Closed ahundt closed 6 years ago
I'm def open to it.
How would you suggest going about that? Right now, it's not the cleanest/simplest code, as I've tried to match the original implementation as closely as possible.
Update: François Chollet, Keras' author, said he is interested in directly incorporating dense prediction/FCN into the Keras API, so I'm seeking suggestions/feedback at https://github.com/fchollet/keras/issues/6538
Might you be interested in a pull request of this code to the official keras-contrib repository?
These keras-contrib issues are also relevant to this repository:
Keras-FCN, which I was planning to adapt for a merge into keras-contrib also has a SegDataGenerator implementation with some of the features you are looking for in your comments, plus additional models and experimental support for coco. My Keras-FCN branch with a README.md may also be informative, there is a pull request in progress to merge upstream.