible?

gitvicky avatar Feb 25 '25 17:02 gitvicky