python CSV轉換tfrecord數據集

from __future__ import division
from __future__ import print_function
from __future__ import absolute_import

import os
import io
import pandas as pd
import tensorflow as tf
import sys
from PIL import Image

# sys.path.append("F:\setup\tf\models-master\research\object_detection")
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict

flags = tf.app.flags
flags.DEFINE_string('csv_input', default='/home/hanqing/SSD-Tensorflow-master/VOC2019/ImageSets/Main/csv/sj_train1.csv',help='')
flags.DEFINE_string('output_path', default='/home/hanqing/SSD-Tensorflow-master/tfrecords_/sj_train.record',help='')
flags.DEFINE_string('image_dir', default='/home/hanqing/SSD-Tensorflow-master/VOC2019/JPEGImages/sj_data/',help='')
FLAGS = flags.FLAGS


# TO-DO replace this with label map
def class_text_to_int(row_label):
    if row_label == "phone":#xml的name值
        return 1#返回id
    elif row_label == 'camera1':
        return 2
    elif row_label == 'camera2':
        return 3
    else:
        return 0


def split(df, group):
    data = namedtuple('data', ['filename', 'object'])
    # print(data)
    # print(df)
    # print(group)
    gb = df.groupby(group)
    # print(gb)
    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)
        # print(type(row['class']),row['class'])
        classes_text.append(str(row['class']).encode('utf8'))#如報錯檢查上面class_text_to_int方法值的類型
        # print(class_text_to_int(row['class']))
        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)
    # print(examples)
    grouped = split(examples, 'filename')
    # print(grouped,1)
    for group in grouped:
        tf_example = create_tf_example(group, path)
        print()
        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()

注：博客標註欄裏面有全套轉換過程，自取