Andrew Hundt

Is there anything outstanding on this before merging? I'm interested in trying it out.

@wtokumaru great! @cbfinn can this be merged?

fyi indigo doesn't support 16.04, only kinetic does

That means your incoming sensor data is mirrored vs what is expected by the algorithm. Mirror your sensor data before it gets to the algorithm.

Perhaps it is worth considering settling on the models in https://github.com/farizrahman4u/keras-contrib/blob/master/keras_contrib/applications/densenet.py and https://github.com/aurora95/Keras-FCN/blob/master/models.py#L288 (this second one calls the keras-contrib version, and just tweaks a couple parameters & the top). They...

Is this the one in the readme that gets accuracy between 0.6 and 0.7? If so it seems pretty different from the paper still I wonder what's up.

The problem with the training time is due to concat allocating too much so batch sizes must remain tiny, see https://github.com/gpleiss/efficient_densenet_pytorch for details. I made a feature request regarding the...

keras-contrib is where new functionality now goes for Keras until it is ready for prime time: https://github.com/fchollet/keras/blob/master/CONTRIBUTING.md#pull-requests Kept replies numbered below so we can refer back to them, the best...

8. also worth noting is https://github.com/nicolov/segmentation_keras

I know this one does https://github.com/farizrahman4u/keras-contrib/blob/master/keras_contrib/applications/densenet.py