Skip to content

How is scaling factor updated during training? #803

Closed Answered by Giuseppe5
hleblevec asked this question in Q&A
Discussion options

You must be logged in to vote

Yes that is basically one aspect of it.
The other option is to accumulate statistics during training time over your tensor, and compute the scale factor based on that.
At eval time, then the scale factor is fixed. This is for activations where you have runtime tensors.

For weights, you can simply have a scale factor which depends on some statistics of the weights.

Replies: 1 comment 3 replies

Comment options

You must be logged in to vote
3 replies
@hleblevec
Comment options

@Giuseppe5
Comment options

Answer selected by hleblevec
@hleblevec
Comment options

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants