Substitute model output to binary form - numpy

Question

I've model output like this,
<tf.Tensor: shape=(3,), dtype=float32, numpy=array([0.92, 0.2 , 0.77], dtype=float32)>> but I want to change max value in array to 1, and other values to 0. If there are two and more maximum value it should be changed to zero array.
For example:
[0.92, 0.2 , 0.77] -> [1.0,0.0,0.0],
[0.92, 0.92 , 0.77] -> [0.0,0.0,0.0]
I know how to make it by np.argmax, but I wanna do this by the keras.layers because summarize the outputs after that and want to do it in binary mode?
I've made custom layer like this, but unfortunately can't compile it
class Amplifier(tf.keras.layers.Layer):
def __init__(self):
super(Amplifier, self).__init__()
# pattern 2D matrix
self.f = tf.constant(
[[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]], dtype='float32')
def call(self, inputs, training=None, mask=None):
# return index of max value
x = tf.math.argmax(
inputs,
axis=None,
output_type=tf.dtypes.int32,
name=None)
# get factor from f constant as 1D matrix form
y = tf.reshape(tf.slice(self.f, [x, 0], [1, 3]), [3])
# multiply input on the pattern matrix
return tf.math.multiply(inputs, y)
I got this error:
ValueError: Tried to convert 'begin' to a tensor and failed. Error: Shapes must be equal rank, but are 1 and 0
From merging shape 0 with other shapes. for '{{node amplifier/Slice/packed}} = Pack[N=2, T=DT_INT32, axis=0](amplifier/ArgMax, amplifier/Slice/packed/1)' with input shapes: [3], [].
I don't know how to avoid this mistake

Answer 1

I think what you are asking is if you can have your output be in tf.one_hot format (correct?). If you just want to report on this output, then you can use a combination of argmax and one_hot. If you want this to be part of your gradient calculation in your network, you need a numerically stable one_hot. Try something like this:
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense
class OneHotLayer(layers.Layer):
def __init__(self, num_labels=3, do_numerical=False):
super().__init__()
# large constant used in masking softmax
self._inf = 1e9
# how many categories we have
self.num_labels = num_labels
# if we need our `one_hot` to be numerically stable
self.do_numerical = do_numerical
# dense layer; the last layer of our network
self.probs = Dense(self.num_labels, activation="softmax")
# this is a numerically stable `one_hot` method.
# it looks for the max across rows, subtracts that from
# the original tensor (across rows) and exponentiates.
# this will make the largest value 1.0. Then we create a
# mask and zero out all other values (again, across rows)
# leaving us with a binary matrix.
def _numerical_one_hot(self, x):
m = tf.math.reduce_max(x, axis=1, keepdims=True)
e = tf.math.exp(x - m)
mask = tf.cast(tf.math.not_equal(e, 1.0), tf.float32)
x = x - self._inf * mask
return tf.nn.softmax(x, axis=1)
def call(self, x):
# do forward pass through last layer
x = self.probs(x)
# do we need numerical stability? If we do use the
# op we created. If not, then take the argmax across
# rows and then use `tf.one_hot`; return both
ohx = self._numerical_one_hot(x) \
if self.do_numerical \
else tf.one_hot(tf.math.argmax(x, axis=1), self.num_labels)
return x, ohx
Data:
# fake data
X = tf.random.normal([8, 10])
y = tf.random.uniform(
shape=[8,],
minval=0,
maxval=3,
dtype=tf.int64)
y = tf.one_hot(y, 3)
Test numerical stability network:
# network with stable one_hot
x_in = tf.keras.Input((10,))
x = Dense(25)(x_in)
x_probs, x_indices = OneHotLayer(3, True)(x)
# ^
# ------------------------------------|
# model
model = tf.keras.Model(x_in, [x_probs, x_indices])
probs, idxs = model(X)
# ^^^ this can be used in loss calc if you need it
print(probs)
# tf.Tensor(
# [[0.12873407 0.83047885 0.04078702]
# [0.22919412 0.1288479 0.641958 ]
# [0.27402356 0.35891128 0.36706516]
# [0.1328154 0.3546107 0.51257384]
# [0.5309519 0.10788985 0.36115825]
# [0.35019153 0.272698 0.37711048]
# [0.35740596 0.23807809 0.4045159 ]
# [0.13749316 0.72042704 0.14207976]],
# shape=(8, 3), # dtype=float32)
print(idxs)
# tf.Tensor(
# [[0. 1. 0.]
# [0. 0. 1.]
# [0. 0. 1.]
# [0. 0. 1.]
# [1. 0. 0.]
# [0. 0. 1.]
# [0. 0. 1.]
# [0. 1. 0.]],
# shape=(8, 3), dtype=float32)
Test built-in one-hot network:
# network using argmax and built-in one_hot
x_in = tf.keras.Input((10,))
x = Dense(25)(x_in)
x_probs, x_indices = OneHotLayer(3, False)(x)
# ^
# ------------------------------------|
# model
model = tf.keras.Model(x_in, [x_probs, x_indices])
probs, idxs = model(X)
print(probs)
# tf.Tensor(
# [[0.28931475 0.33777648 0.3729088 ]
# [0.25985113 0.532114 0.20803489]
# [0.4226228 0.21078317 0.36659405]
# [0.460703 0.3534157 0.18588138]
# [0.6028035 0.26571727 0.13147917]
# [0.1994377 0.4208928 0.37966955]
# [0.39812535 0.33319235 0.26868224]
# [0.13242716 0.47491995 0.3926528 ]],
# shape=(8, 3), dtype=float32)
print(idxs)
# tf.Tensor(
# [[0. 0. 1.]
# [0. 1. 0.]
# [1. 0. 0.]
# [1. 0. 0.]
# [1. 0. 0.]
# [0. 1. 0.]
# [1. 0. 0.]
# [0. 1. 0.]],
# shape=(8, 3), dtype=float32)