Btukfyl

When i tried to print out1 and out2 i observed that the values coming in out2 doesnt exist in out1. But out2 is just finding the maximum from out1. Need help

import tensorflow as tf

from keras import backend as K

box_class_probs = tf.random_normal([2, 2, 1, 2], mean=1, stddev=4, seed = 1)

max_ind_class=K.max(box_class_probs,axis=-1)



with tf.Session() as sess:

    out1=sess.run(box_class_probs)

    print(out1)

    out2=sess.run(max_ind_class)

    print(out2)

output:

[[[[-2.24527287  6.93839502]]



  [[ 1.26131749 -8.77081585]]]





 [[[ 1.39699364  3.36489725]]



  [[ 3.37129188 -7.49171829]]]]

---------------------------------------------

---------------------------------------------

---------------------------------------------

[[[ 1.96837616]

  [ 3.06311464]]



 [[ 9.33515644]

  [ 6.58941841]]]

You need to run both of your results in one session run, because you are generating the box_class_probs randomly, and according to the random seed (default or internal), it is going to change every time you execute a session run. And also, keep in mind its always more consistent to get the current keras backend session using K.get_session() and then run your code when you are mixing keras and tensorflow.

sess = K.get_session()

out1, out2 = sess.run([box_class_probs, max_ind_class])

print(out1)

print(out2)

Result:

[[[[-2.2452729  6.938395 ]]



  [[ 1.2613175 -8.770817 ]]]





 [[[ 1.3969936  3.3648973]]



  [[ 3.3712919 -7.4917183]]]]

[[[6.938395 ]

  [1.2613175]]



 [[3.3648973]

  [3.3712919]]]