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.
Args:
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 _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape, either [batch_size, num_anchors,
num_classes] or [batch_size, num_anchors, 1]. If the shape is
[batch_size, num_anchors, 1], all the classses are equally weighted.
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a float tensor of shape [batch_size, num_anchors, num_classes]
representing the value of the loss function.
"""
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
return per_entry_cross_ent * weights
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a float tensor of shape [batch_size, num_anchors, num_classes]
representing the value of the loss function.
"""
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
return per_entry_cross_ent * weights
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a (scalar) tensor representing the value of the loss function
or a float tensor of shape [batch_size, num_anchors]
"""
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
preds = tf.nn.sigmoid(prediction_tensor)
preds = tf.where(tf.equal(target_tensor, 1), preds, 1. - preds)
losses = -(1. - preds)**self._gamma * tf.log(preds + self._epsilon)
if self._anchorwise_output:
return tf.reduce_sum(losses * weights, 2)
return tf.reduce_sum(losses * weights)
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a (scalar) tensor representing the value of the loss function
or a float tensor of shape [batch_size, num_anchors]
"""
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
if self._anchorwise_output:
return tf.reduce_sum(per_entry_cross_ent * weights, 2)
return tf.reduce_sum(per_entry_cross_ent * weights)
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.
Args:
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 _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Computes the loss value.
Dice loss uses the area of the ground truth and prediction tensors for
normalization. We compute area by summing along the anchors (2nd) dimension.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_pixels,
num_classes] representing the predicted logits for each class.
num_pixels denotes the total number of pixels in the spatial dimensions
of the mask after flattening.
target_tensor: A float tensor of shape [batch_size, num_pixels,
num_classes] representing one-hot encoded classification targets.
num_pixels denotes the total number of pixels in the spatial dimensions
of the mask after flattening.
weights: a float tensor of shape, either [batch_size, num_anchors,
num_classes] or [batch_size, num_anchors, 1]. If the shape is
[batch_size, num_anchors, 1], all the classses are equally weighted.
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a float tensor of shape [batch_size, num_classes]
representing the value of the loss function.
"""
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
if self.is_prediction_probability:
prob_tensor = prediction_tensor
else:
prob_tensor = tf.nn.sigmoid(prediction_tensor)
if self._squared_normalization:
prob_tensor = tf.pow(prob_tensor, 2)
target_tensor = tf.pow(target_tensor, 2)
prob_tensor *= weights
target_tensor *= weights
prediction_area = tf.reduce_sum(prob_tensor, axis=1)
gt_area = tf.reduce_sum(target_tensor, axis=1)
intersection = tf.reduce_sum(prob_tensor * target_tensor, axis=1)
dice_coeff = 2 * intersection / tf.maximum(gt_area + prediction_area,
1.0)
dice_loss = 1 - dice_coeff
return dice_loss
def test_indices_to_dense_vector_empty_indices_as_input(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def test_indices_to_dense_vector_empty_indices_as_input(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def test_indices_to_dense_vector_all_indices_as_input(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def test_indices_to_dense_vector_all_indices_as_input(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
# Weights are the upper bounds.
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
return (per_entry_cross_ent *
tf.cast(prediction_tensor < weights, tf.float32))
def test_indices_to_dense_vector_int(self):
size = 500
num_indices = 25
rand_indices = np.random.permutation(np.arange(size))[0:num_indices]
expected_output = np.zeros(size, dtype=np.int64)
expected_output[rand_indices] = 1
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(
tf_rand_indices, size, 1, dtype=tf.int64)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def test_indices_to_dense_vector_int(self):
size = 500
num_indices = 25
rand_indices = np.random.permutation(np.arange(size))[0:num_indices]
expected_output = np.zeros(size, dtype=np.int64)
expected_output[rand_indices] = 1
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(
tf_rand_indices, size, 1, dtype=tf.int64)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def fn(x, positive_fraction=positive_fraction):
'''
pick indicies from valid_inds. If
positive_fraction is not None use labels
to do balanecd sampling.
'''
labels, valid_inds = x
indicators = ops.indices_to_dense_vector(
valid_inds,
tf.shape(labels)[0])
indicators = tf.cast(indicators, tf.bool)
if positive_fraction is None:
positive_fraction = 1.0
labels = tf.ones_like(labels, tf.bool)
return util.balanced_subsample(indicators, labels,
self._ncobj_proposals,
positive_fraction)
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
# Directly regress to soft targets.
# target_tensor = tf.concat([1 - weights, weights], axis=-1)
# per_entry_cross_ent = (tf.nn.softmax_cross_entropy_with_logits_v2(
# labels=target_tensor, logits=prediction_tensor))
per_entry_cross_ent = tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor * weights, logits=prediction_tensor)
return per_entry_cross_ent
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a (scalar) tensor representing the value of the loss function
or a float tensor of shape [batch_size, num_anchors]
"""
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
prediction_probabilities = tf.sigmoid(prediction_tensor)
p_t = ((target_tensor * prediction_probabilities) +
((1 - target_tensor) * (1 - prediction_probabilities)))
modulating_factor = 1.0
if self._gamma:
modulating_factor = tf.pow(1.0 - p_t, self._gamma)
alpha_weight_factor = 1.0
if self._alpha is not None:
alpha_weight_factor = (target_tensor * self._alpha +
(1 - target_tensor) * (1 - self._alpha))
focal_cross_entropy_loss = (modulating_factor * alpha_weight_factor *
per_entry_cross_ent)
if self._anchorwise_output:
return tf.reduce_sum(focal_cross_entropy_loss * weights, 2)
return tf.reduce_sum(focal_cross_entropy_loss * weights)
def test_indices_to_dense_vector_size_at_inference(self):
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.
tf_all_indices = tf.placeholder(tf.int32)
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices,
tf.shape(tf_all_indices)[0])
feed_dict = {tf_all_indices: all_indices}
with self.test_session() as sess:
output = sess.run(indicator, feed_dict=feed_dict)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def test_indices_to_dense_vector_size_at_inference(self):
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.
tf_all_indices = tf.placeholder(tf.int32)
tf_rand_indices = tf.constant(rand_indices)
indicator = ops.indices_to_dense_vector(tf_rand_indices,
tf.shape(tf_all_indices)[0])
feed_dict = {tf_all_indices: all_indices}
with self.test_session() as sess:
output = sess.run(indicator, feed_dict=feed_dict)
self.assertAllEqual(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a (scalar) tensor representing the value of the loss function
or a float tensor of shape [batch_size, num_anchors]
"""
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
prediction_probabilities = tf.sigmoid(prediction_tensor)
p_t = ((target_tensor * prediction_probabilities) +
((1 - target_tensor) * (1 - prediction_probabilities)))
modulating_factor = 1.0
if self._gamma:
modulating_factor = tf.pow(1.0 - p_t, self._gamma)
alpha_weight_factor = 1.0
if self._alpha is not None:
alpha_weight_factor = (target_tensor * self._alpha +
(1 - target_tensor) * (1 - self._alpha))
focal_cross_entropy_loss = (modulating_factor * alpha_weight_factor *
per_entry_cross_ent)
if self._anchorwise_output:
return tf.reduce_sum(focal_cross_entropy_loss * weights, 2)
return tf.reduce_sum(focal_cross_entropy_loss * weights)
def test_indices_to_dense_vector_custom_values(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllClose(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def _compute_loss(self,
prediction_tensor,
target_tensor,
weights,
class_indices=None):
# Weights are the upper bounds.
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
squared_dist = tf.square(
tf.sigmoid(prediction_tensor) - target_tensor) * 20.
above_conf = tf.cast(prediction_tensor > weights, tf.float32)
# Apply quadratic loss if predictions go above soft target.
loss = per_entry_cross_ent + above_conf * squared_dist
return loss
def test_indices_to_dense_vector_custom_values(self):
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)
with self.test_session() as sess:
output = sess.run(indicator)
self.assertAllClose(output, expected_output)
self.assertEqual(output.dtype, expected_output.dtype)
def _compute_loss(
self,
prediction_tensor, #get the prediction
target_tensor,
weights, #This is the obtained weigts 1or zero based on the similarity default box to grount truth box
class_indices=None):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing the predicted logits for each class
target_tensor: A float tensor of shape [batch_size, num_anchors,
num_classes] representing one-hot encoded classification targets
weights: a float tensor of shape [batch_size, num_anchors]
class_indices: (Optional) A 1-D integer tensor of class indices.
If provided, computes loss only for the specified class indices.
Returns:
loss: a (scalar) tensor representing the value of the loss function
or a float tensor of shape [batch_size, num_anchors]
"""
#normal way of calculating z * -log(sigmoid(x)) + (1 - z) * -log(1 - sigmoid(x)) (z is the class labels , x is the prediction )
#reed tensorflow if needed z labels ,x is score or logit
#This is good if we have probabilistic labels , not 1 or zero hard labels
weights = tf.expand_dims(weights, 2)
if class_indices is not None:
weights *= tf.reshape(
ops.indices_to_dense_vector(class_indices,
tf.shape(prediction_tensor)[2]),
[1, 1, -1])
per_entry_cross_ent = (tf.nn.sigmoid_cross_entropy_with_logits(
labels=target_tensor, logits=prediction_tensor))
if self._anchorwise_output:
return tf.reduce_sum(per_entry_cross_ent * weights, 2)
return tf.reduce_sum(per_entry_cross_ent * weights)