pytorch / pytorch/vision

detector as feature extractor

Open
#2,963 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

Hello,

I am using mask rcnn for detection. So basically fine tuning. However I want extract feature for each object that is being detected.
So possibly extracting feature vector just before last layer. How can I do that ? forward hooks ?

I was also looking into https://github.com/pytorch/vision/blob/master/torchvision/models/_utils.py ? could not get it working.

Also how to use jit for the same ?

Any leads would be helpful. @fmassa

Cheers!

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 with the Mask R-CNN model path and torchvision/models/_utils.py mentioned in the issue, then examine how per-object feature vectors and JIT support would fit the existing API. Done when the requested behavior has a defined interface and a supported implementation or a clearly documented limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.