tensorflow: how to select rows of matrix with condition -


i find similar solutions here. however, solution makes binary selection between 2 matrices based on 1 condition. need select rows satisfy condition. how can achieve this?

i briefly introduce question here. example :

tf.interactivesession() yt = tf.constant([10,1,10]) = tf.constant([1,2,3]) b = tf.constant([3,4,5]) tf.where(tf.less(yt,[5]), a, b).eval() 

the result choose value a if associated yt value less 5, , otherwise choose value b. need select value a if yt<5, , otherwise not choose anything.

how can achieve this?

thank you!

you can do:

a[tf.squeeze(tf.where(tf.less(yt,[5]), none, none)) 

Comments

Popular posts from this blog

Is there a better way to structure post methods in Class Based Views -

reflection - How to access the object-members of an object declaration in kotlin -

php - Doctrine Query Builder Error on Join: [Syntax Error] line 0, col 87: Error: Expected Literal, got 'JOIN' -