google-deepmind / google-deepmind/kinetics-i3d
Is it better to train from scratch on Kinetics-600?
Open
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 467
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I wonder why you only release checkpoint on Kinetics-600 trained from scratch but not from ImageNet pre-trained parameters.
In the paper, performance is better with ImageNet pre-training on Kinetics-400 dataset.
Is it better to train from scratch on Kinetics-600 dataset?
Thanks!
Contributor guide
Assessment
This issue has not been assessed yet.