forked from jkjung-avt/hand-detection-tutorial
-
Notifications
You must be signed in to change notification settings - Fork 0
/
create_kitti_tf_record.py
312 lines (254 loc) · 12.3 KB
/
create_kitti_tf_record.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
# https://github.com/tensorflow/models/blob/master/research/object_detection/dataset_tools/create_kitti_tf_record.py
# ========================================================================
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ========================================================================
"""Convert KITTI detection dataset to TFRecord for object detection.
Example usage:
python3 create_kitti_tf_record.py \
--data_dir=egohands_kitti_formatted \
--output_path=data/egohands \
--classes_to_use=hand \
--label_map_path=data/egohands_label_map.pbtxt \
--validation_set_size=500
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import hashlib
import io
import os
import random
import numpy as np
import PIL.Image as pil
import tensorflow as tf
from object_detection.utils import dataset_util
from object_detection.utils import label_map_util
from object_detection.utils.np_box_ops import iou
tf.app.flags.DEFINE_string('data_dir', '', 'Location for the data. '
'All jpg and txt files are assumed to be '
'present at this location.')
tf.app.flags.DEFINE_string('output_path', '', 'Path to which TFRecord '
'files will be written. The TFRecord with '
'the training set will be located at: '
'<output_path>_train.tfrecord. And the '
'TFRecord with the validation set will be '
'located at: <output_path>_val.tfrecord.')
tf.app.flags.DEFINE_string('classes_to_use', 'hand,dontcare',
'Comma separated list of class names that '
'will be used. Adding the dontcare class '
'will remove all bboxs in the dontcare '
'regions.')
tf.app.flags.DEFINE_string('label_map_path',
'data/egohands_label_map.pbtxt',
'Path to label map proto.')
tf.app.flags.DEFINE_integer('validation_set_size', '500',
'Number of images to be used as a '
'validation set.')
FLAGS = tf.app.flags.FLAGS
def convert_kitti_to_tfrecords(data_dir, output_path, classes_to_use,
label_map_path, validation_set_size):
"""Convert the KITTI detection dataset to TFRecords.
Args:
data_dir: The full path containing KITTI formatted data, with all
jpg files located in <data_dir>/images/ and all txt files in
<data_dir>/labels/.
output_path: The path to which TFRecord files will be written.
The TFRecord with the training set will be located at:
<output_path>_train.tfrecord
And the TFRecord with the validation set will be located at:
<output_path>_val.tfrecord
classes_to_use: List of strings naming the classes for which
data should be converted. Use the same names as presented in
the KIITI README file. Adding dontcare class will remove all
other bounding boxes that overlap with areas marked as dontcare
regions.
label_map_path: Path to label map proto
validation_set_size: How many images should be left as the
validation set. (First `validation_set_size` examples are
selected to be in the validation set).
"""
label_map_dict = label_map_util.get_label_map_dict(label_map_path)
train_count = 0
val_count = 0
annotation_dir = os.path.join(data_dir, 'labels')
image_dir = os.path.join(data_dir, 'images')
train_writer = tf.python_io.TFRecordWriter('%s_train.tfrecord'%
output_path)
val_writer = tf.python_io.TFRecordWriter('%s_val.tfrecord'%
output_path)
images = sorted(tf.gfile.ListDirectory(image_dir))
images = [f for f in images if f.endswith('jpg')] # only keep jpg files
assert len(images) > 0
random.shuffle(images)
for idx, img_name in enumerate(images):
img_num = img_name.split('.')[0]
is_validation_img = idx < validation_set_size
img_anno = read_annotation_file(os.path.join(annotation_dir,
img_num+'.txt'))
image_path = os.path.join(image_dir, img_name)
# Filter all bounding boxes of this frame that are of a legal class,
# and don't overlap with a dontcare region.
# 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)
if is_validation_img:
val_writer.write(example.SerializeToString())
val_count += 1
else:
train_writer.write(example.SerializeToString())
train_count += 1
train_writer.close()
val_writer.close()
def prepare_example(image_path, annotations, label_map_dict):
"""Converts a dictionary with annotations for an image to tf.Example proto.
Args:
image_path: The complete path to image.
annotations: A dictionary representing the annotation of a single object
that appears in the image.
label_map_dict: A map from string label names to integer ids.
Returns:
example: The converted tf.Example.
"""
with tf.gfile.GFile(image_path, 'rb') as fid:
encoded_png = fid.read()
encoded_png_io = io.BytesIO(encoded_png)
image = pil.open(encoded_png_io)
image = np.asarray(image)
key = hashlib.sha256(encoded_png).hexdigest()
width = int(image.shape[1])
height = int(image.shape[0])
xmin_norm = annotations['2d_bbox_left'] / float(width)
ymin_norm = annotations['2d_bbox_top'] / float(height)
xmax_norm = annotations['2d_bbox_right'] / float(width)
ymax_norm = annotations['2d_bbox_bottom'] / float(height)
difficult_obj = [0]*len(xmin_norm)
example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(image_path.encode('utf8')),
'image/source_id': dataset_util.bytes_feature(image_path.encode('utf8')),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_png),
'image/format': dataset_util.bytes_feature('png'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin_norm),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax_norm),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin_norm),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax_norm),
'image/object/class/text': dataset_util.bytes_list_feature(
[x.encode('utf8') for x in annotations['type']]),
'image/object/class/label': dataset_util.int64_list_feature(
[label_map_dict[x] for x in annotations['type']]),
'image/object/difficult': dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated': dataset_util.float_list_feature(
annotations['truncated']),
'image/object/alpha': dataset_util.float_list_feature(
annotations['alpha']),
'image/object/3d_bbox/height': dataset_util.float_list_feature(
annotations['3d_bbox_height']),
'image/object/3d_bbox/width': dataset_util.float_list_feature(
annotations['3d_bbox_width']),
'image/object/3d_bbox/length': dataset_util.float_list_feature(
annotations['3d_bbox_length']),
'image/object/3d_bbox/x': dataset_util.float_list_feature(
annotations['3d_bbox_x']),
'image/object/3d_bbox/y': dataset_util.float_list_feature(
annotations['3d_bbox_y']),
'image/object/3d_bbox/z': dataset_util.float_list_feature(
annotations['3d_bbox_z']),
'image/object/3d_bbox/rot_y': dataset_util.float_list_feature(
annotations['3d_bbox_rot_y']),
}))
return example
def filter_annotations(img_all_annotations, used_classes):
"""Filters out annotations from the unused classes and dontcare regions.
Filters out the annotations that belong to classes we do now wish to use and
(optionally) also removes all boxes that overlap with dontcare regions.
Args:
img_all_annotations: A list of annotation dictionaries. See documentation of
read_annotation_file for more details about the format of the annotations.
used_classes: A list of strings listing the classes we want to keep, if the
list contains "dontcare", all bounding boxes with overlapping with dont
care regions will also be filtered out.
Returns:
img_filtered_annotations: A list of annotation dictionaries that have passed
the filtering.
"""
img_filtered_annotations = {}
# Filter the type of the objects.
relevant_annotation_indices = [
i for i, x in enumerate(img_all_annotations['type']) if x in used_classes
]
for key in img_all_annotations.keys():
img_filtered_annotations[key] = (
img_all_annotations[key][relevant_annotation_indices])
if 'dontcare' in used_classes:
dont_care_indices = [i for i,
x in enumerate(img_filtered_annotations['type'])
if x == 'dontcare']
# bounding box format [y_min, x_min, y_max, x_max]
all_boxes = np.stack([img_filtered_annotations['2d_bbox_top'],
img_filtered_annotations['2d_bbox_left'],
img_filtered_annotations['2d_bbox_bottom'],
img_filtered_annotations['2d_bbox_right']],
axis=1)
ious = iou(boxes1=all_boxes,
boxes2=all_boxes[dont_care_indices])
# Remove all bounding boxes that overlap with a dontcare region.
if ious.size > 0:
boxes_to_remove = np.amax(ious, axis=1) > 0.0
for key in img_all_annotations.keys():
img_filtered_annotations[key] = (
img_filtered_annotations[key][np.logical_not(boxes_to_remove)])
return img_filtered_annotations
def read_annotation_file(filename):
"""Reads a KITTI annotation file.
Converts a KITTI annotation file into a dictionary containing all the
relevant information.
Args:
filename: the path to the annotataion text file.
Returns:
anno: A dictionary with the converted annotation information. See annotation
README file for details on the different fields.
"""
with open(filename) as f:
content = f.readlines()
content = [x.strip().split(' ') for x in content]
anno = {}
anno['type'] = np.array([x[0].lower() for x in content])
anno['truncated'] = np.array([float(x[1]) for x in content])
anno['occluded'] = np.array([int(x[2]) for x in content])
anno['alpha'] = np.array([float(x[3]) for x in content])
anno['2d_bbox_left'] = np.array([float(x[4]) for x in content])
anno['2d_bbox_top'] = np.array([float(x[5]) for x in content])
anno['2d_bbox_right'] = np.array([float(x[6]) for x in content])
anno['2d_bbox_bottom'] = np.array([float(x[7]) for x in content])
anno['3d_bbox_height'] = np.array([float(x[8]) for x in content])
anno['3d_bbox_width'] = np.array([float(x[9]) for x in content])
anno['3d_bbox_length'] = np.array([float(x[10]) for x in content])
anno['3d_bbox_x'] = np.array([float(x[11]) for x in content])
anno['3d_bbox_y'] = np.array([float(x[12]) for x in content])
anno['3d_bbox_z'] = np.array([float(x[13]) for x in content])
anno['3d_bbox_rot_y'] = np.array([float(x[14]) for x in content])
return anno
def main(_):
convert_kitti_to_tfrecords(
data_dir=FLAGS.data_dir,
output_path=FLAGS.output_path,
classes_to_use=FLAGS.classes_to_use.split(','),
label_map_path=FLAGS.label_map_path,
validation_set_size=FLAGS.validation_set_size)
if __name__ == '__main__':
tf.app.run()