I am getting this error while running a downloaded program which i am using for my understanding. Input values are in the form of complex number but i am not be able to initialize the weights for convolutional autoencoder in complex number form. so i am getting this error anyone please help me how to initialize weights in complex number form.
Error message:
‘’‘Input type (CUDAComplexDoubleType) and weight type (torch.cuda.FloatTensor) should be the same’’’
You could try to convert all parameters to complex128
via model.to(torch.complex128)
.
Note however, that this feature is experimental and not all operations might be supported at this moment.
1 Like
Thankyou for the reply @ptrblck but it’s not working. Applying model.to(torch.complex128) i am getting an error " nn.Module.to only accepts floating point dtypes, but got desired dtype=torch.complex128". Is there any other way for converting weights float to complex128.?