You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@singa.apache.org by zh...@apache.org on 2022/03/02 08:23:22 UTC

[singa] branch dev updated: replace SGD optimizer with Adam for bloodmnist

This is an automated email from the ASF dual-hosted git repository.

zhaojing pushed a commit to branch dev
in repository https://gitbox.apache.org/repos/asf/singa.git


The following commit(s) were added to refs/heads/dev by this push:
     new 6d840e4  replace SGD optimizer with Adam for bloodmnist
     new ee2e460  Merge pull request #937 from zlheui/update-bloodmnist-optimizer
6d840e4 is described below

commit 6d840e48f385b1fcc1601dfe43fe8a7d3ea5736e
Author: zhulei <zl...@gmail.com>
AuthorDate: Wed Mar 2 13:00:42 2022 +0800

    replace SGD optimizer with Adam for bloodmnist
---
 examples/demos/Classification/BloodMnist/ClassDemo.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/examples/demos/Classification/BloodMnist/ClassDemo.py b/examples/demos/Classification/BloodMnist/ClassDemo.py
index 1d17150..1047c21 100644
--- a/examples/demos/Classification/BloodMnist/ClassDemo.py
+++ b/examples/demos/Classification/BloodMnist/ClassDemo.py
@@ -243,7 +243,6 @@ batch_size = 256
 # %% model configuration
 model = CNNModel(num_classes=num_class)
 criterion = layer.SoftMaxCrossEntropy()
-# optimizer_ft = opt.SGD(lr=0.005, momentum=0.9, weight_decay=1e-5, dtype=singa_dtype["float32"])
 optimizer_ft = opt.Adam(lr=1e-3)
 # optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr=lr)