This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
Unify input for TorchScript Tensorizers and Models #1256
Closed
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
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D19900062 |
…1256) Summary: Pull Request resolved: facebookresearch#1256 ## Dataflow from PyText client to TorchScript model in predictor 1. Client sends optional "texts", "tokens", "languages", "dense_feat" args in predictor request 2. Predictor pass them to forward() of TorchScript Module(Tensorizer + Model) 3. In ScriptPyTextModule(texts, tokens, languages, dense_feat), the args are converted to ScriptBatchInput(NamedTuple) => Tensorizer.forward() => tuple of Tensors => Model.forward() ## Before: We need a wrapper for each combination of (texts, tokens, languages, dense) ## After: a wrapper for with dense, another wrapper for without dense feature ## Alternative: ScriptPyTextModule(inputs: ScriptBatchInput) after NamedTuple is supported in client example => predictor => ScriptPyTextModule https://fb.workplace.com/groups/811605488888068/permalink/3266598560055403/ Reviewed By: chenyangyu1988 Differential Revision: D19900062 fbshipit-source-id: 556b92374958703fc45e473d982812dd2e68ee68
hudeven
force-pushed
the
export-D19900062
branch
from
cb9922b to
85f7bb7
Compare
|
This pull request was exported from Phabricator. Differential Revision: D19900062 |
|
This pull request has been merged in 898c41c. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Summary:
Dataflow from PyText client to TorchScript model in predictor
Before:
We need a wrapper for each combination of (texts, tokens, languages, dense)
After:
a wrapper for with dense, another wrapper for without dense feature
Alternative:
ScriptPyTextModule(inputs: ScriptBatchInput)
after NamedTuple is supported in client example => predictor => ScriptPyTextModule
https://fb.workplace.com/groups/811605488888068/permalink/3266598560055403/
Reviewed By: chenyangyu1988
Differential Revision: D19900062