未验证 提交 98700cee 编写于 作者: Y Yang yaming 提交者: GitHub

Merge pull request #5867 from pkuyym/fix-5865

Fix LaTeX equation for huber_loss_op.cc.
...@@ -70,11 +70,18 @@ input value and Y as the target value. Huber loss can evaluate the fitness of ...@@ -70,11 +70,18 @@ input value and Y as the target value. Huber loss can evaluate the fitness of
X to Y. Different from MSE loss, Huber loss is more robust for outliers. The X to Y. Different from MSE loss, Huber loss is more robust for outliers. The
shape of X and Y are [batch_size, 1]. The equation is: shape of X and Y are [batch_size, 1]. The equation is:
L_{\delta}(y, f(x)) = $$
Out_{\delta}(X, Y)_i =
\begin{cases} \begin{cases}
0.5 * (y - f(x))^2, \quad |y - f(x)| \leq \delta \\ 0.5 * (Y_i - X_i)^2,
\delta * (|y - f(x)| - 0.5 * \delta), \quad otherwise \quad |Y_i - X_i| \leq \delta \\
\delta * (|Y_i - X_i| - 0.5 * \delta),
\quad otherwise
\end{cases} \end{cases}
$$
In the above equation, $Out_\delta(X, Y)_i$, $X_i$ and $Y_i$ represent the ith
element of Out, X and Y.
)DOC"); )DOC");
} }
......
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