marshal: Save TF models under a versioned folder #228
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dpoulopoulos
approved these changes
Oct 7, 2020
TensorFlow serving expects a model to saved under a versioned (e.g. 1/, 2/, ...) folder, so that the user can save multiple versions of the same mudel in the same place. We now always save a model under `1/` just in case the dump needs to be served as well. The function `load_model` does not handle this case thouth, so we need to take it into account. Signed-off-by: Stefano Fioravanzo <[email protected]> Reviewed-by: Dimitris Poulopoulos <[email protected]>
dpoulopoulos
force-pushed
the
feature-tf-serving-marshal
branch
from
7ee43e7
to
40feeac
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
TensorFlow serving expects a model to saved under a versioned (e.g. 1/,
2/, ...) folder, so that the user can save multiple versions of the same
mudel in the same place.
We now always save a model under
1/just in case the dump needs to beserved as well. The function
load_modeldoes not handle this casethouth, so we need to take it into account.
Signed-off-by: Stefano Fioravanzo [email protected]