google-deepmind / google-deepmind/tapnet
ValueError: converting frame count is not supported.
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2k
- Forks
- 192
- PR merge metrics
- No merged PRs in 30d
Description
I want to track points across many short horizon videos of, say, dimension (8, 256, 256, 3). Suppose I have B such videos and I want to track the same N points in each video. Then, the input that I pass into TAPIR is of dimensions (B, 8, 256, 256, 3) for the frames and (B, N, 3) for the queries. Suppose B = 4 and N = 32 for the sake of an example.
However, this always seems to give me a ValueError: `converting frame count is not supported.` Any ideas of what might be happening here?
Contributor guide
Assessment
This issue has not been assessed yet.