Adapt the resnet model into a pixel classification model

[Ssica]

Hi, I've been attempting to adapt your implementation of the residual model to do pixel-wise classification. It may be a long shot, but I was hoping I could ask you a few question and hoping for some hints.

So I'm currently thinking of using upsampling such that the repræsentation and the input dimensions stays the same but upsampling in the latter part of the model. My images are 155x240 (BRATS CHALLENGE data set) but I'm afraid that the residual model downsamples my input so much that upsampling the image to its original size makes it such that I cannot classify each pixel properly. Another way of preserving the image repræsentations dimensions would simply be to make stride=1 for each layer which downsamples the repræsentation, but if possible I would like to let the resNet architecture stay the same while mbe changing it by only adding layers.

Other hints are welcome as well!

Great work and thanks for sharing it,

Best regards, S2ica

[raghakot]

How about trying dilations instead? It precisely solves this very issue: https://arxiv.org/pdf/1511.07122.pdf

[ahundt]

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