Skip to content
/ VQA Public

A Baseline for Toloka Visual Question Answering Challenge at WSDM Cup 2023

Notifications You must be signed in to change notification settings

Hyu-Zhang/VQA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

A Baseline for Toloka Visual Question Answering Challenge at WSDM Cup 2023 (6th)

Task: Given an image and a textual question, draw the bounding box around the object correctly responding to that question.

Question Image and Answer
What do you use to hit the ball? What do you use to hit the ball?
What do people use for cutting? What do people use for cutting?
What do we use to support the immune system and get vitamin C? What do we use to support the immune system and get vitamin C?

Configuration

install Docker. See https://docs.docker.com/engine/install/

docker pull haoyuzhang6/wsdm2023:latest

mkdir output
docker run --rm -it --gpus all --network host -v /ABSOLUTE_PATH_TO/WSDMCup2023/reproduction/data:/mnt/data -v /ABSOLUTE_PATH_TO/reproduction/output:/mnt/output wsdm2023

The input file will be stored in /mnt/data/test.csv and the input images will be at /mnt/data/imgs. The solution must write a single file to /mnt/output/answer.csv .

About

A Baseline for Toloka Visual Question Answering Challenge at WSDM Cup 2023

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published