WIP: Support exporting pretrained models to mace/ncnn and others via pnnx #527
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
|
It requires |
|
In the export.py, if we just save the |
Yes, you are right. |
|
Closing via #571 |
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Outdated suggestions cannot be applied.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.
The aim of this PR is to support exporting pretrained models in a way such that they can be used by other inference frameworks such as
and possibly others like: tnn, mnn, etc.
We can also use the quantization support from the above frameworks, e.g., using full int8 support from ncnn
As the first step, I am using pnnx as the intermediate format.
It requires
csukuangfj/ncnn#1