An DAU-ConvNet with AlexNet architecture with conv3,conv4 and conv5 replaced with DAU-Conv layer. Corresponds to "Large DAU-ConvNet" in CVPR18 paper using larger number of DAUs per channel.
Model is trained on ilsvrc12 and achieves around 57.3% top-1 accuracy.
mean_file: use standard ilsvrc 2012 mean file provided by caffe
Compatibile only with https://github.com/skokec/DAU-ConvNet-caffe