Closed 1028267022 closed 1 month ago
Yes, that would be possible. You would need to format the data correctly. The feature for simple inference providing a video and a query has not been implemented yet. Just be aware of which model you want to use since there might be a domain gap between the training data and the sample on which you want to make test-time inferences.
where could i find the feature extraced code?
can i inference for other video and text