Differentiable Computer Vision
Today's presentation is a talk by Edgar Riba on the Kornia open source library. Kornia is a differentiable computer vision library. We have covered it before here in previous HTC posts, but this recent presentation from 2 weeks ago will help you get up to date with the latest and greatest developments.
This is from the OpenCV weekly webinar series. They also allude in the webinar to the new Oak-lite kickstarter campaign, which is active now.
1: One thing Edgar points out is that the Kornia library works on tensors, so unlike OpenCV you don't have to worry about how many channels are needed for an input to a particular algorithm. The library just deals with it.
2: In theory one could use the TorchScript part of PyTorch to get C++ code output from a Kornia algorithm. Edgar mentioned 80% compatibility with Torchscript right now. I do get nervous when he says 'in theory' for this or Onyx output.
Post a Comment