[complex] torch.sigmoid: sigmoid does not support automatic differentiation for outputs with complex dtype #48552
Description
import torch
x = torch.tensor(1, dtype=torch.cfloat)
x.requires_grad = True
y = torch.sigmoid(x)
y.backward()Output:
Traceback (most recent call last):
File "test/test_exp.py", line 16, in <module>
y = torch.sigmoid(x)
RuntimeError: sigmoid does not support automatic differentiation for outputs with complex dtype.