Andrew Hundt

dilations are now merged in the keras-contrib adaptation of this repository https://github.com/farizrahman4u/keras-contrib/blob/master/keras_contrib/applications/resnet.py

You might want to consider submitting this at https://github.com/farizrahman4u/keras-contrib, which is more up to date

@bhack yes as linked above https://github.com/ahundt/keras-resnet/tree/dense_predictions should be resuming work a bit this week.

Full details are at https://github.com/farizrahman4u/keras-contrib/issues/63

there are a bunch of pretrained weights floating around. I'm sure just one set of weights would be enough for them to accept the request for the first version. I...

~~What may be the easiest option is to simply~~ convert the ones from the [tensorflow slim models repository](https://github.com/tensorflow/models/tree/master/slim). They have a [resnet implementation](https://github.com/tensorflow/models/blob/master/slim/nets/resnet_v2.py) and links to their [pre-trained models](https://github.com/tensorflow/models/tree/master/slim#pre-trained-models) which...

looks like based on the description some of the weights were already transferred in here: https://github.com/fchollet/deep-learning-models so it might be worth asking if there is code that was used to...

I believe the most appropriate place for this now might be keras-contrib: https://github.com/farizrahman4u/keras-contrib

I've taken first steps towards this at https://github.com/farizrahman4u/keras-contrib/pull/148

no, I haven't been using ResNets directly recently