No difference in binarized and full-precision LeNet model size

hpi-xnor / BMXNet

(New version is out: https://github.com/hpi-xnor/BMXNet-v2) BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet

Apache License 2.0

349 stars 95 forks source link

No difference in binarized and full-precision LeNet model size #47

Closed jonkoi closed 6 years ago

jonkoi commented 6 years ago

I tried your binarized mnist Lenet example and trained a binarized model and a normal model. The resulting binarized/normal params files are 4.6MB/4.6MB instead of 206kB/4.6MB in the paper. I saw your pretrained binarized model really achieved 206kB.

Am I missing something? Is there a compression step?

jonkoi commented 6 years ago

Sorry, i did not read about the model converter part. Trying it out, closing the issue.

kaka-lin commented 5 years ago

sorry Have you solved the problem？