jwyang / jwyang/faster-rcnn.pytorch

how many classes you used of visual genome data? 2500 or 1600? Seems peter anderson used 1600 indeed. And with that, I got mAP of 2.7

Open
#331 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.9k
Forks
2.3k
PR merge metrics
No merged PRs in 30d

Description

This issue has no description.

Contributor guide

No contributing guide indexed for this repository

Research direction

No file, test, or entry point is mentioned. Start by locating the Visual Genome class-count configuration and compare the reported 2,500-class setup with the 1,600 classes attributed to Peter Anderson; this issue needs a reproducible configuration and a defined expected mAP before work is ready.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.