def _build_training_batch_dict(batch_sequences_with_states, unroll_length,
batch_size):
"""Builds training batch samples.
Args:
batch_sequences_with_states: A batch_sequences_with_states object.
unroll_length: Unrolled length for LSTM training.
batch_size: Batch size for queue outputs.
Returns:
A dictionary of tensors based on items in input_reader_config.
"""
seq_tensors_dict = {
fields.InputDataFields.image: [],
fields.InputDataFields.groundtruth_boxes: [],
fields.InputDataFields.groundtruth_classes: [],
'batch': batch_sequences_with_states,
}
for i in range(unroll_length):
for j in range(batch_size):
filtered_dict = util_ops.filter_groundtruth_with_nan_box_coordinates(
{
fields.InputDataFields.groundtruth_boxes:
(batch_sequences_with_states.sequences['groundtruth_boxes']
[j][i]),
fields.InputDataFields.groundtruth_classes:
(batch_sequences_with_states.
sequences['groundtruth_classes'][j][i]),
})
filtered_dict = util_ops.retain_groundtruth_with_positive_classes(
filtered_dict)
seq_tensors_dict[fields.InputDataFields.image].append(
batch_sequences_with_states.sequences['image'][j][i])
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes].append(
filtered_dict[fields.InputDataFields.groundtruth_boxes])
seq_tensors_dict[
fields.InputDataFields.groundtruth_classes].append(
filtered_dict[fields.InputDataFields.groundtruth_classes])
seq_tensors_dict[fields.InputDataFields.image] = tuple(
seq_tensors_dict[fields.InputDataFields.image])
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes] = tuple(
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes])
seq_tensors_dict[fields.InputDataFields.groundtruth_classes] = tuple(
seq_tensors_dict[fields.InputDataFields.groundtruth_classes])
return seq_tensors_dict
def _build_training_batch_dict(batch_sequences_with_states, unroll_length,
batch_size):
"""Builds training batch samples.
Args:
batch_sequences_with_states: A batch_sequences_with_states object.
unroll_length: Unrolled length for LSTM training.
batch_size: Batch size for queue outputs.
Returns:
A dictionary of tensors based on items in input_reader_config.
"""
seq_tensors_dict = {
fields.InputDataFields.image: [],
fields.InputDataFields.groundtruth_boxes: [],
fields.InputDataFields.groundtruth_classes: [],
'batch': batch_sequences_with_states,
}
for i in range(unroll_length):
for j in range(batch_size):
filtered_dict = util_ops.filter_groundtruth_with_nan_box_coordinates({
fields.InputDataFields.groundtruth_boxes: (
batch_sequences_with_states.sequences['groundtruth_boxes'][j][i]),
fields.InputDataFields.groundtruth_classes: (
batch_sequences_with_states.sequences['groundtruth_classes'][j][i]
),
})
filtered_dict = util_ops.retain_groundtruth_with_positive_classes(
filtered_dict)
seq_tensors_dict[fields.InputDataFields.image].append(
batch_sequences_with_states.sequences['image'][j][i])
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes].append(
filtered_dict[fields.InputDataFields.groundtruth_boxes])
seq_tensors_dict[fields.InputDataFields.groundtruth_classes].append(
filtered_dict[fields.InputDataFields.groundtruth_classes])
seq_tensors_dict[fields.InputDataFields.image] = tuple(
seq_tensors_dict[fields.InputDataFields.image])
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes] = tuple(
seq_tensors_dict[fields.InputDataFields.groundtruth_boxes])
seq_tensors_dict[fields.InputDataFields.groundtruth_classes] = tuple(
seq_tensors_dict[fields.InputDataFields.groundtruth_classes])
return seq_tensors_dict
def test_filter_groundtruth_with_positive_classes(self):
input_image = tf.placeholder(tf.float32, shape=(None, None, 3))
input_boxes = tf.placeholder(tf.float32, shape=(None, 4))
input_classes = tf.placeholder(tf.int32, shape=(None,))
input_is_crowd = tf.placeholder(tf.bool, shape=(None,))
input_area = tf.placeholder(tf.float32, shape=(None,))
input_difficult = tf.placeholder(tf.float32, shape=(None,))
input_label_types = tf.placeholder(tf.string, shape=(None,))
valid_indices = tf.placeholder(tf.int32, shape=(None,))
input_tensors = {
fields.InputDataFields.image: input_image,
fields.InputDataFields.groundtruth_boxes: input_boxes,
fields.InputDataFields.groundtruth_classes: input_classes,
fields.InputDataFields.groundtruth_is_crowd: input_is_crowd,
fields.InputDataFields.groundtruth_area: input_area,
fields.InputDataFields.groundtruth_difficult: input_difficult,
fields.InputDataFields.groundtruth_label_types: input_label_types
}
output_tensors = ops.retain_groundtruth_with_positive_classes(input_tensors)
image_tensor = np.random.rand(224, 224, 3)
feed_dict = {
input_image: image_tensor,
input_boxes:
np.array([[0.2, 0.4, 0.1, 0.8], [0.2, 0.4, 1.0, 0.8]], dtype=np.float),
input_classes:
np.array([1, 0], dtype=np.int32),
input_is_crowd:
np.array([False, True], dtype=np.bool),
input_area:
np.array([32, 48], dtype=np.float32),
input_difficult:
np.array([True, False], dtype=np.bool),
input_label_types:
np.array(['APPROPRIATE', 'INCORRECT'], dtype=np.string_),
valid_indices:
np.array([0], dtype=np.int32)
}
expected_tensors = {
fields.InputDataFields.image:
image_tensor,
fields.InputDataFields.groundtruth_boxes:
[[0.2, 0.4, 0.1, 0.8]],
fields.InputDataFields.groundtruth_classes:
[1],
fields.InputDataFields.groundtruth_is_crowd:
[False],
fields.InputDataFields.groundtruth_area:
[32],
fields.InputDataFields.groundtruth_difficult:
[True],
fields.InputDataFields.groundtruth_label_types:
['APPROPRIATE']
}
with self.test_session() as sess:
output_tensors = sess.run(output_tensors, feed_dict=feed_dict)
for key in [fields.InputDataFields.image,
fields.InputDataFields.groundtruth_boxes,
fields.InputDataFields.groundtruth_area]:
self.assertAllClose(expected_tensors[key], output_tensors[key])
for key in [fields.InputDataFields.groundtruth_classes,
fields.InputDataFields.groundtruth_is_crowd,
fields.InputDataFields.groundtruth_label_types]:
self.assertAllEqual(expected_tensors[key], output_tensors[key])
def test_filter_groundtruth_with_positive_classes(self):
input_image = tf.placeholder(tf.float32, shape=(None, None, 3))
input_boxes = tf.placeholder(tf.float32, shape=(None, 4))
input_classes = tf.placeholder(tf.int32, shape=(None,))
input_is_crowd = tf.placeholder(tf.bool, shape=(None,))
input_area = tf.placeholder(tf.float32, shape=(None,))
input_difficult = tf.placeholder(tf.float32, shape=(None,))
input_label_types = tf.placeholder(tf.string, shape=(None,))
valid_indices = tf.placeholder(tf.int32, shape=(None,))
input_tensors = {
fields.InputDataFields.image: input_image,
fields.InputDataFields.groundtruth_boxes: input_boxes,
fields.InputDataFields.groundtruth_classes: input_classes,
fields.InputDataFields.groundtruth_is_crowd: input_is_crowd,
fields.InputDataFields.groundtruth_area: input_area,
fields.InputDataFields.groundtruth_difficult: input_difficult,
fields.InputDataFields.groundtruth_label_types: input_label_types
}
output_tensors = ops.retain_groundtruth_with_positive_classes(input_tensors)
image_tensor = np.random.rand(224, 224, 3)
feed_dict = {
input_image: image_tensor,
input_boxes:
np.array([[0.2, 0.4, 0.1, 0.8], [0.2, 0.4, 1.0, 0.8]], dtype=np.float),
input_classes:
np.array([1, 0], dtype=np.int32),
input_is_crowd:
np.array([False, True], dtype=np.bool),
input_area:
np.array([32, 48], dtype=np.float32),
input_difficult:
np.array([True, False], dtype=np.bool),
input_label_types:
np.array(['APPROPRIATE', 'INCORRECT'], dtype=np.string_),
valid_indices:
np.array([0], dtype=np.int32)
}
expected_tensors = {
fields.InputDataFields.image:
image_tensor,
fields.InputDataFields.groundtruth_boxes:
[[0.2, 0.4, 0.1, 0.8]],
fields.InputDataFields.groundtruth_classes:
[1],
fields.InputDataFields.groundtruth_is_crowd:
[False],
fields.InputDataFields.groundtruth_area:
[32],
fields.InputDataFields.groundtruth_difficult:
[True],
fields.InputDataFields.groundtruth_label_types:
['APPROPRIATE']
}
with self.test_session() as sess:
output_tensors = sess.run(output_tensors, feed_dict=feed_dict)
for key in [fields.InputDataFields.image,
fields.InputDataFields.groundtruth_boxes,
fields.InputDataFields.groundtruth_area]:
self.assertAllClose(expected_tensors[key], output_tensors[key])
for key in [fields.InputDataFields.groundtruth_classes,
fields.InputDataFields.groundtruth_is_crowd,
fields.InputDataFields.groundtruth_label_types]:
self.assertAllEqual(expected_tensors[key], output_tensors[key])
