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.

Sign up for GitHub

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

Jump to bottom

Full sequence of steps for training and inference #4

Open

Tushar-N opened this issue Feb 27, 2023 · 0 comments

Tushar-N commented Feb 27, 2023 •

edited

Loading

Could you please update the QUICKSTART.md file with exact commands to run in order to train the models and generate predictions on the test set?

I cannot fully run these experiments. Several issues exist:

The default config uses an embedding file (but this issue says it is not used)
There is no test_model.py script. test_all.py fails for ICVAE. There are also several predict*.py files. Are these used?
The H3M config file uses 6 input clips, making it incompatible with the ICVAE model that uses 8.
Does H3M need to be finetuned from a recognition checkpoint? (pretrained_weights/multitask_recognition.pt)

Could you also please share training logs and pretrained checkpoints to verify if everything is set up correctly? Thanks

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment