Closed haoxiangsnr closed 4 years ago
This is an error when the dimensions at 1 don't match (as the error message says...). The input size SHOULD be (B x 1 x 16384) and the latent vector z
must have size (B x 1024 x 8) in order to train successfully. Please double-check if you have matched these conditions. The B stands for batch size.
Ok, thank you for your prompt reply.
Hello, I really like the implementation you wrote. I used the TIMIT and NoiseX92 to synthesize my own dataset, but at runtime, I am prompted with the following error: