The ML.CONVERT_COLOR_SPACE function

This document describes the ML.CONVERT_COLOR_SPACE scalar function, which lets you convert images that have an RGB color space to a different color space. You can use ML.CONVERT_COLOR_SPACE with the ML.PREDICT function or chain it with other functions or subqueries.

Syntax

ML.CONVERT_COLOR_SPACE(image, target_color_space)

Arguments

ML.CONVERT_COLOR_SPACE takes the following arguments:

• image : a STRUCT value that represents an RGB image in one of the following forms:

  • STRUCT<ARRAY<INT64>, ARRAY<FLOAT64>>
  • STRUCT<ARRAY<INT64>, ARRAY<INT64>>

  The first array in the struct must contain the dimensions of the image. It must contain three INT64 values, which represent the image height (H), width (W), and number of channels (C).

  The second array in the struct must contain the image data. The length of the array must be equivalent to H x W x C from the preceding array. If the image data is in FLOAT64 , each value in the array must be between [0, 1) . If the image data is in INT64 , each value in the array must be between [0, 255) .

  The struct value must be <= 60 MB.

• target_color_space : a STRING value that specifies the target color space. Valid values are HSV , GRAYSCALE , YIQ , and YUV .

Output

ML.CONVERT_COLOR_SPACE returns a STRUCT value that represents the modified image in the form STRUCT<ARRAY<INT64>, ARRAY<FLOAT64>> .

The first array in the struct represents the dimensions of the image, and the second array in the struct contains the image data, similar to the image input argument. Each value in the second array is between [0, 1) .

Example

The following example uses the ML.CONVERT_COLOR_SPACE function within the ML.PREDICT function to change the color space for input images from RGB to GRAYSCALE :

 CREATE 
  
 OR 
  
 REPLACE 
  
 TABLE 
  
 mydataset 
 . 
 model_output 
 AS 
  
 ( 
  
 SELECT 
  
 * 
  
 FROM 
  
 ML 
 . 
 PREDICT 
 ( 
  
 MODEL 
  
 ` 
 mydataset 
 . 
 mymodel 
 ` 
 , 
  
 SELECT 
  
 ML 
 . 
 CONVERT_COLOR_SPACE 
 ( 
 ML 
 . 
 DECODE_IMAGE 
 ( 
 data 
 ), 
  
 'GRAYSCALE' 
 ) 
  
 AS 
  
 image 
 , 
  
 uri 
  
 FROM 
  
 ` 
 mydataset 
 . 
 images 
 ` 
 ) 
 ); 

What's next

• For information about feature preprocessing, see Feature preprocessing overview .
• For information about the supported SQL statements and functions for each model type, see End-to-end user journey for each model .