创建的tfcord文件是
create_my_data_tf_record.py是google object detection api 里面的文件。
如下：
import hashlib
import io
import logging
import os
from lxml import etree
import PIL.Image
import tensorflow as tf
from object_detection.utils import dataset_util
from object_detection.utils import label_map_util
#from tensorflow.models.research.object_detection.utils import label_map_util
#
#from tensorflow.models.research.object_detection.utils import visualization_utils as vis_util
flags = tf.app.flags
flags.DEFINE_string('data_dir', '', 'Root directory to raw PASCAL VOC dataset.')
flags.DEFINE_string('set', 'train', 'Convert training set, validation set or '
'merged set.')
flags.DEFINE_string('annotations_dir', 'Annotations',
'(Relative) path to annotations directory.')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
flags.DEFINE_string('label_map_path', 'VOCdevkit/data/label_map.pbtxt',
'Path to label map proto')
flags.DEFINE_boolean('ignore_difficult_instances', False, 'Whether to ignore '
'difficult instances')
FLAGS = flags.FLAGS
SETS = ['train', 'val', 'trainval', 'test']
def dict_to_tf_example(data,
dataset_directory,
label_map_dict,
ignore_difficult_instances=False,
image_subdirectory='JPEGImages'):
"""Convert XML derived dict to tf.Example proto.
Notice that this function normalizes the bounding box coordinates provided
by the raw data.
Args:
data: dict holding PASCAL XML fields for a single image (obtained by
running dataset_util.recursive_parse_xml_to_dict)
dataset_directory: Path to root directory holding PASCAL dataset
label_map_dict: A map from string label names to integers ids.
ignore_difficult_instances: Whether to skip difficult instances in the
dataset (default: False).
image_subdirectory: String specifying subdirectory within the
PASCAL dataset directory holding the actual image data.
Returns:
example: The converted tf.Example.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
img_path = os.path.join(data['folder'], image_subdirectory, data['filename'])
full_path = os.path.join(dataset_directory, img_path)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
key = hashlib.sha256(encoded_jpg).hexdigest()
width = int(data['szie']['width'])
height = int(data['szie']['height'])
xmin = []
ymin = []
xmax = []
ymax = []
classes = []
classes_text = []
truncated = []
poses = []
difficult_obj = []
for obj in data['object']:
difficult = bool(int(obj['difficult']))
if ignore_difficult_instances and difficult:
continue
difficult_obj.append(int(difficult))
xmin.append(float(obj['bndbox']['xmin']) / width)
ymin.append(float(obj['bndbox']['ymin']) / height)
xmax.append(float(obj['bndbox']['xmax']) / width)
ymax.append(float(obj['bndbox']['ymax']) / height)
classes_text.append(obj['name'].encode('utf8'))
classes.append(label_map_dict[obj['name']])
truncated.append(int(obj['truncated']))
poses.append(obj['pose'].encode('utf8'))
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(
data['filename'].encode('utf8')),
'image/source_id': dataset_util.bytes_feature(
data['filename'].encode('utf8')),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
'image/object/difficult': dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated': dataset_util.int64_list_feature(truncated),
'image/object/view': dataset_util.bytes_list_feature(poses),
}))
return example
def main(_):
if FLAGS.set not in SETS:
raise ValueError('set must be in : {}'.format(SETS))
data_dir = FLAGS.data_dir
datasets = ['data']
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)
for dataset in datasets:
logging.info('Reading from PASCAL %s dataset.', dataset)
examples_path = os.path.join(data_dir, dataset, 'ImageSets', 'Main/' + FLAGS.set + '.txt')
annotations_dir = os.path.join(data_dir, dataset, FLAGS.annotations_dir)
examples_list = dataset_util.read_examples_list(examples_path)
for idx, example in enumerate(examples_list):
if idx % 100 == 0:
logging.info('On image %d of %d', idx, len(examples_list))
path = os.path.join(annotations_dir, example + '.xml')
with tf.gfile.GFile(path, 'r') as fid:
xml_str = fid.read()
xml = etree.fromstring(xml_str)
data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
FLAGS.ignore_difficult_instances)
writer.write(tf_example.SerializeToString())
writer.close()
if __name__ == '__main__':
tf.app.run()
现在读取一个文件tfcord文件
#encoding=utf-8
import tensorflow as tf
import numpy as np
import cv2
import io
from PIL import Image
def parse_tf(example_proto):
dics = {}
dics['image/encoded'] = tf.FixedLenFeature(shape=[],dtype=tf.string)
dics['image/width'] = tf.FixedLenFeature(shape=[], dtype=tf.int64)
dics['image/height'] = tf.FixedLenFeature(shape=[], dtype=tf.int64)
dics['image/object/class/text'] = tf.VarLenFeature(tf.string)
dics['image/filename'] = tf.VarLenFeature(tf.string)
dics['image/object/class/label'] = tf.VarLenFeature(tf.int64)
dics['image/object/bbox/xmin'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/xmax'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/ymin'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/ymax'] = tf.VarLenFeature(tf.float32)
parse_example = tf.parse_single_example(serialized=example_proto,features=dics)
filename = parse_example['image/filename']
xmin = parse_example['image/object/bbox/xmin']
xmax = parse_example['image/object/bbox/xmax']
ymin = parse_example['image/object/bbox/ymin']
ymax = parse_example['image/object/bbox/ymax']
image = parse_example['image/encoded']#tf.decode_raw(parse_example['image/encoded'],out_type=tf.uint8)
image = img_data = tf.image.decode_jpeg(image)
w = parse_example['image/width']
h = parse_example['image/height']
return filename,image,w,h,xmin,xmax,ymin,ymax
dataset = tf.data.TFRecordDataset("./TFrecodr/eval.record")
dataset = dataset.map(parse_tf).batch(1).repeat(1)
iterator = dataset.make_one_shot_iterator()
next_element = iterator.get_next()
with tf.Session() as session:
for i in range(3):
filename,image, w, h,xmin, xmax, ymin, ymax = session.run(fetches=next_element)
#左上角坐标与右下角坐标
print(filename)
print(np.squeeze(image).shape, )
print(image.dtype)
image = np.squeeze(image)
image1 = cv2.rectangle(image,(xmin.values[0]*w,ymin.values[0]*h),(xmax.values[0]*w,ymax.values[0]*h),color=(0,255,0))
cv2.imshow("s",image1)
cv2.waitKey(0)
使用tensorflow官方提供的api进行测试
对一张图片进行测试，仅仅是可视化。
# encoding=utf-8
import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
from PIL import Image
from object_detection.utils import label_map_util
def parse_tf(example_proto):
dics = {}
dics['image/encoded'] = tf.FixedLenFeature(shape=[],dtype=tf.string)
dics['image/width'] = tf.FixedLenFeature(shape=[], dtype=tf.int64)
dics['image/height'] = tf.FixedLenFeature(shape=[], dtype=tf.int64)
dics['image/object/class/text'] = tf.VarLenFeature(tf.string)
dics['image/filename'] = tf.VarLenFeature(tf.string)
dics['image/object/class/label'] = tf.VarLenFeature(tf.int64)
dics['image/object/bbox/xmin'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/xmax'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/ymin'] = tf.VarLenFeature(tf.float32)
dics['image/object/bbox/ymax'] = tf.VarLenFeature(tf.float32)
parse_example = tf.parse_single_example(serialized=example_proto,features=dics)
filename = parse_example['image/filename']
xmin = parse_example['image/object/bbox/xmin']
xmax = parse_example['image/object/bbox/xmax']
ymin = parse_example['image/object/bbox/ymin']
ymax = parse_example['image/object/bbox/ymax']
image = parse_example['image/encoded']#tf.decode_raw(parse_example['image/encoded'],out_type=tf.uint8)
image = img_data = tf.image.decode_jpeg(image)
w = parse_example['image/width']
h = parse_example['image/height']
label = parse_example['image/object/class/label']
return filename,image,w,h,xmin,xmax,ymin,ymax,label
dataset = tf.data.TFRecordDataset("./record/pascal_train.record")
dataset = dataset.map(parse_tf).batch(1).repeat(1)
iterator = dataset.make_one_shot_iterator()
next_element = iterator.get_next()
PATH_TO_LABELS = "record/pascal_label_map.pbtxt"
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map,max_num_classes = 221,use_display_name = True)
category_index = label_map_util.create_category_index(categories)
with tf.Session() as session:
filename,image, w, h,xmin, xmax, ymin, ymax ,label= session.run(fetches=next_element)
image_np = np.squeeze(image)
print(filename)
#可视化结果
boxes = list(np.stack((ymin.values, xmin.values, ymax.values, xmax.values),axis=1))
print(xmin.values)
classes = list(label.values)
scores = [[1,1] + [0]*18]
print(classes ,boxes)
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.reshape(boxes,(-1,4)),
np.array(classes),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=(8,8))
print(type(image_np))
print(image_np.shape)
image_np = np.array(image_np,dtype=np.uint8)
plt.imshow(image_np)
plt.show()
