Skip to content

GitLab

"tools/vscode:/vscode.git/clone" did not exist on "6013e23c6dd4202b02470dd22643fa058f369f54"
Unverified Commit 3f78f4cf authored by derekjchow's avatar derekjchow Committed by GitHub
Browse files

Merge pull request #3494 from pkulzc/master 

Update object detection with internal changes and remove unused BUILD files.
parents 73748d01 0319908c
Hide whitespace changes
Inline Side-by-side
Showing with 316 additions and 720 deletions
research/object_detection/builders/optimizer_builder_test.py
View file @ 3f78f4cf
......@@ -187,7 +187,7 @@ class OptimizerBuilderTest(tf.test.TestCase):
optimizer, _ = optimizer_builder.build(optimizer_proto)
self.assertTrue(
isinstance(optimizer, tf.contrib.opt.MovingAverageOptimizer))
# TODO: Find a way to not depend on the private members.
# TODO(rathodv): Find a way to not depend on the private members.
self.assertAlmostEqual(optimizer._ema._decay, 0.2)
def testBuildEmptyOptimizer(self):
......
research/object_detection/builders/preprocessor_builder.py
View file @ 3f78f4cf
......@@ -256,12 +256,10 @@ def build(preprocessor_step_config):
area_range = [(op.min_area, op.max_area) for op in config.operations]
overlap_thresh = [op.overlap_thresh for op in config.operations]
random_coef = [op.random_coef for op in config.operations]
min_padded_size_ratio = [
(op.min_padded_size_ratio[0], op.min_padded_size_ratio[1])
for op in config.operations]
max_padded_size_ratio = [
(op.max_padded_size_ratio[0], op.max_padded_size_ratio[1])
for op in config.operations]
min_padded_size_ratio = [tuple(op.min_padded_size_ratio)
for op in config.operations]
max_padded_size_ratio = [tuple(op.max_padded_size_ratio)
for op in config.operations]
pad_color = [(op.pad_color_r, op.pad_color_g, op.pad_color_b)
for op in config.operations]
return (preprocessor.ssd_random_crop_pad,
......@@ -296,30 +294,29 @@ def build(preprocessor_step_config):
if step_type == 'ssd_random_crop_pad_fixed_aspect_ratio':
config = preprocessor_step_config.ssd_random_crop_pad_fixed_aspect_ratio
kwargs = {}
aspect_ratio = config.aspect_ratio
if aspect_ratio:
kwargs['aspect_ratio'] = aspect_ratio
min_padded_size_ratio = config.min_padded_size_ratio
if min_padded_size_ratio:
if len(min_padded_size_ratio) != 2:
raise ValueError('min_padded_size_ratio should have 2 elements if set!')
kwargs['min_padded_size_ratio'] = tuple(min_padded_size_ratio)
max_padded_size_ratio = config.max_padded_size_ratio
if max_padded_size_ratio:
if len(max_padded_size_ratio) != 2:
raise ValueError('max_padded_size_ratio should have 2 elements if set!')
kwargs['max_padded_size_ratio'] = tuple(max_padded_size_ratio)
if config.operations:
min_object_covered = [op.min_object_covered for op in config.operations]
aspect_ratio_range = [(op.min_aspect_ratio, op.max_aspect_ratio)
for op in config.operations]
area_range = [(op.min_area, op.max_area) for op in config.operations]
overlap_thresh = [op.overlap_thresh for op in config.operations]
random_coef = [op.random_coef for op in config.operations]
min_padded_size_ratio = [
(op.min_padded_size_ratio[0], op.min_padded_size_ratio[1])
for op in config.operations]
max_padded_size_ratio = [
(op.max_padded_size_ratio[0], op.max_padded_size_ratio[1])
for op in config.operations]
return (preprocessor.ssd_random_crop_pad_fixed_aspect_ratio,
{
'min_object_covered': min_object_covered,
'aspect_ratio': config.aspect_ratio,
'aspect_ratio_range': aspect_ratio_range,
'area_range': area_range,
'overlap_thresh': overlap_thresh,
'random_coef': random_coef,
'min_padded_size_ratio': min_padded_size_ratio,
'max_padded_size_ratio': max_padded_size_ratio,
})
return (preprocessor.ssd_random_crop_pad_fixed_aspect_ratio, {})
kwargs['min_object_covered'] = [op.min_object_covered
for op in config.operations]
kwargs['aspect_ratio_range'] = [(op.min_aspect_ratio, op.max_aspect_ratio)
for op in config.operations]
kwargs['area_range'] = [(op.min_area, op.max_area)
for op in config.operations]
kwargs['overlap_thresh'] = [op.overlap_thresh for op in config.operations]
kwargs['random_coef'] = [op.random_coef for op in config.operations]
return (preprocessor.ssd_random_crop_pad_fixed_aspect_ratio, kwargs)
raise ValueError('Unknown preprocessing step.')
research/object_detection/builders/preprocessor_builder_test.py
View file @ 3f78f4cf
......@@ -532,8 +532,6 @@ class PreprocessorBuilderTest(tf.test.TestCase):
max_area: 1.0
overlap_thresh: 0.0
random_coef: 0.375
min_padded_size_ratio: [1.0, 1.0]
max_padded_size_ratio: [2.0, 2.0]
}
operations {
min_object_covered: 0.25
......@@ -543,10 +541,10 @@ class PreprocessorBuilderTest(tf.test.TestCase):
max_area: 1.0
overlap_thresh: 0.25
random_coef: 0.375
min_padded_size_ratio: [1.0, 1.0]
max_padded_size_ratio: [2.0, 2.0]
}
aspect_ratio: 0.875
min_padded_size_ratio: [1.0, 1.0]
max_padded_size_ratio: [2.0, 2.0]
}
"""
preprocessor_proto = preprocessor_pb2.PreprocessingStep()
......@@ -560,8 +558,8 @@ class PreprocessorBuilderTest(tf.test.TestCase):
'area_range': [(0.5, 1.0), (0.5, 1.0)],
'overlap_thresh': [0.0, 0.25],
'random_coef': [0.375, 0.375],
'min_padded_size_ratio': [(1.0, 1.0), (1.0, 1.0)],
'max_padded_size_ratio': [(2.0, 2.0), (2.0, 2.0)]})
'min_padded_size_ratio': (1.0, 1.0),
'max_padded_size_ratio': (2.0, 2.0)})
if __name__ == '__main__':
......
research/object_detection/core/BUILD deleted 100644 → 0
View file @ 73748d01
# Tensorflow Object Detection API: Core.
package(
default_visibility = ["//visibility:public"],
)
licenses(["notice"])
# Apache 2.0
py_library(
name = "batcher",
srcs = ["batcher.py"],
deps = [
":prefetcher",
":preprocessor",
":standard_fields",
"//tensorflow",
],
)
py_test(
name = "batcher_test",
srcs = ["batcher_test.py"],
deps = [
":batcher",
"//tensorflow",
],
)
py_library(
name = "box_list",
srcs = [
"box_list.py",
],
deps = [
"//tensorflow",
],
)
py_test(
name = "box_list_test",
srcs = ["box_list_test.py"],
deps = [
":box_list",
],
)
py_library(
name = "box_list_ops",
srcs = [
"box_list_ops.py",
],
deps = [
":box_list",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:shape_utils",
],
)
py_test(
name = "box_list_ops_test",
srcs = ["box_list_ops_test.py"],
deps = [
":box_list",
":box_list_ops",
],
)
py_library(
name = "box_coder",
srcs = [
"box_coder.py",
],
deps = [
"//tensorflow",
],
)
py_test(
name = "box_coder_test",
srcs = [
"box_coder_test.py",
],
deps = [
":box_coder",
":box_list",
"//tensorflow",
],
)
py_library(
name = "keypoint_ops",
srcs = [
"keypoint_ops.py",
],
deps = [
"//tensorflow",
],
)
py_test(
name = "keypoint_ops_test",
srcs = ["keypoint_ops_test.py"],
deps = [
":keypoint_ops",
],
)
py_library(
name = "losses",
srcs = ["losses.py"],
deps = [
":box_list",
":box_list_ops",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:ops",
],
)
py_library(
name = "matcher",
srcs = [
"matcher.py",
],
deps = [
"//tensorflow/models/research/object_detection/utils:ops",
],
)
py_library(
name = "model",
srcs = ["model.py"],
deps = [
":standard_fields",
],
)
py_test(
name = "matcher_test",
srcs = [
"matcher_test.py",
],
deps = [
":matcher",
"//tensorflow",
],
)
py_library(
name = "prefetcher",
srcs = ["prefetcher.py"],
deps = ["//tensorflow"],
)
py_library(
name = "preprocessor",
srcs = [
"preprocessor.py",
],
deps = [
":box_list",
":box_list_ops",
":keypoint_ops",
":preprocessor_cache",
":standard_fields",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:shape_utils",
],
)
py_library(
name = "preprocessor_cache",
srcs = [
"preprocessor_cache.py",
],
)
py_test(
name = "preprocessor_test",
srcs = [
"preprocessor_test.py",
],
deps = [
":preprocessor",
":preprocessor_cache",
"//tensorflow",
],
)
py_test(
name = "losses_test",
srcs = ["losses_test.py"],
deps = [
":box_list",
":losses",
":matcher",
"//tensorflow",
],
)
py_test(
name = "prefetcher_test",
srcs = ["prefetcher_test.py"],
deps = [
":prefetcher",
"//tensorflow",
],
)
py_library(
name = "standard_fields",
srcs = [
"standard_fields.py",
],
)
py_library(
name = "post_processing",
srcs = ["post_processing.py"],
deps = [
":box_list",
":box_list_ops",
":standard_fields",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:shape_utils",
],
)
py_test(
name = "post_processing_test",
srcs = ["post_processing_test.py"],
deps = [
":box_list",
":box_list_ops",
":post_processing",
"//tensorflow",
],
)
py_library(
name = "target_assigner",
srcs = [
"target_assigner.py",
],
deps = [
":box_list",
":matcher",
":region_similarity_calculator",
":standard_fields",
"//tensorflow",
"//tensorflow/models/research/object_detection/box_coders:faster_rcnn_box_coder",
"//tensorflow/models/research/object_detection/box_coders:mean_stddev_box_coder",
"//tensorflow/models/research/object_detection/core:box_coder",
"//tensorflow/models/research/object_detection/matchers:argmax_matcher",
"//tensorflow/models/research/object_detection/matchers:bipartite_matcher",
"//tensorflow/models/research/object_detection/utils:shape_utils",
],
)
py_test(
name = "target_assigner_test",
size = "large",
timeout = "long",
srcs = ["target_assigner_test.py"],
deps = [
":box_list",
":region_similarity_calculator",
":target_assigner",
"//tensorflow",
"//tensorflow/models/research/object_detection/box_coders:keypoint_box_coder",
"//tensorflow/models/research/object_detection/box_coders:mean_stddev_box_coder",
"//tensorflow/models/research/object_detection/matchers:bipartite_matcher",
"//tensorflow/models/research/object_detection/utils:test_case",
],
)
py_library(
name = "data_decoder",
srcs = ["data_decoder.py"],
)
py_library(
name = "data_parser",
srcs = ["data_parser.py"],
)
py_library(
name = "box_predictor",
srcs = ["box_predictor.py"],
deps = [
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:ops",
"//tensorflow/models/research/object_detection/utils:shape_utils",
"//tensorflow/models/research/object_detection/utils:static_shape",
],
)
py_test(
name = "box_predictor_test",
srcs = ["box_predictor_test.py"],
deps = [
":box_predictor",
"//tensorflow",
"//tensorflow/models/research/object_detection/builders:hyperparams_builder",
"//tensorflow/models/research/object_detection/protos:hyperparams_py_pb2",
"//tensorflow/models/research/object_detection/utils:test_case",
],
)
py_library(
name = "region_similarity_calculator",
srcs = [
"region_similarity_calculator.py",
],
deps = [
"//tensorflow",
"//tensorflow/models/research/object_detection/core:box_list_ops",
],
)
py_test(
name = "region_similarity_calculator_test",
srcs = [
"region_similarity_calculator_test.py",
],
deps = [
":region_similarity_calculator",
"//tensorflow/models/research/object_detection/core:box_list",
],
)
py_library(
name = "anchor_generator",
srcs = [
"anchor_generator.py",
],
deps = [
"//tensorflow",
],
)
py_library(
name = "minibatch_sampler",
srcs = [
"minibatch_sampler.py",
],
deps = [
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:ops",
],
)
py_test(
name = "minibatch_sampler_test",
srcs = [
"minibatch_sampler_test.py",
],
deps = [
":minibatch_sampler",
"//tensorflow",
],
)
py_library(
name = "balanced_positive_negative_sampler",
srcs = [
"balanced_positive_negative_sampler.py",
],
deps = [
":minibatch_sampler",
"//tensorflow",
],
)
py_test(
name = "balanced_positive_negative_sampler_test",
srcs = [
"balanced_positive_negative_sampler_test.py",
],
deps = [
":balanced_positive_negative_sampler",
"//tensorflow",
],
)
research/object_detection/core/anchor_generator.py
View file @ 3f78f4cf
......@@ -77,7 +77,7 @@ class AnchorGenerator(object):
def generate(self, feature_map_shape_list, **params):
"""Generates a collection of bounding boxes to be used as anchors.
TODO: remove **params from argument list and make stride and
TODO(rathodv): remove **params from argument list and make stride and
offsets (for multiple_grid_anchor_generator) constructor arguments.
Args:
......@@ -88,7 +88,9 @@ class AnchorGenerator(object):
**params: parameters for anchor generation op
Returns:
boxes: a BoxList holding a collection of N anchor boxes
boxes_list: a list of BoxLists each holding anchor boxes corresponding to
the input feature map shapes.
Raises:
ValueError: if the number of feature map shapes does not match the length
of NumAnchorsPerLocation.
......@@ -98,13 +100,14 @@ class AnchorGenerator(object):
raise ValueError('Number of feature maps is expected to equal the length '
'of `num_anchors_per_location`.')
with tf.name_scope(self.name_scope()):
anchors = self._generate(feature_map_shape_list, **params)
anchors_list = self._generate(feature_map_shape_list, **params)
if self.check_num_anchors:
with tf.control_dependencies([
self._assert_correct_number_of_anchors(
anchors, feature_map_shape_list)]):
anchors.set(tf.identity(anchors.get()))
return anchors
anchors_list, feature_map_shape_list)]):
for item in anchors_list:
item.set(tf.identity(item.get()))
return anchors_list
@abstractmethod
def _generate(self, feature_map_shape_list, **params):
......@@ -117,15 +120,17 @@ class AnchorGenerator(object):
**params: parameters for anchor generation op
Returns:
boxes: a BoxList holding a collection of N anchor boxes
boxes_list: a list of BoxList, each holding a collection of N anchor
boxes.
"""
pass
def _assert_correct_number_of_anchors(self, anchors, feature_map_shape_list):
def _assert_correct_number_of_anchors(self, anchors_list,
feature_map_shape_list):
"""Assert that correct number of anchors was generated.
Args:
anchors: box_list.BoxList object holding anchors generated
anchors_list: A list of box_list.BoxList object holding anchors generated.
feature_map_shape_list: list of (height, width) pairs in the format
[(height_0, width_0), (height_1, width_1), ...] that the generated
anchors must align with.
......@@ -134,10 +139,12 @@ class AnchorGenerator(object):
match the number of expected anchors.
"""
expected_num_anchors = 0
for num_anchors_per_location, feature_map_shape in zip(
self.num_anchors_per_location(), feature_map_shape_list):
actual_num_anchors = 0
for num_anchors_per_location, feature_map_shape, anchors in zip(
self.num_anchors_per_location(), feature_map_shape_list, anchors_list):
expected_num_anchors += (num_anchors_per_location
* feature_map_shape[0]
* feature_map_shape[1])
return tf.assert_equal(expected_num_anchors, anchors.num_boxes())
actual_num_anchors += anchors.num_boxes()
return tf.assert_equal(expected_num_anchors, actual_num_anchors)
research/object_detection/core/box_list_ops.py
View file @ 3f78f4cf
......@@ -585,7 +585,7 @@ def sort_by_field(boxlist, field, order=SortOrder.descend, scope=None):
['Incorrect field size: actual vs expected.', num_entries, num_boxes])
with tf.control_dependencies([length_assert]):
# TODO: Remove with tf.device when top_k operation runs
# TODO(derekjchow): Remove with tf.device when top_k operation runs
# correctly on GPU.
with tf.device('/cpu:0'):
_, sorted_indices = tf.nn.top_k(field_to_sort, num_boxes, sorted=True)
......@@ -657,7 +657,7 @@ def filter_greater_than(boxlist, thresh, scope=None):
This op keeps the collection of boxes whose corresponding scores are
greater than the input threshold.
TODO: Change function name to filter_scores_greater_than
TODO(jonathanhuang): Change function name to filter_scores_greater_than
Args:
boxlist: BoxList holding N boxes. Must contain a 'scores' field
......@@ -937,7 +937,7 @@ def box_voting(selected_boxes, pool_boxes, iou_thresh=0.5):
iou_ = iou(selected_boxes, pool_boxes)
match_indicator = tf.to_float(tf.greater(iou_, iou_thresh))
num_matches = tf.reduce_sum(match_indicator, 1)
# TODO: Handle the case where some boxes in selected_boxes do not
# TODO(kbanoop): Handle the case where some boxes in selected_boxes do not
# match to any boxes in pool_boxes. For such boxes without any matches, we
# should return the original boxes without voting.
match_assert = tf.Assert(
......
research/object_detection/core/box_list_ops_test.py
View file @ 3f78f4cf
......@@ -738,12 +738,9 @@ class NonMaxSuppressionTest(tf.test.TestCase):
boxes.add_field('scores', tf.constant([.9, .75, .6, .95, .5]))
iou_thresh = .5
max_output_size = 3
nms = box_list_ops.non_max_suppression(
boxes, iou_thresh, max_output_size)
with self.test_session() as sess:
with self.assertRaisesWithPredicateMatch(
errors.InvalidArgumentError, 'scores has incompatible shape'):
sess.run(nms.get())
with self.assertRaisesWithPredicateMatch(ValueError,
'Dimensions must be equal'):
box_list_ops.non_max_suppression(boxes, iou_thresh, max_output_size)
def test_select_from_three_clusters(self):
corners = tf.constant([[0, 0, 1, 1],
......
research/object_detection/core/box_predictor.py
View file @ 3f78f4cf
......@@ -64,11 +64,9 @@ class BoxPredictor(object):
scope=None, **params):
"""Computes encoded object locations and corresponding confidences.
Takes a high level image feature map as input and produce two predictions,
(1) a tensor encoding box locations, and
(2) a tensor encoding class scores for each corresponding box.
In this interface, we only assume that two tensors are returned as output
and do not assume anything about their shapes.
Takes a list of high level image feature maps as input and produces a list
of box encodings and a list of class scores where each element in the output
lists correspond to the feature maps in the input list.
Args:
image_features: A list of float tensors of shape [batch_size, height_i,
......@@ -81,12 +79,14 @@ class BoxPredictor(object):
Returns:
A dictionary containing at least the following tensors.
box_encodings: A float tensor of shape
[batch_size, num_anchors, q, code_size] representing the location of
the objects, where q is 1 or the number of classes.
class_predictions_with_background: A float tensor of shape
[batch_size, num_anchors, num_classes + 1] representing the class
predictions for the proposals.
box_encodings: A list of float tensors of shape
[batch_size, num_anchors_i, q, code_size] representing the location of
the objects, where q is 1 or the number of classes. Each entry in the
list corresponds to a feature map in the input `image_features` list.
class_predictions_with_background: A list of float tensors of shape
[batch_size, num_anchors_i, num_classes + 1] representing the class
predictions for the proposals. Each entry in the list corresponds to a
feature map in the input `image_features` list.
Raises:
ValueError: If length of `image_features` is not equal to length of
......@@ -104,7 +104,7 @@ class BoxPredictor(object):
return self._predict(image_features, num_predictions_per_location,
**params)
# TODO: num_predictions_per_location could be moved to constructor.
# TODO(rathodv): num_predictions_per_location could be moved to constructor.
# This is currently only used by ConvolutionalBoxPredictor.
@abstractmethod
def _predict(self, image_features, num_predictions_per_location, **params):
......@@ -120,12 +120,14 @@ class BoxPredictor(object):
Returns:
A dictionary containing at least the following tensors.
box_encodings: A float tensor of shape
[batch_size, num_anchors, q, code_size] representing the location of
the objects, where q is 1 or the number of classes.
class_predictions_with_background: A float tensor of shape
[batch_size, num_anchors, num_classes + 1] representing the class
predictions for the proposals.
box_encodings: A list of float tensors of shape
[batch_size, num_anchors_i, q, code_size] representing the location of
the objects, where q is 1 or the number of classes. Each entry in the
list corresponds to a feature map in the input `image_features` list.
class_predictions_with_background: A list of float tensors of shape
[batch_size, num_anchors_i, num_classes + 1] representing the class
predictions for the proposals. Each entry in the list corresponds to a
feature map in the input `image_features` list.
"""
pass
......@@ -133,7 +135,7 @@ class BoxPredictor(object):
class RfcnBoxPredictor(BoxPredictor):
"""RFCN Box Predictor.
Applies a position sensitve ROI pooling on position sensitive feature maps to
Applies a position sensitive ROI pooling on position sensitive feature maps to
predict classes and refined locations. See https://arxiv.org/abs/1605.06409
for details.
......@@ -191,12 +193,14 @@ class RfcnBoxPredictor(BoxPredictor):
box_code_size].
Returns:
box_encodings: A float tensor of shape
[batch_size, num_anchors, num_classes, code_size] representing the
location of the objects.
class_predictions_with_background: A float tensor of shape
[batch_size, num_anchors, num_classes + 1] representing the class
predictions for the proposals.
box_encodings: A list of float tensors of shape
[batch_size, num_anchors_i, q, code_size] representing the location of
the objects, where q is 1 or the number of classes. Each entry in the
list corresponds to a feature map in the input `image_features` list.
class_predictions_with_background: A list of float tensors of shape
[batch_size, num_anchors_i, num_classes + 1] representing the class
predictions for the proposals. Each entry in the list corresponds to a
feature map in the input `image_features` list.
Raises:
ValueError: if num_predictions_per_location is not 1 or if
......@@ -266,11 +270,12 @@ class RfcnBoxPredictor(BoxPredictor):
class_predictions_with_background,
[batch_size * num_boxes, 1, total_classes])
return {BOX_ENCODINGS: box_encodings,
return {BOX_ENCODINGS: [box_encodings],
CLASS_PREDICTIONS_WITH_BACKGROUND:
class_predictions_with_background}
[class_predictions_with_background]}
# TODO(rathodv): Change the implementation to return lists of predictions.
class MaskRCNNBoxPredictor(BoxPredictor):
"""Mask R-CNN Box Predictor.
......@@ -644,18 +649,18 @@ class ConvolutionalBoxPredictor(BoxPredictor):
feature map.
Returns:
A dictionary containing the following tensors.
box_encodings: A float tensor of shape [batch_size, num_anchors, 1,
code_size] representing the location of the objects, where
num_anchors = feat_height * feat_width * num_predictions_per_location
class_predictions_with_background: A float tensor of shape
[batch_size, num_anchors, num_classes + 1] representing the class
predictions for the proposals.
box_encodings: A list of float tensors of shape
[batch_size, num_anchors_i, q, code_size] representing the location of
the objects, where q is 1 or the number of classes. Each entry in the
list corresponds to a feature map in the input `image_features` list.
class_predictions_with_background: A list of float tensors of shape
[batch_size, num_anchors_i, num_classes + 1] representing the class
predictions for the proposals. Each entry in the list corresponds to a
feature map in the input `image_features` list.
"""
box_encodings_list = []
class_predictions_list = []
# TODO: Come up with a better way to generate scope names
# TODO(rathodv): Come up with a better way to generate scope names
# in box predictor once we have time to retrain all models in the zoo.
# The following lines create scope names to be backwards compatible with the
# existing checkpoints.
......@@ -741,12 +746,13 @@ class ConvolutionalBoxPredictor(BoxPredictor):
num_predictions_per_location,
num_class_slots]))
class_predictions_list.append(class_predictions_with_background)
return {BOX_ENCODINGS: tf.concat(box_encodings_list, axis=1),
CLASS_PREDICTIONS_WITH_BACKGROUND:
tf.concat(class_predictions_list, axis=1)}
return {
BOX_ENCODINGS: box_encodings_list,
CLASS_PREDICTIONS_WITH_BACKGROUND: class_predictions_list
}
# TODO: Merge the implementation with ConvolutionalBoxPredictor above
# TODO(rathodv): Merge the implementation with ConvolutionalBoxPredictor above
# since they are very similar.
class WeightSharedConvolutionalBoxPredictor(BoxPredictor):
"""Convolutional Box Predictor with weight sharing.
......@@ -806,13 +812,14 @@ class WeightSharedConvolutionalBoxPredictor(BoxPredictor):
shared.
Returns:
A dictionary containing the following tensors.
box_encodings: A float tensor of shape [batch_size, num_anchors, 1,
code_size] representing the location of the objects, where
num_anchors = feat_height * feat_width * num_predictions_per_location
class_predictions_with_background: A float tensor of shape
[batch_size, num_anchors, num_classes + 1] representing the class
predictions for the proposals.
box_encodings: A list of float tensors of shape
[batch_size, num_anchors_i, q, code_size] representing the location of
the objects, where q is 1 or the number of classes. Each entry in the
list corresponds to a feature map in the input `image_features` list.
class_predictions_with_background: A list of float tensors of shape
[batch_size, num_anchors_i, num_classes + 1] representing the class
predictions for the proposals. Each entry in the list corresponds to a
feature map in the input `image_features` list.
Raises:
ValueError: If the image feature maps do not have the same number of
......@@ -890,6 +897,7 @@ class WeightSharedConvolutionalBoxPredictor(BoxPredictor):
num_predictions_per_location,
num_class_slots]))
class_predictions_list.append(class_predictions_with_background)
return {BOX_ENCODINGS: tf.concat(box_encodings_list, axis=1),
CLASS_PREDICTIONS_WITH_BACKGROUND:
tf.concat(class_predictions_list, axis=1)}
return {
BOX_ENCODINGS: box_encodings_list,
CLASS_PREDICTIONS_WITH_BACKGROUND: class_predictions_list
}
research/object_detection/core/box_predictor_test.py
View file @ 3f78f4cf
......@@ -165,9 +165,11 @@ class RfcnBoxPredictorTest(tf.test.TestCase):
[image_features], num_predictions_per_location=[1],
scope='BoxPredictor',
proposal_boxes=proposal_boxes)
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
class_predictions_with_background = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
init_op = tf.global_variables_initializer()
with self.test_session() as sess:
......@@ -215,9 +217,11 @@ class ConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
objectness_predictions = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
return (box_encodings, objectness_predictions)
image_features = np.random.rand(4, 8, 8, 64).astype(np.float32)
(box_encodings, objectness_predictions) = self.execute(graph_fn,
......@@ -242,9 +246,10 @@ class ConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[1],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
objectness_predictions = tf.concat(box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1)
return (box_encodings, objectness_predictions)
image_features = np.random.rand(4, 8, 8, 64).astype(np.float32)
(box_encodings, objectness_predictions) = self.execute(graph_fn,
......@@ -273,9 +278,11 @@ class ConvolutionalBoxPredictorTest(test_case.TestCase):
[image_features],
num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
class_predictions_with_background = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
return (box_encodings, class_predictions_with_background)
(box_encodings,
class_predictions_with_background) = self.execute(graph_fn,
......@@ -302,9 +309,11 @@ class ConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
objectness_predictions = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
init_op = tf.global_variables_initializer()
resolution = 32
......@@ -348,9 +357,11 @@ class ConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
objectness_predictions = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
init_op = tf.global_variables_initializer()
resolution = 32
......@@ -412,9 +423,10 @@ class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
objectness_predictions = tf.concat(box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1)
return (box_encodings, objectness_predictions)
image_features = np.random.rand(4, 8, 8, 64).astype(np.float32)
(box_encodings, objectness_predictions) = self.execute(
......@@ -438,9 +450,10 @@ class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
[image_features],
num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
class_predictions_with_background = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1)
return (box_encodings, class_predictions_with_background)
image_features = np.random.rand(4, 8, 8, 64).astype(np.float32)
......@@ -466,9 +479,11 @@ class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
[image_features1, image_features2],
num_predictions_per_location=[5, 5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
class_predictions_with_background = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
return (box_encodings, class_predictions_with_background)
image_features1 = np.random.rand(4, 8, 8, 64).astype(np.float32)
......@@ -493,9 +508,11 @@ class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
[image_features1, image_features2],
num_predictions_per_location=[5, 5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
class_predictions_with_background = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
return (box_encodings, class_predictions_with_background)
with self.test_session(graph=tf.Graph()):
......@@ -543,9 +560,10 @@ class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
box_encodings = tf.concat(box_predictions[box_predictor.BOX_ENCODINGS],
axis=1)
objectness_predictions = tf.concat(box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1)
init_op = tf.global_variables_initializer()
resolution = 32
......
research/object_detection/core/losses.py
View file @ 3f78f4cf
......@@ -116,14 +116,23 @@ class WeightedL2LocalizationLoss(Loss):
class WeightedSmoothL1LocalizationLoss(Loss):
"""Smooth L1 localization loss function.
"""Smooth L1 localization loss function aka Huber Loss..
The smooth L1_loss is defined elementwise as .5 x^2 if |x|<1 and |x|-.5
otherwise, where x is the difference between predictions and target.
The smooth L1_loss is defined elementwise as .5 x^2 if |x| <= delta and
0.5 x^2 + delta * (|x|-delta) otherwise, where x is the difference between
predictions and target.
See also Equation (3) in the Fast R-CNN paper by Ross Girshick (ICCV 2015)
"""
def __init__(self, delta=1.0):
"""Constructor.
Args:
delta: delta for smooth L1 loss.
"""
self._delta = delta
def _compute_loss(self, prediction_tensor, target_tensor, weights):
"""Compute loss function.
......@@ -138,13 +147,14 @@ class WeightedSmoothL1LocalizationLoss(Loss):
loss: a float tensor of shape [batch_size, num_anchors] tensor
representing the value of the loss function.
"""
diff = prediction_tensor - target_tensor
abs_diff = tf.abs(diff)
abs_diff_lt_1 = tf.less(abs_diff, 1)
anchorwise_smooth_l1norm = tf.reduce_sum(
tf.where(abs_diff_lt_1, 0.5 * tf.square(abs_diff), abs_diff - 0.5),
2) * weights
return anchorwise_smooth_l1norm
return tf.reduce_sum(tf.losses.huber_loss(
target_tensor,
prediction_tensor,
delta=self._delta,
weights=tf.expand_dims(weights, axis=2),
loss_collection=None,
reduction=tf.losses.Reduction.NONE
), axis=2)
class WeightedIOULocalizationLoss(Loss):
......
research/object_detection/core/losses_test.py
View file @ 3f78f4cf
......@@ -545,7 +545,7 @@ class WeightedSoftmaxClassificationLossTest(tf.test.TestCase):
def testReturnsCorrectAnchorWiseLossWithHighLogitScaleSetting(self):
"""At very high logit_scale, all predictions will be ~0.33."""
# TODO: Also test logit_scale with anchorwise=False.
# TODO(yonib): Also test logit_scale with anchorwise=False.
logit_scale = 10e16
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
......
research/object_detection/core/preprocessor.py
View file @ 3f78f4cf
......@@ -204,7 +204,7 @@ def _random_integer(minval, maxval, seed):
[], minval=minval, maxval=maxval, dtype=tf.int32, seed=seed)
# TODO: This method is needed because the current
# TODO(mttang): This method is needed because the current
# tf.image.rgb_to_grayscale method does not support quantization. Replace with
# tf.image.rgb_to_grayscale after quantization support is added.
def _rgb_to_grayscale(images, name=None):
......@@ -2140,7 +2140,7 @@ def resize_to_range(image,
return result
# TODO: Make sure the static shapes are preserved.
# TODO(alirezafathi): Make sure the static shapes are preserved.
def resize_to_min_dimension(image, masks=None, min_dimension=600):
"""Resizes image and masks given the min size maintaining the aspect ratio.
......@@ -2226,7 +2226,7 @@ def scale_boxes_to_pixel_coordinates(image, boxes, keypoints=None):
return tuple(result)
# TODO: Investigate if instead the function should return None if
# TODO(alirezafathi): Investigate if instead the function should return None if
# masks is None.
# pylint: disable=g-doc-return-or-yield
def resize_image(image,
......
research/object_detection/core/target_assigner.py
View file @ 3f78f4cf
......@@ -324,7 +324,7 @@ class TargetAssigner(object):
return self._box_coder
# TODO: This method pulls in all the implementation dependencies into
# TODO(rathodv): This method pulls in all the implementation dependencies into
# core. Therefore its best to have this factory method outside of core.
def create_target_assigner(reference, stage=None,
negative_class_weight=1.0,
......
research/object_detection/core/target_assigner_test.py
View file @ 3f78f4cf
......@@ -836,7 +836,7 @@ class CreateTargetAssignerTest(tf.test.TestCase):
def test_create_target_assigner(self):
"""Tests that named constructor gives working target assigners.
TODO: Make this test more general.
TODO(rathodv): Make this test more general.
"""
corners = [[0.0, 0.0, 1.0, 1.0]]
groundtruth = box_list.BoxList(tf.constant(corners))
......
research/object_detection/data/BUILD deleted 100644 → 0
View file @ 73748d01
package(
default_visibility = ["//visibility:public"],
)
licenses(["notice"])
exports_files([
"pet_label_map.pbtxt",
])
research/object_detection/data_decoders/BUILD deleted 100644 → 0
View file @ 73748d01
# Tensorflow Object Detection API: data decoders.
package(
default_visibility = ["//visibility:public"],
)
licenses(["notice"])
# Apache 2.0
py_library(
name = "tf_example_decoder",
srcs = ["tf_example_decoder.py"],
deps = [
"//tensorflow",
"//tensorflow/models/research/object_detection/core:data_decoder",
"//tensorflow/models/research/object_detection/core:standard_fields",
"//tensorflow/models/research/object_detection/protos:input_reader_py_pb2",
"//tensorflow/models/research/object_detection/utils:label_map_util",
],
)
py_test(
name = "tf_example_decoder_test",
srcs = ["tf_example_decoder_test.py"],
deps = [
":tf_example_decoder",
"//tensorflow",
"//tensorflow/models/research/object_detection/core:standard_fields",
"//tensorflow/models/research/object_detection/protos:input_reader_py_pb2",
],
)
research/object_detection/data_decoders/tf_example_decoder.py
View file @ 3f78f4cf
......@@ -20,6 +20,9 @@ protos for object detection.
"""
import tensorflow as tf
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import control_flow_ops
from tensorflow.python.ops import math_ops
from object_detection.core import data_decoder
from object_detection.core import standard_fields as fields
from object_detection.protos import input_reader_pb2
......@@ -28,6 +31,40 @@ from object_detection.utils import label_map_util
slim_example_decoder = tf.contrib.slim.tfexample_decoder
class BackupHandler(slim_example_decoder.ItemHandler):
"""An ItemHandler that tries two ItemHandlers in order."""
def __init__(self, handler, backup):
"""Initializes the BackupHandler handler.
If the first Handler's tensors_to_item returns a Tensor with no elements,
the second Handler is used.
Args:
handler: The primary ItemHandler.
backup: The backup ItemHandler.
Raises:
ValueError: if either is not an ItemHandler.
"""
if not isinstance(handler, slim_example_decoder.ItemHandler):
raise ValueError('Primary handler is of type %s instead of ItemHandler' %
type(handler))
if not isinstance(backup, slim_example_decoder.ItemHandler):
raise ValueError(
'Backup handler is of type %s instead of ItemHandler' % type(backup))
self._handler = handler
self._backup = backup
super(BackupHandler, self).__init__(handler.keys + backup.keys)
def tensors_to_item(self, keys_to_tensors):
item = self._handler.tensors_to_item(keys_to_tensors)
return control_flow_ops.cond(
pred=math_ops.equal(math_ops.reduce_prod(array_ops.shape(item)), 0),
true_fn=lambda: self._backup.tensors_to_item(keys_to_tensors),
false_fn=lambda: item)
class TfExampleDecoder(data_decoder.DataDecoder):
"""Tensorflow Example proto decoder."""
......@@ -101,13 +138,18 @@ class TfExampleDecoder(data_decoder.DataDecoder):
'image/object/weight':
tf.VarLenFeature(tf.float32),
}
if dct_method:
image = slim_example_decoder.Image(
image_key='image/encoded',
format_key='image/format',
channels=3,
dct_method=dct_method)
else:
image = slim_example_decoder.Image(
image_key='image/encoded', format_key='image/format', channels=3)
self.items_to_handlers = {
fields.InputDataFields.image:
slim_example_decoder.Image(
image_key='image/encoded',
format_key='image/format',
channels=3,
dct_method=dct_method),
image,
fields.InputDataFields.source_id: (
slim_example_decoder.Tensor('image/source_id')),
fields.InputDataFields.key: (
......@@ -160,7 +202,11 @@ class TfExampleDecoder(data_decoder.DataDecoder):
default_value=-1)
# If the label_map_proto is provided, try to use it in conjunction with
# the class text, and fall back to a materialized ID.
label_handler = slim_example_decoder.BackupHandler(
# TODO(lzc): note that here we are using BackupHandler defined in this
# file(which is branching slim_example_decoder.BackupHandler). Need to
# switch back to slim_example_decoder.BackupHandler once tf 1.5 becomes
# more popular.
label_handler = BackupHandler(
slim_example_decoder.LookupTensor(
'image/object/class/text', table, default_value=''),
slim_example_decoder.Tensor('image/object/class/label'))
......
research/object_detection/data_decoders/tf_example_decoder_test.py
View file @ 3f78f4cf
......@@ -19,10 +19,19 @@ import os
import numpy as np
import tensorflow as tf
from tensorflow.core.example import example_pb2
from tensorflow.core.example import feature_pb2
from tensorflow.python.framework import constant_op
from tensorflow.python.framework import dtypes
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import lookup_ops
from tensorflow.python.ops import parsing_ops
from object_detection.core import standard_fields as fields
from object_detection.data_decoders import tf_example_decoder
from object_detection.protos import input_reader_pb2
slim_example_decoder = tf.contrib.slim.tfexample_decoder
class TfExampleDecoderTest(tf.test.TestCase):
......@@ -57,6 +66,68 @@ class TfExampleDecoderTest(tf.test.TestCase):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=value))
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def _Int64FeatureFromList(self, ndarray):
return feature_pb2.Feature(
int64_list=feature_pb2.Int64List(value=ndarray.flatten().tolist()))
def _BytesFeatureFromList(self, ndarray):
values = ndarray.flatten().tolist()
for i in range(len(values)):
values[i] = values[i].encode('utf-8')
return feature_pb2.Feature(bytes_list=feature_pb2.BytesList(value=values))
def testDecodeExampleWithBranchedBackupHandler(self):
example1 = example_pb2.Example(
features=feature_pb2.Features(
feature={
'image/object/class/text':
self._BytesFeatureFromList(
np.array(['cat', 'dog', 'guinea pig'])),
'image/object/class/label':
self._Int64FeatureFromList(np.array([42, 10, 900]))
}))
example2 = example_pb2.Example(
features=feature_pb2.Features(
feature={
'image/object/class/text':
self._BytesFeatureFromList(
np.array(['cat', 'dog', 'guinea pig'])),
}))
example3 = example_pb2.Example(
features=feature_pb2.Features(
feature={
'image/object/class/label':
self._Int64FeatureFromList(np.array([42, 10, 901]))
}))
# 'dog' -> 0, 'guinea pig' -> 1, 'cat' -> 2
table = lookup_ops.index_table_from_tensor(
constant_op.constant(['dog', 'guinea pig', 'cat']))
keys_to_features = {
'image/object/class/text': parsing_ops.VarLenFeature(dtypes.string),
'image/object/class/label': parsing_ops.VarLenFeature(dtypes.int64),
}
backup_handler = tf_example_decoder.BackupHandler(
handler=slim_example_decoder.Tensor('image/object/class/label'),
backup=slim_example_decoder.LookupTensor('image/object/class/text',
table))
items_to_handlers = {
'labels': backup_handler,
}
decoder = slim_example_decoder.TFExampleDecoder(keys_to_features,
items_to_handlers)
obtained_class_ids_each_example = []
with self.test_session() as sess:
sess.run(lookup_ops.tables_initializer())
for example in [example1, example2, example3]:
serialized_example = array_ops.reshape(
example.SerializeToString(), shape=[])
obtained_class_ids_each_example.append(
decoder.decode(serialized_example)[0].eval())
self.assertAllClose([42, 10, 900], obtained_class_ids_each_example[0])
self.assertAllClose([2, 0, 1], obtained_class_ids_each_example[1])
self.assertAllClose([42, 10, 901], obtained_class_ids_each_example[2])
def testDecodeJpegImage(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
......
research/object_detection/dataset_tools/BUILD deleted 100644 → 0
View file @ 73748d01
# Tensorflow Object Detection API: dataset tools.
package(
default_visibility = ["//visibility:public"],
)
licenses(["notice"])
# Apache 2.0
py_binary(
name = "create_coco_tf_record",
srcs = [
"create_coco_tf_record.py",
],
deps = [
"//PIL:pil",
"//pycocotools",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:dataset_util",
"//tensorflow/models/research/object_detection/utils:label_map_util",
],
)
py_test(
name = "create_coco_tf_record_test",
srcs = [
"create_coco_tf_record_test.py",
],
deps = [
":create_coco_tf_record",
"//tensorflow",
],
)
py_binary(
name = "create_kitti_tf_record",
srcs = [
"create_kitti_tf_record.py",
],
deps = [
"//PIL:pil",
"//lxml",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:dataset_util",
"//tensorflow/models/research/object_detection/utils:label_map_util",
"//tensorflow/models/research/object_detection/utils:np_box_ops",
],
)
py_test(
name = "create_kitti_tf_record_test",
srcs = [
"create_kitti_tf_record_test.py",
],
deps = [
":create_kitti_tf_record",
"//tensorflow",
],
)
py_binary(
name = "create_pascal_tf_record",
srcs = [
"create_pascal_tf_record.py",
],
deps = [
"//PIL:pil",
"//lxml",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:dataset_util",
"//tensorflow/models/research/object_detection/utils:label_map_util",
],
)
py_test(
name = "create_pascal_tf_record_test",
srcs = [
"create_pascal_tf_record_test.py",
],
deps = [
":create_pascal_tf_record",
"//tensorflow",
],
)
py_binary(
name = "create_pet_tf_record",
srcs = [
"create_pet_tf_record.py",
],
deps = [
"//PIL:pil",
"//lxml",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:dataset_util",
"//tensorflow/models/research/object_detection/utils:label_map_util",
],
)
py_library(
name = "oid_tfrecord_creation",
srcs = ["oid_tfrecord_creation.py"],
deps = [
"//tensorflow",
"//tensorflow/models/research/object_detection/core:standard_fields",
"//tensorflow/models/research/object_detection/utils:dataset_util",
],
)
py_test(
name = "oid_tfrecord_creation_test",
srcs = ["oid_tfrecord_creation_test.py"],
deps = [
":oid_tfrecord_creation",
"//contextlib2",
"//pandas",
"//tensorflow",
],
)
py_binary(
name = "create_oid_tf_record",
srcs = ["create_oid_tf_record.py"],
deps = [
":oid_tfrecord_creation",
"//contextlib2",
"//pandas",
"//tensorflow",
"//tensorflow/models/research/object_detection/utils:label_map_util",
],
)
research/object_detection/dataset_tools/create_kitti_tf_record.py
View file @ 3f78f4cf
......@@ -120,7 +120,7 @@ def convert_kitti_to_tfrecords(data_dir, output_path, classes_to_use,
# Filter all bounding boxes of this frame that are of a legal class, and
# don't overlap with a dontcare region.
# TODO filter out targets that are truncated or heavily occluded.
# TODO(talremez) filter out targets that are truncated or heavily occluded.
annotation_for_image = filter_annotations(img_anno, classes_to_use)
example = prepare_example(image_path, annotation_for_image, label_map_dict)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment