sxjscience closed pull request #9867: Using "uniform" Xavier strategy to
initialize the weight for VGG network (a trial solution to issue#9866)
URL: https://github.com/apache/incubator-mxnet/pull/9867
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/example/image-classification/common/fit.py
b/example/image-classification/common/fit.py
index 0e0cd521f2..9412b6f937 100755
--- a/example/image-classification/common/fit.py
+++ b/example/image-classification/common/fit.py
@@ -237,6 +237,9 @@ def fit(args, network, data_loader, **kwargs):
if args.network == 'alexnet':
# AlexNet will not converge using Xavier
initializer = mx.init.Normal()
+ # VGG will not trend to converge using Xavier-Gaussian
+ elif 'vgg' in args.network:
+ initializer = mx.init.Xavier()
else:
initializer = mx.init.Xavier(
rnd_type='gaussian', factor_type="in", magnitude=2)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
