[doc] refine pretrained model links #1006
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
xingchensong
reviewed
Apr 3, 2022
|
it's averaged checkpoint. It's just our convention to name it as |
|
Since we changed the interface, all the runtime models should be re-exported with the new interface. That's the main function of the PR. |
xingchensong
approved these changes
Apr 3, 2022
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Outdated suggestions cannot be applied.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.
We used to provide checkpoint model, runtime x86 model, runtime android model. However, runtime model could be used in both x86 and android, which is tricky for some users.
So we combine them into one quantized model in this PR, which reduces the model size, network traffic, as well as maintainance efforts. And our experiments shows, quantized models show comparable accuracy and better RTF compared with corresponding float model on both x86 and android platforms.