Skip to content

A
Annotated Deep Learning Paper Implementations

Greenplum / Annotated Deep Learning Paper Implementations
11 个月 前同步成功

通知 6
Star 0
Fork 0
A
Annotated Deep Learning Paper Implementations

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 b2b305ff 编写于 作者: V Varuna Jayasiri
浏览文件
操作

optim configs

上级 19bd8b8e
隐藏空白更改
内联 并排
Showing with 4 addition and 4 deletion
labml_nn/gan/mnist.py
浏览文件 @ b2b305ff
......@@ -171,8 +171,8 @@ def _discriminator_optimizer(c: Configs):
opt_conf = OptimizerConfigs()
opt_conf.optimizer = 'Adam'
opt_conf.parameters = c.discriminator.parameters()
opt_conf.learning_rate = 2.5e-5
# opt_conf.betas = (0.5, 0.999)
opt_conf.learning_rate = 2.5e-4
opt_conf.betas = (0.5, 0.999)
return opt_conf
......@@ -181,8 +181,8 @@ def _generator_optimizer(c: Configs):
opt_conf = OptimizerConfigs()
opt_conf.optimizer = 'Adam'
opt_conf.parameters = c.generator.parameters()
opt_conf.learning_rate = 2.5e-5
# opt_conf.betas = (0.5, 0.999)
opt_conf.learning_rate = 2.5e-4
opt_conf.betas = (0.5, 0.999)
return opt_conf
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或