Closed Pari-singh closed 3 years ago
Thank you!
Right now the only way is splitting your video frame-by-frame, running inference on the folder and then combining the predicted depth maps back. However, adding support to direct video processing doesn't sound too hard and would be useful, I will look into that. In the end it will still be frame-by-frame, but doing the splitting/combining in the code itself.
Hi @VitorGuizilini,
Thanks for your code and the great work! I am trying to get the inference on a custom video/image-sequence, and so was wondering if there needs a major change in the config or is to be done frame-by-frame in the video?
Thanks in advance