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

Edit description of convolutional layer

This commit is contained in:
Bulat Suleymanov 2020-02-24 13:16:51 +05:00 committed by GitHub
parent 34ceed5c1f
commit db4eaf254b
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
src/layers/conv.jl
View File

@ -17,7 +17,7 @@ Example: Applying Conv layer to a 1-channel input using a 2x2 window size,
out = 16 out = 16
Conv((2, 2), 1=>16, relu) Conv((2, 2), 1=>16, relu)
Data should be stored in WHCN order (width, height, # channels, # batches). Data should be stored in WHCN order (width, height, # channels, batch size).
In other words, a 100×100 RGB image would be a `100×100×3×1` array, In other words, a 100×100 RGB image would be a `100×100×3×1` array,
and a batch of 50 would be a `100×100×3×50` array. and a batch of 50 would be a `100×100×3×50` array.