Difficulty: Easy Tags: Computer Vision, Data Processing
Netflix normalizes every uploaded artwork candidate before it reaches the thumbnail-ranking CNN. Get the normalization wrong and the model silently sees out-of-distribution inputs with no error thrown anywhere.
x' = (x - mu) / sigma
where mu and sigma are the mean and population standard deviation of the pixel values in
the given image.
H W
p_1,1 ... p_1,W
...
p_H,1 ... p_H,W
First line: mu and sigma. Then the H x W normalized matrix, row by row, all to 6 decimals.
1 <= H, W <= 512Input
2 2
100 150
200 250
Output
175.000000 55.901699
-1.341641 -0.447214
0.447214 1.341641
No results yet
Run your code to check it against the examples, or submit to run every test.