Open felixdittrich92 opened 1 month ago
Yeah, something like layer._inbound_nodes[i].outputs
. Note that you'd be using a private API so there's no strong guarantee that it will always work.
Thanks @fchollet 👍 Any recommendations for a "safer" way if you mention that it could change at any time to extract specific layer outputs from a backbone model ?
As context: I started to bring https://github.com/mindee/doctr step by step to Keras v3 - otherwise the docTR + Tensorflow backend would die over the time 😅 (https://github.com/mindee/doctr/pull/1724)
Btw. i saw it's planned to bring Onnx support to keras v3 is there already any progress ?
Thanks again 🤗
Any recommendations for a "safer" way if you mention that it could change at any time to extract specific layer outputs from a backbone model ?
I would recommend just using the code snippet -- it is private, but very stable in practice (hasn't changed since the original Keras 3 release). We just don't think this is common enough to need an official public API. Very little chance it would actually ever break, but make sure to have CI running just in case a so you can catch it.
If we make it a public API it would probably be .inbound_nodes
.
Btw. i saw it's planned to bring Onnx support to keras v3 is there already any progress ?
Would you like to contribute something? We haven't staffed it yet but we could guide you if you're interested!
Any recommendations for a "safer" way if you mention that it could change at any time to extract specific layer outputs from a backbone model ?
I would recommend just using the code snippet -- it is private, but very stable in practice (hasn't changed since the original Keras 3 release). We just don't think this is common enough to need an official public API. Very little chance it would actually ever break, but make sure to have CI running just in case a so you can catch it.
If we make it a public API it would probably be
.inbound_nodes
.Btw. i saw it's planned to bring Onnx support to keras v3 is there already any progress ?
Would you like to contribute something? We haven't staffed it yet but we could guide you if you're interested!
Backend:
torch.onnx.export
?tf2onnx
(which is not yet 100% compatible with keras v3) or "own" integration (looots of work) ?
Hi :wave:,
A quick question is there a equivalent in keras v3 for
model.get_layer(layer_name).get_output_at(0)
from keras v2 ?context:
Thanks :)