This is an automated email from the ASF dual-hosted git repository.
sxjscience pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new 17a9c6a Using "uniform" Xavier strategy to initialize the weight for
VGG network (a trial solution to issue#9866) (#9867)
17a9c6a is described below
commit 17a9c6ad440139d3f87924a8e989d4da252504be
Author: Shufan <[email protected]>
AuthorDate: Wed Feb 28 13:01:34 2018 +0800
Using "uniform" Xavier strategy to initialize the weight for VGG network (a
trial solution to issue#9866) (#9867)
* Enable the reporting of cross-entropy or nll loss value during training
* Set the default value of loss as a '' to avoid a Python runtime issue
when loss argument is not set
* Applying the Xavier with "uniform" type to initialize weight when network
is VGG
---
example/image-classification/common/fit.py | 3 +++
1 file changed, 3 insertions(+)
diff --git a/example/image-classification/common/fit.py
b/example/image-classification/common/fit.py
index 0e0cd52..9412b6f 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)
--
To stop receiving notification emails like this one, please contact
[email protected].
