def test_smooth(
self,
value: float,
smooth_nr: float,
smooth_dr: float,
expected: float,
):
"""
Test values in extreme cases where numerator/denominator are all zero.
:param value: value for input.
:param smooth_nr: constant for numerator.
:param smooth_dr: constant for denominator.
:param expected: target value.
"""
shape = (1, 10)
y_true = tf.ones(shape=shape) * value
y_pred = tf.ones(shape=shape) * value
got = label.JaccardIndex(smooth_nr=smooth_nr,
smooth_dr=smooth_dr).call(
y_true,
y_pred,
)
expected = tf.constant(expected)
assert is_equal_tf(got[0], expected)
def test_get_config(self):
got = label.JaccardIndex().get_config()
expected = dict(
binary=False,
scales=None,
kernel="gaussian",
reduction=tf.keras.losses.Reduction.SUM,
name="JaccardIndex",
)
assert got == expected
def test_call(self, y_true, y_pred, binary, scales, expected):
expected = np.array([expected] *
self.shape[0]) # call returns (batch, )
got = label.JaccardIndex(binary=binary,
scales=scales).call(y_true=y_true,
y_pred=y_pred)
assert is_equal_tf(got, expected)
got = label.JaccardLoss(binary=binary,
scales=scales).call(y_true=y_true,
y_pred=y_pred)
assert is_equal_tf(got, -expected)
def test_get_config(self):
got = label.JaccardIndex().get_config()
expected = dict(
binary=False,
background_weight=0.0,
smooth_nr=1e-5,
smooth_dr=1e-5,
reduction=tf.keras.losses.Reduction.AUTO,
name="JaccardIndex",
)
assert got == expected
def test_exact_value(self, binary: bool, background_weight: float,
shape: Tuple):
"""
Test Jaccard index by comparing at ground truth values.
:param binary: if project labels to binary values.
:param background_weight: the weight of background class.
:param shape: shape of input.
"""
# init
shape = (1, ) + shape # add batch axis
foreground_weight = 1 - background_weight
tf.random.set_seed(0)
y_true = tf.random.uniform(shape=shape)
y_pred = tf.random.uniform(shape=shape)
# obtained value
got = label.JaccardIndex(
binary=binary,
background_weight=background_weight,
).call(y_true=y_true, y_pred=y_pred)
# expected value
flatten = tf.keras.layers.Flatten()
y_true = flatten(y_true)
y_pred = flatten(y_pred)
if binary:
y_true = tf.cast(y_true >= 0.5, dtype=y_true.dtype)
y_pred = tf.cast(y_pred >= 0.5, dtype=y_pred.dtype)
num = foreground_weight * tf.reduce_sum(
y_true * y_pred, axis=1) + background_weight * tf.reduce_sum(
(1 - y_true) * (1 - y_pred), axis=1)
denom = foreground_weight * tf.reduce_sum(
y_true + y_pred, axis=1) + background_weight * tf.reduce_sum(
(1 - y_true) + (1 - y_pred), axis=1)
denom = denom - num
expected = (num + EPS) / (denom + EPS)
assert is_equal_tf(got, expected)