summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNicolas Patry <patry.nicolas@protonmail.com>2023-07-27 16:36:36 +0200
committerNicolas Patry <patry.nicolas@protonmail.com>2023-08-01 14:26:02 +0200
commitebd0315623a42c1798e39f4d6321d096fd328b06 (patch)
tree75de066423e9c169f4f5ae8357fa44a7bbae4fa5
parentad9d8fe4003eb08c1df20a86697f8d026ee3a800 (diff)
downloadcandle-ebd0315623a42c1798e39f4d6321d096fd328b06.tar.gz
candle-ebd0315623a42c1798e39f4d6321d096fd328b06.tar.bz2
candle-ebd0315623a42c1798e39f4d6321d096fd328b06.zip
Typo.
-rw-r--r--candle-book/src/guide/hello_world.md2
1 files changed, 1 insertions, 1 deletions
diff --git a/candle-book/src/guide/hello_world.md b/candle-book/src/guide/hello_world.md
index bdf7b712..ee630979 100644
--- a/candle-book/src/guide/hello_world.md
+++ b/candle-book/src/guide/hello_world.md
@@ -127,7 +127,7 @@ fn main() -> Result<()> {
Now it works, great and is a great way to create your own layers.
But most of the classical layers are already implemented in [candle-nn](https://github.com/LaurentMazare/candle/tree/main/candle-nn).
-## Using a `candle_nn`.
+## Using `candle_nn`.
For instance [Linear](https://github.com/LaurentMazare/candle/blob/main/candle-nn/src/linear.rs) is already there.
This Linear is coded with PyTorch layout in mind, to reuse better existing models out there, so it uses the transpose of the weights and not the weights directly.