PyTorch from a Flux ML Perspective | by Erik Engheim
Oct 19, 2020 · The reduction and agg are how we reduce or aggregate the values in each batch of data processed. Notice how in PyTorch it is specified as a string 'sum' while in Julia it is actually just the normal sum function in the Julia standard library. loss (x, y) = Flux.Losses.mse (model (x), y, agg=sum) learning_rate = 1e-4.
DA: 22 PA: 25 MOZ Rank: 11