google-deepmind / google-deepmind/tapnet

KeyError: 'global_step' When I load the weight of TAPIR

Open
#93 5 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
2k
Forks
192
PR merge metrics
No merged PRs in 30d

Description

I downloaded tapir_checkpoint_panning.npy from the link provided, but it didn't load. I printed ckpt_state.keys() in the restore function in experiment_utils.py and found only 'params' and 'state' in the key of ckpt_state. There is no 'global_step' in the key. Below are my command to run the evaluation.
`python3 ./tapnet/experiment.py --config=./tapnet/configs/tapir_config.py --jaxline_mode=eval_davis_points --config.checkpoint_dir=./tapnet/checkpoint/ --config.experiment_kwargs.config.davis_points_path=/tapvid_davis/tapvid_davis.pkl`
How do I get the code to run? Thanks!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.