From 96a9c65f97059d33fa19f9fe0ff0d89abb739259 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Tue, 18 Aug 2020 13:50:55 +0200 Subject: [PATCH] Add model architectures intro --- website/docs/usage/training.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/website/docs/usage/training.md b/website/docs/usage/training.md index 9f74cafac..fc96a76c1 100644 --- a/website/docs/usage/training.md +++ b/website/docs/usage/training.md @@ -385,6 +385,19 @@ that reference this variable. ### Model architectures {#model-architectures} +A **model architecture** is a function that wires up a Thinc `Model` instance, +which you can then use in a component or as a layer of a larger network. You +can use Thinc as a thin wrapper around frameworks such as PyTorch, Tensorflow +or MXNet, or you can implement your logic in Thinc directly. + +spaCy's built-in components will never construct their `Model` instances +themselves, so you won't have to subclass the component to change its model +architecture. You can just update the config so that it refers +to a different registered function. Once the component has been created, its +model instance has already been assigned, so you cannot change its model +architecture. The architecture is like a recipe for the network, and you can't +change the recipe once the dish has already been prepared. You have to make +a new one. ### Metrics, training output and weighted scores {#metrics}