pytorch / pytorch/vision

Add quantization support for BackboneWithFPN

Open
#5,571 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

module: models.quantization
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 The feature

Add quantization support for BackboneWithFPN.

Motivation, pitch

Currently, it is possible to use from torchvision.models.detection.backbone_utils.resnet_fpn_backbone/BackboneWithFPN in order to produce a backbone fpn network, given some sort of network that can produce features.

While the original resnet/other base networks you want to use (ex. efficientnet), have quantized variants supported (with pretrained weights too), it would be nice to support QAT in the context of FPN networks, to speed up the detectors even more.

Alternatives

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading torchvision.models.detection.backbone_utils.resnet_fpn_backbone and BackboneWithFPN, then examine how the existing quantized base networks and QAT support are integrated. Done means BackboneWithFPN can support quantization-aware training for detector backbones, with the relevant behavior verified by tests identified during that review.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.