def subsample_indicator(indicator, num_samples):
"""Subsample indicator vector.
Given a boolean indicator vector with M elements set to `True`, the function
assigns all but `num_samples` of these previously `True` elements to
`False`. If `num_samples` is greater than M, the original indicator vector
is returned.
Arguments:
- *indicator*: a 1-dimensional boolean tensor indicating which elements
are allowed to be sampled and which are not.
- *num_samples*: int32 scalar tensor
Returns:
A boolean tensor with the same shape as input (indicator) tensor
"""
indices = tf.where(indicator)
indices = tf.random.shuffle(indices)
indices = tf.reshape(indices, [-1])
num_samples = tf.minimum(tf.size(indices), num_samples)
selected_indices = tf.slice(indices, [0], tf.reshape(num_samples, [1]))
selected_indicator = ops.indices_to_dense_vector(selected_indices,
tf.shape(indicator)[0])
return tf.equal(selected_indicator, 1)
def test_indices_to_dense_vector_empty_indices_as_input():
size = 500
rand_indices = []
expected_output = np.zeros(size, dtype=np.float32)
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices, size)
np.testing.assert_array_equal(indicator, expected_output)
assert indicator.dtype == expected_output.dtype
def test_indices_to_dense_vector_all_indices_as_input():
size = 500
num_indices = 500
rand_indices = np.random.permutation(np.arange(size))[0:num_indices]
expected_output = np.ones(size, dtype=np.float32)
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices, size)
np.testing.assert_array_equal(indicator, expected_output)
assert indicator.dtype == expected_output.dtype
def test_indices_to_dense_vector():
size = 10000
num_indices = np.random.randint(size)
rand_indices = np.random.permutation(np.arange(size))[0:num_indices]
expected_output = np.zeros(size, dtype=np.float32)
expected_output[rand_indices] = 1.
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices, size)
np.testing.assert_array_equal(indicator, expected_output)
assert indicator.dtype == expected_output.dtype
def test_indices_to_dense_vector_size_at_inference():
size = 5000
num_indices = 250
all_indices = np.arange(size)
rand_indices = np.random.permutation(all_indices)[0:num_indices]
expected_output = np.zeros(size, dtype=np.float32)
expected_output[rand_indices] = 1.
indicator = ops.indices_to_dense_vector(rand_indices,
tf.shape(all_indices)[0])
np.testing.assert_array_equal(indicator, expected_output)
assert indicator.dtype == expected_output.dtype
def test_indices_to_dense_vector_custom_values():
size = 100
num_indices = 10
rand_indices = np.random.permutation(np.arange(size))[0:num_indices]
indices_value = np.random.rand(1)
default_value = np.random.rand(1)
expected_output = np.float32(np.ones(size) * default_value)
expected_output[rand_indices] = indices_value
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices,
size,
indices_value=indices_value,
default_value=default_value)
np.testing.assert_allclose(indicator, expected_output)
assert indicator.dtype == expected_output.dtype