未验证 提交 36dc2ef1 编写于 作者: W Walter 提交者: GitHub

Update MobileNetV3_large_x1_0_quantization.yaml

上级 8e85ef47
...@@ -43,7 +43,7 @@ Optimizer: ...@@ -43,7 +43,7 @@ Optimizer:
lr: lr:
name: Cosine name: Cosine
learning_rate: 0.065 learning_rate: 0.065
warmup_epoch: 5 warmup_epoch: 0
regularizer: regularizer:
name: 'L2' name: 'L2'
coeff: 0.00002 coeff: 0.00002
......
Markdown is supported
0% .
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