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

Running pip install -r requirements.txt throws up error #1

Closed
fomalhaut-b opened this issue Jun 23, 2021 · 3 comments
Closed

Running pip install -r requirements.txt throws up error #1

fomalhaut-b opened this issue Jun 23, 2021 · 3 comments

Comments

@fomalhaut-b
Copy link

Hi @coldmanck ,
After running pip install -r requirements.txt it's throwing up error saying "is it == instead of =". Changing this does not fix. Could you once check if there was any error?

@coldmanck
Copy link
Owner

Hi, thank you for your interest in our project!

Sorry that the original requirements.txt file doesn't work. This project is constructed with Python 3.6, PyTorch 1.1.0, and CUDA 9.0 and is largely based on VL-BERT. Please follow the original instruction to install a conda environment. I've also uploaded a new requirements.txt (basically the same as in VL-BERT) and updated the README.MD file.

@fomalhaut-b
Copy link
Author

fomalhaut-b commented Jun 23, 2021

Hi @coldmanck , thanks. This worked. I wasn't able to run script since I dont have cuda, so i'll try it again on cuda. How to run your code on custom inputs? Is retraining code available? I think you are just using pretrained weights right?

@coldmanck
Copy link
Owner

coldmanck commented Jun 23, 2021

Hi, we only provide inference scripts (for the specific datasets) and trained checkpoints for verification purposes only, and yes, we incorporate visual-linguistic knowledge in the pretrained weights from VL-BERT.

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