-
Notifications
You must be signed in to change notification settings - Fork 356
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Question: How do I use TensorNetworkLayer to replace Dense Layers on Trained Model w/o re-train? #911
Comments
Hi @shun-lin sorry for the late reply! Let me rope in @jacksonwb on this! |
Hi @shun-lin you can extract the Doing the decomposition manually can be relatively straight forward or somewhat complex depending on the layer shape you are decomposing to. I would probably recommend you freeze the other layers and train from scratch, unless you are particularly interested in approximating layers specifically trained as fully-connected. |
Hi @jacksonwb, Thanks for the quick response! I have a few follow-up questions:
I think i'm interested in knowing the answer to this in the lens of AutoML to try to cut down computation costs / model search time and some techniques uses transfer learning :) |
If the |
Hi!
I have a
saved_model
with a few fully-connected layers (fc_layers
), is it possible to transform theweights
already learned from thosefc_layers
to the weights oftn_layers
? Or do I have to retrain those tn_layers while freezing other layers? Thanks!Sincerely,
Shun Lin
The text was updated successfully, but these errors were encountered: