clarify docs on single batch image to conv

fixes #309
This commit is contained in:
Kristoffer Carlsson 2019-01-24 11:24:10 +01:00
parent 4be08fe194
commit 325e3a4f70

View File

@ -13,7 +13,7 @@ Standard convolutional layer. `size` should be a tuple like `(2, 2)`.
`in` and `out` specify the number of input and output channels respectively.
Data should be stored in WHCN order. In other words, a 100×100 RGB image would
be a `100×100×3` array, and a batch of 50 would be a `100×100×3×50` array.
be a `100×100×3×1` array, and a batch of 50 would be a `100×100×3×50` array.
Takes the keyword arguments `pad`, `stride` and `dilation`.
"""