From 398097c86513fdd294f87801c4bde7ad5f1145d5 Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Fri, 9 May 2025 23:15:30 +0200 Subject: [PATCH] Update sampler_explaination.md --- sampler_explaination.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sampler_explaination.md b/sampler_explaination.md index b6101eb..b2a976f 100644 --- a/sampler_explaination.md +++ b/sampler_explaination.md @@ -22,7 +22,9 @@ The input tensor is normalized by dividing it by its norm: tn = t.div(norm) -This step projects the tensors onto a unit hypersphere. (Note from me: that's a super fancy way to say I divide by the norm/radius, juste to ensure a similar scale, also usable by the slerp after) +This step projects the tensors onto a unit hypersphere. + +(Note from me: that's a super fancy way to say I divide by the norm/radius, juste to ensure a similar scale, also usable by the slerp after) Next, the function calculates a distance metric between all pairs of normalized tensors: