TastyPancakes
/
Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update docs/src/performance.md 

Co-Authored-By: Kristoffer Carlsson <kristoffer.carlsson@chalmers.se>
This commit is contained in:
Lyndon White 2019-05-28 14:19:56 +01:00 committed by GitHub
parent fc4827c48f
commit fe759ac43c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/performance.md
View File

@ -26,7 +26,7 @@ A very artificial example using an activation function like
will result in performance on `Float32` input orders of magnitude slower than the normal `tanh` would,
because it results in having to use slow mixed type multiplication in the dense layers.
Similar can occur in the loss function during backpropagation.
Similar situations can occur in the loss function during backpropagation.
Which means if you change your data say from `Float64` to `Float32` (which should give a speedup: see above),
you will see a large slow-down