This commit is contained in:
Nicolas Patry
2023-07-27 16:36:36 +02:00
parent ad9d8fe400
commit ebd0315623

View File

@ -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.