def test_unequal_static_shape_along_first_dim_raises_exception(self):
shape_a = tf.constant(np.zeros([4, 2, 2, 1]))
shape_b = tf.constant(np.zeros([6, 2, 3, 1]))
with self.assertRaisesRegex(ValueError, 'Unequal first dimension'):
shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(shape_a),
shape_utils.combined_static_and_dynamic_shape(shape_b))
def graph_fn():
shape_a = tf.constant(np.zeros([4, 2, 2, 1]))
shape_b = tf.constant(np.zeros([4, 7, 2]))
shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(shape_a),
shape_utils.combined_static_and_dynamic_shape(shape_b))
return tf.constant(0)
def test_unequal_static_shape_along_first_dim_raises_exception(self):
shape_a = tf.constant(np.zeros([4, 2, 2, 1]))
shape_b = tf.constant(np.zeros([6, 2, 3, 1]))
with self.assertRaisesRegexp(
ValueError, 'Unequal first dimension'):
shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(shape_a),
shape_utils.combined_static_and_dynamic_shape(shape_b))
def test_equal_static_shape_along_first_dim_succeeds(self):
shape_a = tf.constant(np.zeros([4, 2, 2, 1]))
shape_b = tf.constant(np.zeros([4, 7, 2]))
with self.test_session() as sess:
op = shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(shape_a),
shape_utils.combined_static_and_dynamic_shape(shape_b))
sess.run(op)
def test_equal_dynamic_shape_along_first_dim_succeeds(self):
tensor_a = tf.placeholder(tf.float32, shape=[None, None, None, 3])
tensor_b = tf.placeholder(tf.float32, shape=[None])
op = shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(tensor_a),
shape_utils.combined_static_and_dynamic_shape(tensor_b))
with self.test_session() as sess:
sess.run(op, feed_dict={tensor_a: np.zeros([5, 2, 2, 3]),
tensor_b: np.zeros([5])})
def test_unequal_dynamic_shape_along_first_dim_raises_tf_assert(self):
tensor_a = tf.placeholder(tf.float32, shape=[None, None, None, 3])
tensor_b = tf.placeholder(tf.float32, shape=[None, None, 3])
op = shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(tensor_a),
shape_utils.combined_static_and_dynamic_shape(tensor_b))
with self.test_session() as sess:
with self.assertRaises(tf.errors.InvalidArgumentError):
sess.run(op, feed_dict={tensor_a: np.zeros([1, 2, 2, 3]),
tensor_b: np.zeros([2, 4, 3])})
def merge_boxes_with_multiple_labels(boxes,
classes,
confidences,
num_classes,
quantization_bins=10000):
"""Merges boxes with same coordinates and returns K-hot encoded classes.
Args:
boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. Only
normalized coordinates are allowed.
classes: A tf.int32 tensor with shape [N] holding class indices.
The class index starts at 0.
confidences: A tf.float32 tensor with shape [N] holding class confidences.
num_classes: total number of classes to use for K-hot encoding.
quantization_bins: the number of bins used to quantize the box coordinate.
Returns:
merged_boxes: A tf.float32 tensor with shape [N', 4] holding boxes,
where N' <= N.
class_encodings: A tf.int32 tensor with shape [N', num_classes] holding
K-hot encodings for the merged boxes.
confidence_encodings: A tf.float32 tensor with shape [N', num_classes]
holding encodings of confidences for the merged boxes.
merged_box_indices: A tf.int32 tensor with shape [N'] holding original
indices of the boxes.
"""
boxes_shape = tf.shape(boxes)
classes_shape = tf.shape(classes)
confidences_shape = tf.shape(confidences)
box_class_shape_assert = shape_utils.assert_shape_equal_along_first_dimension(
boxes_shape, classes_shape)
box_confidence_shape_assert = (
shape_utils.assert_shape_equal_along_first_dimension(
boxes_shape, confidences_shape))
box_dimension_assert = tf.assert_equal(boxes_shape[1], 4)
box_normalized_assert = shape_utils.assert_box_normalized(boxes)
with tf.control_dependencies([
box_class_shape_assert, box_confidence_shape_assert,
box_dimension_assert, box_normalized_assert
]):
quantized_boxes = tf.to_int64(boxes * (quantization_bins - 1))
ymin, xmin, ymax, xmax = tf.unstack(quantized_boxes, axis=1)
hashcodes = (
ymin + xmin * quantization_bins +
ymax * quantization_bins * quantization_bins +
xmax * quantization_bins * quantization_bins * quantization_bins)
unique_hashcodes, unique_indices = tf.unique(hashcodes)
num_boxes = tf.shape(boxes)[0]
num_unique_boxes = tf.shape(unique_hashcodes)[0]
merged_box_indices = tf.unsorted_segment_min(tf.range(num_boxes),
unique_indices,
num_unique_boxes)
merged_boxes = tf.gather(boxes, merged_box_indices)
def map_box_encodings(i):
"""Produces box K-hot and score encodings for each class index."""
box_mask = tf.equal(unique_indices,
i * tf.ones(num_boxes, dtype=tf.int32))
box_mask = tf.reshape(box_mask, [-1])
box_indices = tf.boolean_mask(classes, box_mask)
box_confidences = tf.boolean_mask(confidences, box_mask)
box_class_encodings = tf.sparse_to_dense(box_indices,
[num_classes],
1,
validate_indices=False)
box_confidence_encodings = tf.sparse_to_dense(
box_indices, [num_classes],
box_confidences,
validate_indices=False)
return box_class_encodings, box_confidence_encodings
class_encodings, confidence_encodings = tf.map_fn(
map_box_encodings,
tf.range(num_unique_boxes),
back_prop=False,
dtype=(tf.int32, tf.float32))
merged_boxes = tf.reshape(merged_boxes, [-1, 4])
class_encodings = tf.reshape(class_encodings, [-1, num_classes])
confidence_encodings = tf.reshape(confidence_encodings,
[-1, num_classes])
merged_box_indices = tf.reshape(merged_box_indices, [-1])
return (merged_boxes, class_encodings, confidence_encodings,
merged_box_indices)
def merge_boxes_with_multiple_labels(boxes,
classes,
confidences,
num_classes,
quantization_bins=10000):
"""Merges boxes with same coordinates and returns K-hot encoded classes.
Args:
boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. Only
normalized coordinates are allowed.
classes: A tf.int32 tensor with shape [N] holding class indices.
The class index starts at 0.
confidences: A tf.float32 tensor with shape [N] holding class confidences.
num_classes: total number of classes to use for K-hot encoding.
quantization_bins: the number of bins used to quantize the box coordinate.
Returns:
merged_boxes: A tf.float32 tensor with shape [N', 4] holding boxes,
where N' <= N.
class_encodings: A tf.int32 tensor with shape [N', num_classes] holding
K-hot encodings for the merged boxes.
confidence_encodings: A tf.float32 tensor with shape [N', num_classes]
holding encodings of confidences for the merged boxes.
merged_box_indices: A tf.int32 tensor with shape [N'] holding original
indices of the boxes.
"""
boxes_shape = tf.shape(boxes)
classes_shape = tf.shape(classes)
confidences_shape = tf.shape(confidences)
box_class_shape_assert = shape_utils.assert_shape_equal_along_first_dimension(
boxes_shape, classes_shape)
box_confidence_shape_assert = (
shape_utils.assert_shape_equal_along_first_dimension(
boxes_shape, confidences_shape))
box_dimension_assert = tf.assert_equal(boxes_shape[1], 4)
box_normalized_assert = shape_utils.assert_box_normalized(boxes)
with tf.control_dependencies(
[box_class_shape_assert, box_confidence_shape_assert,
box_dimension_assert, box_normalized_assert]):
quantized_boxes = tf.to_int64(boxes * (quantization_bins - 1))
ymin, xmin, ymax, xmax = tf.unstack(quantized_boxes, axis=1)
hashcodes = (
ymin +
xmin * quantization_bins +
ymax * quantization_bins * quantization_bins +
xmax * quantization_bins * quantization_bins * quantization_bins)
unique_hashcodes, unique_indices = tf.unique(hashcodes)
num_boxes = tf.shape(boxes)[0]
num_unique_boxes = tf.shape(unique_hashcodes)[0]
merged_box_indices = tf.unsorted_segment_min(
tf.range(num_boxes), unique_indices, num_unique_boxes)
merged_boxes = tf.gather(boxes, merged_box_indices)
def map_box_encodings(i):
"""Produces box K-hot and score encodings for each class index."""
box_mask = tf.equal(
unique_indices, i * tf.ones(num_boxes, dtype=tf.int32))
box_mask = tf.reshape(box_mask, [-1])
box_indices = tf.boolean_mask(classes, box_mask)
box_confidences = tf.boolean_mask(confidences, box_mask)
box_class_encodings = tf.sparse_to_dense(
box_indices, [num_classes], 1, validate_indices=False)
box_confidence_encodings = tf.sparse_to_dense(
box_indices, [num_classes], box_confidences, validate_indices=False)
return box_class_encodings, box_confidence_encodings
class_encodings, confidence_encodings = tf.map_fn(
map_box_encodings,
tf.range(num_unique_boxes),
back_prop=False,
dtype=(tf.int32, tf.float32))
merged_boxes = tf.reshape(merged_boxes, [-1, 4])
class_encodings = tf.reshape(class_encodings, [-1, num_classes])
confidence_encodings = tf.reshape(confidence_encodings, [-1, num_classes])
merged_box_indices = tf.reshape(merged_box_indices, [-1])
return (merged_boxes, class_encodings, confidence_encodings,
merged_box_indices)
def graph_fn(tensor_a, tensor_b):
shape_utils.assert_shape_equal_along_first_dimension(
shape_utils.combined_static_and_dynamic_shape(tensor_a),
shape_utils.combined_static_and_dynamic_shape(tensor_b))
return tf.constant(0)
