def extract_images_and_targets(read_data):
"""Extract images and targets from the input dict."""
image = read_data[fields.InputDataFields.image]
key = ''
if fields.InputDataFields.source_id in read_data:
key = read_data[fields.InputDataFields.source_id]
location_gt = read_data[fields.InputDataFields.groundtruth_boxes]
classes_gt = tf.cast(read_data[fields.InputDataFields.groundtruth_classes],
tf.int32)
classes_gt -= label_id_offset
if merge_multiple_label_boxes and use_multiclass_scores:
raise ValueError(
'Using both merge_multiple_label_boxes and use_multiclass_scores is'
'not supported'
)
if merge_multiple_label_boxes:
location_gt, classes_gt, _ = util_ops.merge_boxes_with_multiple_labels(
location_gt, classes_gt, num_classes)
elif use_multiclass_scores:
classes_gt = tf.cast(read_data[fields.InputDataFields.multiclass_scores],
tf.float32)
else:
classes_gt = util_ops.padded_one_hot_encoding(
indices=classes_gt, depth=num_classes, left_pad=0)
masks_gt = read_data.get(fields.InputDataFields.groundtruth_instance_masks)
keypoints_gt = read_data.get(fields.InputDataFields.groundtruth_keypoints)
if (merge_multiple_label_boxes and (
masks_gt is not None or keypoints_gt is not None)):
raise NotImplementedError('Multi-label support is only for boxes.')
weights_gt = read_data.get(
fields.InputDataFields.groundtruth_weights)
return (image, key, location_gt, classes_gt, masks_gt, keypoints_gt,
weights_gt)
def extract_images_and_targets(read_data):
image = read_data[fields.InputDataFields.image]
location_gt = read_data[fields.InputDataFields.groundtruth_boxes]
classes_gt = tf.cast(read_data[fields.InputDataFields.groundtruth_classes],
tf.int32)
classes_gt -= label_id_offset
classes_gt = util_ops.padded_one_hot_encoding(indices=classes_gt,
depth=num_classes, left_pad=0)
masks_gt = read_data.get(fields.InputDataFields.groundtruth_instance_masks)
return image, location_gt, classes_gt, masks_gt
def test_correct_padded_one_hot_tensor_with_empty_indices(self):
depth = 6
pad = 2
indices = tf.constant([])
one_hot_tensor = ops.padded_one_hot_encoding(
indices, depth=depth, left_pad=pad)
expected_tensor = np.zeros((0, depth + pad))
with self.test_session() as sess:
out_one_hot_tensor = sess.run(one_hot_tensor)
self.assertAllClose(out_one_hot_tensor, expected_tensor, rtol=1e-10,
atol=1e-10)
def test_correct_one_hot_tensor_with_pad_three(self):
indices = tf.constant([1, 2, 3, 5])
one_hot_tensor = ops.padded_one_hot_encoding(indices, depth=6, left_pad=3)
expected_tensor = np.array([[0, 0, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 1]], np.float32)
with self.test_session() as sess:
out_one_hot_tensor = sess.run(one_hot_tensor)
self.assertAllClose(out_one_hot_tensor, expected_tensor, rtol=1e-10,
atol=1e-10)
def extract_images_and_targets(read_data):
"""Extract images and targets from the input dict."""
suffix = 0
images = []
keys = []
locations = []
classes = []
masks = []
keypoints = []
while fields.InputDataFields.image + str(suffix) in read_data:
image = read_data[fields.InputDataFields.image + str(suffix)]
key = ''
if fields.InputDataFields.source_id in read_data:
key = read_data[fields.InputDataFields.source_id + str(suffix)]
location_gt = (
read_data[fields.InputDataFields.groundtruth_boxes + str(suffix)])
classes_gt = tf.cast(
read_data[fields.InputDataFields.groundtruth_classes + str(suffix)],
tf.int32)
classes_gt -= label_id_offset
masks_gt = read_data.get(
fields.InputDataFields.groundtruth_instance_masks + str(suffix))
keypoints_gt = read_data.get(
fields.InputDataFields.groundtruth_keypoints + str(suffix))
if merge_multiple_label_boxes:
location_gt, classes_gt, _ = util_ops.merge_boxes_with_multiple_labels(
location_gt, classes_gt, num_classes)
else:
classes_gt = util_ops.padded_one_hot_encoding(
indices=classes_gt, depth=num_classes, left_pad=0)
# Batch read input data and groundtruth. Images and locations, classes by
# default should have the same number of items.
images.append(image)
keys.append(key)
locations.append(location_gt)
classes.append(classes_gt)
masks.append(masks_gt)
keypoints.append(keypoints_gt)
suffix += 1
return (images, keys, locations, classes, masks, keypoints)
def extract_images_and_targets(read_data):
"""Extract images and targets from the input dict."""
image = read_data[fields.InputDataFields.image]
key = ''
if fields.InputDataFields.source_id in read_data:
key = read_data[fields.InputDataFields.source_id]
location_gt = read_data[fields.InputDataFields.groundtruth_boxes]
classes_gt = tf.cast(
read_data[fields.InputDataFields.groundtruth_classes], tf.int32)
classes_gt -= label_id_offset
if merge_multiple_label_boxes and use_multiclass_scores:
raise ValueError(
'Using both merge_multiple_label_boxes and use_multiclass_scores is'
'not supported')
if merge_multiple_label_boxes:
location_gt, classes_gt, _ = util_ops.merge_boxes_with_multiple_labels(
location_gt, classes_gt, num_classes)
classes_gt = tf.cast(classes_gt, tf.float32)
elif use_multiclass_scores:
classes_gt = tf.cast(
read_data[fields.InputDataFields.multiclass_scores],
tf.float32)
else:
classes_gt = util_ops.padded_one_hot_encoding(indices=classes_gt,
depth=num_classes,
left_pad=0)
masks_gt = read_data.get(
fields.InputDataFields.groundtruth_instance_masks)
keypoints_gt = read_data.get(
fields.InputDataFields.groundtruth_keypoints)
if (merge_multiple_label_boxes
and (masks_gt is not None or keypoints_gt is not None)):
raise NotImplementedError('Multi-label support is only for boxes.')
weights_gt = read_data.get(fields.InputDataFields.groundtruth_weights)
return (image, key, location_gt, classes_gt, masks_gt, keypoints_gt,
weights_gt)
def test_raise_value_error_on_float_depth(self):
indices = tf.constant(1.0, shape=(2, 3))
with self.assertRaises(ValueError):
ops.padded_one_hot_encoding(indices, depth=0.1, left_pad=2)
def test_raise_value_error_on_negative_pad(self):
indices = tf.constant(1.0, shape=(2, 3))
with self.assertRaises(ValueError):
ops.padded_one_hot_encoding(indices, depth=6, left_pad=-1)
def test_return_none_on_zero_depth(self): indices = tf.constant([1, 2, 3, 4, 5]) one_hot_tensor = ops.padded_one_hot_encoding(indices, depth=0, left_pad=2) self.assertEqual(one_hot_tensor, None)
def test_raise_value_error_on_float_depth(self):
indices = tf.constant(1.0, shape=(2, 3))
with self.assertRaises(ValueError):
ops.padded_one_hot_encoding(indices, depth=0.1, left_pad=2)
def test_raise_value_error_on_negative_pad(self):
indices = tf.constant(1.0, shape=(2, 3))
with self.assertRaises(ValueError):
ops.padded_one_hot_encoding(indices, depth=6, left_pad=-1)
def test_return_none_on_zero_depth(self): indices = tf.constant([1, 2, 3, 4, 5]) one_hot_tensor = ops.padded_one_hot_encoding(indices, depth=0, left_pad=2) self.assertEqual(one_hot_tensor, None)
