fizyr/keras-retinanet

evaluate.py support other data format?

Open

#911 opened on Feb 19, 2019

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (4,352 stars) (1,982 forks)batch import
help wanted

Description

Is there a way I can run evaluate.py on a separate test set with trained models? It appears it doesn't support oid and a couple of other formats where train.py does.

Contributor guide

Tech stack
python
Domain
machine learningbackend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
PythonKerasObject detection basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Examine how train.py handles different data formats (e.g., OID, Pascal VOC) by looking at the data loading utilities. Then, modify evaluate.py to accept a similar data format parameter, adapting the dataset loading logic accordingly. Look at the repository's data generators and scripts for reference.
evaluate.py support other data format? · fizyr/keras-retinanet#911 | Good First Issue