Converting a tensor such that maximum value is 1 and rest is 0

user_12348788 0
Viewed 477

I am struggling with a problem in which I need to convert my tensor such that out of total values, the maximum value gets 1 as a value and rest as 0.

tf.Tensor(
    [[0.05]
     [0.1]
     [0.5]
     [0.35]],shape=(4,1),dtype = float32)

I tried

out = tf.sparse_to_dense(tf.argmax(a),tf.cast(tf.shape(a), dtype=tf.int64), tf.reduce_max(a))

but unfortunately, getting an error as 

Input must be a SparseTensor.

I wanted the output as

tf.Tensor(
    [[0]
     [0]
     [1]
     [0]],shape=(4,1),dtype = float32)

please help me to solve the problem. Thanks a lot

tensor tensorflow deep-learning machine-learning
2 Answers

try in this way

x = tf.constant(
    [[0.05],
     [0.1],
     [0.5],
     [0.35]])

top_values, top_indices = tf.nn.top_k(tf.reshape(x, (-1,)), 1)
tf.cast(tf.greater_equal(x, top_values), tf.float64)

output

<tf.Tensor: shape=(4, 1), dtype=float64, numpy=
array([[0.],
       [0.],
       [1.],
       [0.]])>
user_103750490

Using keras backend K.cast(K.equal(a, K.max(a)), dtype='int8')

import numpy as np

import tensorflow as tf
from tensorflow.keras import backend as K

a = np.arange(0, 1, 0.1)
a = a[:, np.newaxis]

a


array([[0. ],
       [0.1],
       [0.2],
       [0.3],
       [0.4],
       [0.5],
       [0.6],
       [0.7],
       [0.8],
       [0.9]], dtype=float32)

tensor = K.cast(a, dtype='float32')

tensor

<tf.Tensor: shape=(10, 1), dtype=float32, numpy=
array([[0. ],
       [0.1],
       [0.2],
       [0.3],
       [0.4],
       [0.5],
       [0.6],
       [0.7],
       [0.8],
       [0.9]], dtype=float32)>

K.cast(K.equal(a, K.max(a)), dtype='int8')


<tf.Tensor: shape=(10, 1), dtype=int8, numpy=
array([[0],
       [0],
       [0],
       [0],
       [0],
       [0],
       [0],
       [0],
       [0],
       [1]], dtype=int8)>
user_112731240
Related