Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[TorchFX] Fix depthwise + transpose conv weights quantization #2912

Merged
merged 2 commits into from
Aug 27, 2024
Merged

[TorchFX] Fix depthwise + transpose conv weights quantization #2912

merged 2 commits into from
Aug 27, 2024

Conversation

daniil-lyakhov
Copy link
Collaborator

@daniil-lyakhov daniil-lyakhov commented Aug 23, 2024 •
edited
Loading

Changes

  • Nodes with weights are updated with depthwise and transpose convs

Reason for changes

  • To correctly quantize depthwise and transpose convolutions as they are missing weights quantizers right now

Related tickets

#2766

Tests

  • mobilenet_v3_small and unet references quantized graph are updated

@daniil-lyakhov daniil-lyakhov requested a review from a team as a code owner August 23, 2024 16:43
@github-actions github-actions bot added NNCF PT Pull requests that updates NNCF PyTorch experimental NNCF PTQ Pull requests that updates NNCF PTQ labels Aug 23, 2024
@daniil-lyakhov daniil-lyakhov changed the title [TorchFX] Fix depthwise weights quantization [TorchFX] Fix depthwise + transpose conv weights quantization Aug 23, 2024
@AlexanderDokuchaev AlexanderDokuchaev merged commit ec25a29 into openvinotoolkit:develop Aug 27, 2024
13 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@AlexanderDokuchaev AlexanderDokuchaev AlexanderDokuchaev approved these changes

Assignees
No one assigned
Labels
NNCF PT Pull requests that updates NNCF PyTorch NNCF PTQ Pull requests that updates NNCF PTQ
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@daniil-lyakhov @AlexanderDokuchaev