tensorflow / tensorflow/models

How to modify the prediction pipeline of a saved model?

Open
#8,189 1 comment 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since May 21, 2020.

models:research:odapi type:bug
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

System information

  • Tensorflow version: 2.1.0
  • Python 3.6
  • Ubuntu 18.04

Hello! I am loading (without any problem) a Faster RCNN model trained on the EPIC-KITCHENS dataset.

I want to change the prediction pipeline by modifying the non-max-suppression step in order to perform some tests. My final output should be a set of bounding boxes and a set of scoring vectors with a size of 1*C (C is the total number of classes of my dataset). However, I don't know how to do this since I cannot access to the pipeline of this trained model.

Is there any way to do this? Maybe by building a new model with my new pipeline and loading the trained weights somehow?

Thanks in advance!

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.