rmse

Functions

int main(int argc, char *argv[])

rmse [ option ] file1 [ infile ]

-l int
- length of vector \((1 \le L)\)
-m int
- order of vector \((0 \le L - 1)\)
-magic double
- remove magic number
-f
- output RMSE frame-by-frame
file1 str
- double-type data sequence
infile str
- double-type data sequence
stdout
- double-type RMSE

The inputs of this command are

\[ \begin{array}{ccc} \underbrace{x_0(0), \; \ldots, \; x_0(L-1)}_L, & \underbrace{x_1(0), \; \ldots, \; x_1(L-1)}_L, & \ldots, \end{array} \]

and

\[ \begin{array}{ccc} \underbrace{y_0(0), \; \ldots, \; y_0(L-1)}_L, & \underbrace{y_1(0), \; \ldots, \; y_1(L-1)}_L, & \ldots, \end{array} \]

and the output is the sequence of RMSE:

\[ \begin{array}{ccc} e_0, & e_1, & \ldots, \end{array} \]

where

\[ e_n = \sqrt{\frac{1}{L} \sum_{l=0}^{L-1} (x_n(l) - y_n(l))^2}. \]

If -f option is not specified, the average of RMSEs is calculated.

echo 1 2 3 | x2x +ad > data.1
echo 0 4 3 | x2x +ad > data.2
rmse data.1 data.2 -l 1 -f | x2x +da
# 1 2 0
rmse data.1 data.2 -l 1 | x2x +da
# 1
rmse data.1 data.2 | x2x +da
# 1.29099