2

I trained a neural network model on Digits and it seemed to run fine there.
Then i exported the trained model files and copied them into a different system running the standard caffe web demo. I hoped to just be able to plug those files in and have them run in Caffe but i am getting an error.

Specifically I copied my model into bvlc_reference_caffenet.caffemodel, the deploy.prototxt into deploy.prototxt, and the mean.binaryproto into the ilsvrc_2012_mean.npy file. However when I try to run it , it appears to not like the format of the mean.binaryproto file as indicated by the error message:

IOError: Failed to interpret file '/home/vagrant/caffe/python/caffe/imagenet/ilsvrc_2012_mean.npy' as a pickle

what am I doing wrong here? Do I need to process the mean.binaryproto file from Digits somehow before I use it with caffe?

Shai
  • 111,146
  • 38
  • 238
  • 371
user2284821
  • 433
  • 6
  • 16

1 Answers1

2

You need to convert the .binaryproto file to a numpy file. There is a nice example here using caffe.io and caffe.proto.

Shai
  • 111,146
  • 38
  • 238
  • 371