Evgenii Shalnov

Too huge step_size at initialization stage

1

I found that step_size is too high in the initial 5 steps. The problem is in the code: ``` if N_sma >= self.N_sma_threshhold: step_size = math.sqrt((1 - beta2_t) * (N_sma...

I have made a pytorch version. It also allows filter and column pruning

Add ```map_location``` to ```torch.load``` in order to fix an issue with an absence of CUDA devices