未验证 提交 a66a488c 编写于 作者: L lilong12 提交者: GitHub

align to mxnet (#41)

上级 d0b9710b
...@@ -126,7 +126,7 @@ class ResNet(BaseModel): ...@@ -126,7 +126,7 @@ class ResNet(BaseModel):
return input return input
def bottleneck_block(self, input, num_filters, stride, is_train): def bottleneck_block(self, input, num_filters, stride, is_train):
if self.layers < 101: if self.layers < 500:
bn1 = fluid.layers.batch_norm(input=input, bn1 = fluid.layers.batch_norm(input=input,
act=None, act=None,
epsilon=2e-05, epsilon=2e-05,
......
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