google-deepmind / google-deepmind/kinetics-i3d
how to use the pretrained model
Open
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 467
- PR merge metrics
- No merged PRs in 30d
Description
excuse me,could you tell me how to use the pretrained model on imagenet?because imagenet dataset include images,but ucf dataset includes videos, and they don't have the same dimensions
Contributor guide
Research direction
No file or test is named. Start by locating the pretrained-model inference entry point and the dataset preparation code for ImageNet and UCF, then check how video inputs are shaped and preprocessed. Done means the repository explains a reproducible way to use the pretrained model with the UCF video data.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100