Adding multiweight support to Quantized MobileNetV2 and MobileNetV3 #4859
Conversation
This file contains hidden or 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
💊 CI failures summary and remediationsAs of commit 9988a6c (more details on the Dr. CI page):
1 failure not recognized by patterns:
This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
datumbox
added
enhancement
module: models.quantization
datumbox
commented
Nov 4, 2021
| @@ -4,8 +4,7 @@ | |||
| from .googlenet import * | |||
| from .inception import * | |||
| from .mnasnet import * | |||
| from .mobilenetv2 import * | |||
| from .mobilenetv3 import * | |||
| from .mobilenet import * | |||
There was a problem hiding this comment.
For BC reasons, we need to maintain the .mobilenet space.
| kwargs["num_classes"] = len(weights.meta["categories"]) | ||
| if "backend" in weights.meta: | ||
| kwargs["backend"] = weights.meta["backend"] | ||
| backend = kwargs.pop("backend", "qnnpack") |
There was a problem hiding this comment.
The backend here is qnnpack
| ] | ||
|
|
||
|
|
||
| def _mobilenet_v3_model( |
There was a problem hiding this comment.
I kept this method instead on dumping everything in the public method because on the future we might want to support also the _small version of the model and this method will remain unchanged.
|
|
||
| if quantize: | ||
| torch.quantization.convert(model, inplace=True) | ||
| model.eval() |
There was a problem hiding this comment.
Check carefully lines 44-54 comparing to original. This is a simplification of the code.
facebook-github-bot
pushed a commit
that referenced
this pull request
Nov 8, 2021
…leNetV3 (#4859) Summary: * Adding multiweight suport on Quant MobileNetV2 and MobileNetV3. * Fixing enum name. * Fixing lint. Reviewed By: kazhang Differential Revision: D32216681 fbshipit-source-id: 60e2d3c02508c65ec865e603c7155a74cb6bd8b3
cyyever
pushed a commit
to cyyever/vision
that referenced
this pull request
Nov 16, 2021
…ytorch#4859) * Adding multiweight suport on Quant MobileNetV2 and MobileNetV3. * Fixing enum name. * Fixing lint.
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.
Fixes #4674
Verified with:
cc @bjuncek