提交 1ed31b4e 编写于 作者: H hedaoyuan

Bug fix.

上级 c6e010d0
7 合并请求!11636[IMPORTANT] MKLDNN layout: Support for sum operator,!8482Release/0.11.0,!8190Release/0.11.0,!8189Release/0.11.0,!6633给线性回归的get-started代码加上了预测的示例~~,!4615Feature/tensor array add python binding,!2282Add convolution Function
......@@ -104,11 +104,11 @@ public:
protected:
size_t getFilterHeight(const TensorShape& filter) const {
filter[filter.ndims() - 2];
return filter[filter.ndims() - 2];
}
size_t getFilterWidth(const TensorShape& filter) const {
filter[filter.ndims() - 1];
return filter[filter.ndims() - 1];
}
std::vector<size_t> strides_;
......
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
反馈
建议
客服 返回
顶部