Incredibly proud to release this: a new deep learning library, incorporating lessons we've learned from @spacy_io, https://prodi.gy and @tiangolo's FastAPI.
Even if you're not looking for new tools, there's lots you might find interesting conceptually. Quick thread: 1/5https://twitter.com/explosion_ai/status/1222265907965321216 …
-
-
Something I’m not really getting: can gradients flow between different frameworks with this setup? That would be pretty neat.
-
Yes they can. It maybe helps to read about the backprop strategy, and then the pytorch shim sourcehttps://thinc.ai/docs/concept
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
Author of the
Founder
Static type checking
Mix
Integrated config system
Extensible backends incl. JAX (experimental)
Variable-length sequences & more