Getting multiple results in regression using deep learning

Question

Given the RGB image of the hand and the 3d position of the key points of the hand as a dataset, I want to do this as a regression problem in DL. In this case, the input will be an RGB image, and the output should be evaluated as the 3D position of the key points.
I saw some information about regression, but most of them are trying to evaluate a single value. Is it possible to immediately evaluate several values ​​(or conclusions)?

I have currently mentioned this code . This guy is trying to assess the age of a person in an image.

Answer 1

, . , (x, y, z) 10 , 30- (x1, y1, z1, x2, y2, z2.............., x10, y10, z10), xi, yi, zi i- , , . . , RMSE, , RMSE , , 3x10 3x10

loss = tf.sqrt(tf.reduce_mean(tf.squared_difference(Y1, Y2))) 

, .