evidential-deep-learning
evidential-deep-learning copied to clipboard
Add pytorch demo script
500 iters:
1500 iters:
Thanks a lot for the implementation. I have noticed a strange behavior of Pytorch:
When concatenating the return value of LinearNormalGamma
at https://github.com/aamini/evidential-deep-learning/blob/71ebd59ab3a4b66c38d919e8aa9ad3711a416796/torch_hello_world.py#L22
such that:
ret = mu, self.evidence(logv), self.evidence(logalpha) + 1, self.evidence(logbeta)
return torch.cat(ret, dim=-1)
the training does not seem to progress and a constant value is predicted. Is there any reasonable explanation for this?