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

Make Flux.onehot accessible in the MNIST example

Browse Source 
Alternatively, line 4 could be rewritten to

data = [(trainfeatures(i), Flux.onehot(trainlabel(i), 0:9)) for i = 1:60_000]
This commit is contained in:
Peter Dolan 2017-06-23 16:57:08 -07:00 committed by GitHub
parent ea5d43ed77
commit ac6a9d9a51
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/MNIST.jl
View File

@ -1,5 +1,5 @@
using Flux, MNIST using Flux, MNIST
using Flux: accuracy using Flux: accuracy, onehot
data = [(trainfeatures(i), onehot(trainlabel(i), 0:9)) for i = 1:60_000] data = [(trainfeatures(i), onehot(trainlabel(i), 0:9)) for i = 1:60_000]
train = data[1:50_000] train = data[1:50_000]