-
Notifications
You must be signed in to change notification settings - Fork 29
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
No effect after “ fuse_bn_recursively” #7
Comments
Please, take a look at the resent example. You need some bells and whistles to make it work. |
Thank you very much for your prompt reply. I think I understand what you mean. This project is very enlightening for me. |
Actually I think the bn fusion in this repo is for depthwise convolution. Not standard convolution, correct me if I am wrong. Please checking the implementation of kito. |
I load mobileNet v2 and operate it by fuse_bn_recursively function, then print the network strutures of this two model, but I found that the bn_fusion net is the same as the initial net, is it because of my misoperation?
`
import torch
from bn_fusion import fuse_bn_recursively
from pytorchcv.model_provider import get_model as ptcv_get_model
if name == 'main':
`
The text was updated successfully, but these errors were encountered: