I was asked to embed an AlexNet in a Java application but I'm not a machine learning at all. This is what I did. First I tried to build it using MatLab (using this deploy https://github.com/BVLC/caffe/blob/master/models/bvlc_alexnet/deploy.prototxt) but it returned a network in .onnx format; unfortunatelly I need a caffemodel, and therefore I tried to covert it using https://github.com/MTlab/onnx2caffe and https://github.com/onnx/onnx/blob/master/README.md but these latterse do not support Local Response Normalization (LRN) convolutional layer ("TypeError: ONNX node of type LRN is not supported." error came out). At this point I triend to use this wrapper https://github.com/fabiocarrara/pyffe but after 2 days of set up, installing, upgranding, changing configuration files I gave up. My question is: can you please reccommend me a simple and effective script or tutorial that train an AlexNet from scratch? Thanks very much


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.