MILVLG / openvqa

A lightweight, scalable, and general framework for visual question answering research
Apache License 2.0
320 stars 64 forks source link

Setup Issues #2 #46

Closed HyperDenton closed 5 years ago

HyperDenton commented 5 years ago

Hi,

I tried setting up the environment described in the doc and then ran

python3 run.py --RUN='train' --MODEL='mcan_small' --DATASET='vqa'

in the directory, but I didn't receive any output or error message,let alone any checkpoint files or training log.

I also tried running other codes such as

python3 run.py --RUN='train' --MODEL='mcan_large' --DATASET='vqa'

and it still showed nothing.

What could be the problem?

Thank you.

HyperDenton commented 5 years ago

Sorry, my mistake. It's because my anaconda is misconfigured. When I ran python run.py --RUN=train --MODEL=mcan_large --DATASET=vqa And then it worked

Amajo0209 commented 2 years ago

Hello! I'm also facing the same. But mine is giving me error

run.py: error: argument --RUN: invalid choice: "'train'" (choose from 'train', 'val', 'test')