Closed N2606 closed 4 years ago
Hi! Thanks for your comment. Fixed
@N2606 how to slove the initialize problem? When I change the initial value of log_sigma2, the loss can become non-Nan. However, loss is almost constant, resulting in the failure of model convergence.
Hi, thanks for the works. I ran the mnist_ard and the loss is always nan regardless how I initialize log_sigma2. Did anyone train successfully?