diff --git a/python/paddle/fluid/clip.py b/python/paddle/fluid/clip.py index 79904cec93d1732f9f3f25115869c63385bd6276..32b8f1189fd65ba1e8da5aeaf316fc0ae05af552 100644 --- a/python/paddle/fluid/clip.py +++ b/python/paddle/fluid/clip.py @@ -280,7 +280,7 @@ class GradientClipByGlobalNorm(BaseGradientClipAttr): group_scale_name = self.group_name + "_scale" if group_scale_name not in self.context: group_norm_var = layers.sums(input=self.context[self.group_name]) - layers.sqrt(x=group_norm_var, out=group_norm_var) + group_norm_var = layers.sqrt(x=group_norm_var) clip_var = self.context[self.group_name + "_clip"] group_scale_var = layers.elementwise_div( x=clip_var,