[Torch, QNN] Support quantized mobilenet v3 from torch 1.8 #7606
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
anijain2305
approved these changes
Mar 8, 2021
|
Thanks @masahi @anijain2305 |
masahi
added a commit
to masahi/tvm
that referenced
this pull request
Mar 8, 2021
* [Torch] support hardsigmoid * qhswish first impl * add qhardsigmoid but the result is not correct * add qmv3 to test * comment fix
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
* [Torch] support hardsigmoid * qhswish first impl * add qhardsigmoid but the result is not correct * add qmv3 to test * comment fix
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
May 11, 2021
* [Torch] support hardsigmoid * qhswish first impl * add qhardsigmoid but the result is not correct * add qmv3 to test * comment fix
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Outdated suggestions cannot be applied.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.
Added support for quantized hardsigmoid and hardswish to support the new, QAT-ed, quantized mobilenet v3 large model from PyTorch 1.8 (see their release note https://github.com/pytorch/vision/releases/tag/v0.9.0).
Here are accuracy and latency numbers on a VNNI capable Icelake laptop.
cc @siju-samuel @anijain2305 please review