Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Some questions about model testing #5

Open
VicZlq opened this issue Aug 23, 2021 · 1 comment
Open

Some questions about model testing #5

VicZlq opened this issue Aug 23, 2021 · 1 comment

Comments

@VicZlq
Copy link

VicZlq commented Aug 23, 2021

Hello, thank you very much for your work!
I recently had some problems in reproducing this work. The address you provided for the dataset download, the data format is tsv and the code is reading in json format. Is it a direct conversion of tsv to a json format file, please?
When testing the model, I tried the demo, but it did not turn the "blue car" into a "red car", but I checked that it did load the model you provided, have you encountered such problems? Thank you very much!

@xh-liu
Copy link
Owner

xh-liu commented Aug 27, 2021

Thank you for your interest in our work.

  1. The original data format downloaded from the Conceptual Captions webpage contains the download link of each image and the meta information. It is not a direct transform from tsv to json. You need to download the images from Conceptual Captions dataset (or other datasets) first. The json file contains the filepath of each image.
  2. I have updated a few bugs and typos in test.sh and test.py. Please try if you can run the demo now.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants