tf.boolean_mask

tf.boolean_mask is a function in TensorFlow that allows you to apply a boolean mask to an input tensor and return a new tensor containing only the elements that correspond to True values in the mask. The mask is a boolean tensor with the same shape as the input tensor, and it determines which elements to keep in the output tensor.

Here's an example usage of tf.boolean_mask:

import tensorflow as tf

input_tensor = tf.constant([1, 2, 3, 4, 5])
mask = tf.constant([True, False, True, False, True])

output_tensor = tf.boolean_mask(input_tensor, mask)

print(output_tensor)

Output:

[1 3 5]

In this example, the boolean mask `[True, False, True, False, True]` selects the elements in the input tensor `[1, 2, 3, 4, 5]` at positions where the mask is True. The resulting output tensor contains only the selected elements `[1, 3, 5]`.