我是tensorflow的新手,我试图使用对象检测API来训练人脸识别模型,但是我被困在这一部分
raise ValueError('all elements of boxlists should be BoxList objects')
ValueError: all elements of boxlists should be BoxList objects
我已经检查了csv文件,一切似乎都按顺序进行,但我无法解决问题
filename width height class xmin ymin xmax ymax
img_591.jpg 450 431 Face 187 43 351 279
img_265.jpg 449 305 Face 61 20 149 154
img_265.jpg 449 305 Face 157 87 211 171
img_265.jpg 449 305 Face 298 47 382 187
img_423.jpg 449 450 Face 196 46 314 220
img_490.jpg 370 450 Face 111 24 179 132
img_17676.jpg 364 450 Face 1 1 57 74
img_17676.jpg 364 450 Face 62 13 162 171
img_228.jpg 409 450 Face 70 52 136 162
img_228.jpg 409 450 Face 258 10 332 128
img_402.jpg 450 311 Face 328 30 366 82
img_402.jpg 450 311 Face 78 39 162 197
img_402.jpg 450 311 Face 418 42 442 74
img_769.jpg 318 450 Face 24 11 148 207
img_769.jpg 318 450 Face 192 67 296 245
img_581.jpg 317 450 Face 85 86 225 292
img_723.jpg 348 449 Face 82 56 260 298
img_821.jpg 341 450 Face 82 57 274 347
img_610.jpg 410 294 Face 143 24 257 184
img_610.jpg 410 294 Face 1 88 79 202
img_610.jpg 410 294 Face 327 55 410 181
img_610.jpg 410 294 Face 120 108 192 204
img_610.jpg 410 294 Face 278 110 334 192
img_610.jpg 410 294 Face 19 40 93 142
img_1116.jpg 450 318 Face 149 29 259 193
img_1116.jpg 450 318 Face 365 94 385 122
img_19238.jpg 450 338 Face 45 36 129 158
img_19238.jpg 450 338 Face 325 103 411 235
img_660.jpg 386 450 Face 126 55 248 243
img_607.jpg 293 450 Face 106 10 188 134
img_3708.jpg 450 322 Face 80 2 208 176
img_3708.jpg 450 322 Face 299 24 403 194
img_511.jpg 449 320 Face 83 29 179 179
img_511.jpg 449 320 Face 240 30 314 142
Use `tf.data.Dataset.batch(..., drop_remainder=True)`.
<object_detection.core.box_list.BoxList object at 0x122d9d208>
Traceback (most recent call last):
File "object_detection/model_main.py", line 112, in <module>
tf.app.run()
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "object_detection/model_main.py", line 108, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 471, in train_and_evaluate
return executor.run()
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 610, in run
return self.run_local()
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 711, in run_local
saving_listeners=saving_listeners)
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 354, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1207, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1237, in _train_model_default
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/Users/gllow/venv/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1195, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/Users/gllow/Desktop/GL/Tensorflow/models/research/object_detection/model_lib.py", line 302, in model_fn
features[fields.InputDataFields.true_image_shape])
File "/Users/gllow/Desktop/GL/Tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 578, in predict
im_width=image_shape[2]))
File "/Users/gllow/Desktop/GL/Tensorflow/models/research/object_detection/core/box_list_ops.py", line 565, in concatenate
raise ValueError('all elements of boxlists should be BoxList objects')
ValueError: all elements of boxlists should be BoxList objects
“”“
“”“ 用法: #从tensorflow / models / #创建火车数据: python generate_tfrecord.py --csv_input = data / train_labels.csv --output_path = train.record #创建测试数据: python generate_tfrecord.py --csv_input = data / test_labels.csv --output_path = test.record “” 来自未来进口部门 从未来导入print_function 从未来导入absolute_import
import os
import io
import pandas as pd
import tensorflow as tf
from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict
flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
flags.DEFINE_string('image_dir', '', 'Path to images')
FLAGS = flags.FLAGS
# TO-DO replace this with label map
def class_text_to_int(row_label):
if row_label == 'Face':
return 1
else:
None
def split(df, group):
data = namedtuple('data', ['filename', 'object'])
gb = df.groupby(group)
return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
def create_tf_example(group, path):
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_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(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def main(_):
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
path = os.path.join(FLAGS.image_dir)
examples = pd.read_csv(FLAGS.csv_input)
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
output_path = os.path.join(os.getcwd(), FLAGS.output_path)
print('Successfully created the TFRecords: {}'.format(output_path))
if __name__ == '__main__':
tf.app.run()
“”“