Hi, Thanks for you codes. What is the following sentence function to achieve?
caffe_model_decompress (netmodel, "alexnet_xx.caffemodel", "alexnetzip.npz")
Why is the output of alexnet_xx.caffemodel the size is not the same of the not compressed before? How to fine tune the data set test accuracy with the compressed model?I will be very grateful if anyone can help me, Thanks!
I tried the codes, because weights sharing ,so the size reduced by 4X. secondly ,when I fine tune the network , I got errors. It likely to be caused by too many zero weights, I am not sure.
Hi, Thanks for you codes. What is the following sentence function to achieve? caffe_model_decompress (netmodel, "alexnet_xx.caffemodel", "alexnetzip.npz") Why is the output of alexnet_xx.caffemodel the size is not the same of the not compressed before? How to fine tune the data set test accuracy with the compressed model?I will be very grateful if anyone can help me, Thanks!