Open rolisz opened 5 years ago
The output type of image segmentation is a matrix of class ids of the same size of the input image. That input type is not supported yet. But there is nothing preventing you from adding it. It is on our roadmap, but it may take a while to be implemented. We welcome contributions.
Any updates on semantic segmentation?
@slavakurilyak Answering the same thing I answered for the GAN feature request. This is currently not being worked on, after the release of v0.3 (a month or so) we will reassess all users requests to figure out priorities for v0.4, but we did not forget about this, it's just that with the resources at our disposal, it has not been prioritized yet.
Is there any architectural/technical limitation why Ludwig is not able to perform image segmentation? Or is it just not yet implemented?