questions about the weights of different losses

[icoz69]

in the demo 256 code, the weights of different losses are 1,1/1.6,1/2.3,1/2.8,10/0.5. where do these hyperparameters come from?
in the paper, it says they are "inverse of the number of elements in each layer', what do you mean by "number of elements", and how to calculate the weights above?
looking forward to ur reply, thank you

[CQFIO]

If you just the weights listed there, it should be fine.

I use tf.reduce_mean to compute the average. The weights 1,1/1.6,1/2.3,1/2.8,10/0.5 are computed from the average l0,...,l5 in the 100 epoch.

[icoz69]

@CQFIO
thanks for your reply.
what do l0,...,l5 mean?
and how could the weights be learnable? losses are always positive, so weighting will keep decreasing during the training.