Function implementation in keras tensorflow

Question

Suppose I´ve got three tensors shape (n,1) T,r,E and I wanted to implement a function that calculates: sum(i,j) (T[j] < T[i]) (r[j] > r[i]) E[j]. How can I proceed?

This is what I´ve got

#tensor examples
T=K.constant([1,4,5])
r=K.constant([.8,.3,.7])
E=K.constant([1,0,1])

# cartesian product of T to compare element wise
c = tf.stack(tf.meshgrid(T, T, indexing='ij'), axis=-1)
cartesian_T = tf.reshape(c, (-1, 2))

# cartesian product of r to compare elemento wise
r = tf.stack(tf.meshgrid(r, r, indexing='ij'), axis=-1)
cartesian_r = tf.reshape(r, (-1, 2))

# TO DO: 
# compare the two columns in cartesian T and cast to integer 1/0 if  
# second column in T less/greater than first column in T => return tensor


# compare the two columns in cartesian E and cast to integer 1/0 if  
# second column in r greater/less than first column in r => return tensor

# multiply previous tensors by a broadcasted version of E, then do K.sum()

Do you think I'm on the right track? What would you suggest to implement this?

Can you give the output you expect in your example when T=[1,4,5] & r=[.8,.3,.7] & E=[1,0,1]? — giser_yugang
– giser_yugang, Commented Jun 6, 2019 at 3:53

giser_yugang · Accepted Answer · 2019-06-14 01:53:37Z

1

Try:

import keras.backend as K
import tensorflow as tf

T=K.constant([1,4,5])
r=K.constant([.8,.3,.7])
E=K.constant([1,0,1])

T_new = tf.less(T[tf.newaxis,:],T[:,tf.newaxis])
r_new = tf.greater(r[tf.newaxis,:],r[:,tf.newaxis])
E_row,_ = tf.meshgrid(E, E)
result = tf.reduce_sum(tf.boolean_mask(E_row,tf.logical_and(T_new,r_new)))

with tf.Session() as sess:
    print(sess.run(result))

#print
2.0

edited Jun 14, 2019 at 1:53

answered Jun 6, 2019 at 11:28

giser_yugang

6,1864 gold badges24 silver badges47 bronze badges

Sign up to request clarification or add additional context in comments.

7 Comments

Juan Castaño Over a year ago

Great! This it it! So grateful!

giser_yugang Over a year ago

@JuanCastaño Please accept the answer if you have no question.

Juan Castaño Over a year ago

I've implemented the function; however when the tensors are big, it blows the memory; do you happen to think of a more performatic implementation?

giser_yugang Over a year ago

@JuanCastaño How about the updated code? But I think the best way is to reduce batch size.

giser_yugang Over a year ago

@JuanCastaño Did you use tf.placeholder to feed data?

|

Collectives™ on Stack Overflow

Function implementation in keras tensorflow

1 Answer 1

7 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

7 Comments

Your Answer

Sign up or log in

Post as a guest

Related