Python xml.etree.ElementTree.ParseEroorについて

目的
自前の学習データを用いた物体検出を行うため、以下のサイトを参考にしてKerasでSSDを行っています。
http://qiita.com/slowsingle/items/64cc927bb29a49a7af14
まずは，コードの意味を理解するために，以下のファイルを用いて用意されたアノテーションデータ（VOC2007)から学習用のpklファイルの作成を試みています．
https://github.com/rykov8/ssd_keras/blob/master/PASCAL_VOC/get_data_from_XML.py

問題
自前のデータではなく，VOC2007に入っているアノテーションxmlファイルを用いて，以下のコードを走らせたのですが，etree.ElemetTreeの読み込みエラーと思われるエラーが生じています．コードはデフォルトのままになります．（フォルダの場所は変更しています．）
下記のエラーの対処方法について教えてください．よろしくお願いします．
環境
conda 4.5.1
Python 3.5.2

エラー
Traceback (most recent call last):
File "get_data_from_XML.py", line 89, in <module>
data = XML_preprocessor('VOCdevkit/VOC2007/Annotations/').data
File "get_data_from_XML.py", line 11, in init
self._preprocess_XML()
File "get_data_from_XML.py", line 16, in _preprocess_XML
tree = ElementTree.parse(self.path_prefix + filename)
File "/Users/anaconda/envs/py35/lib/python3.5/xml/etree/ElementTree.py", line 1184, in parse
tree.parse(source, parser)
File "/Users/anaconda/envs/py35/lib/python3.5/xml/etree/ElementTree.py", line 596, in parse
self._root = parser._parse_whole(source)
xml.etree.ElementTree.ParseError: not well-formed (invalid token): line 1, column 0

コード
import numpy as np
import os
from xml.etree import ElementTree

class XML_preprocessor(object):

def __init__(self, data_path):
    self.path_prefix = data_path
    self.num_classes = 20
    self.data = dict()
    self._preprocess_XML()

def _preprocess_XML(self):
    filenames = os.listdir(self.path_prefix)
    for filename in filenames:
        tree = ElementTree.parse(self.path_prefix + filename)
        root = tree.getroot()
        bounding_boxes = []
        one_hot_classes = []
        size_tree = root.find('size')
        width = float(size_tree.find('width').text)
        height = float(size_tree.find('height').text)
        for object_tree in root.findall('object'):
            for bounding_box in object_tree.iter('bndbox'):
                xmin = float(bounding_box.find('xmin').text)/width
                ymin = float(bounding_box.find('ymin').text)/height
                xmax = float(bounding_box.find('xmax').text)/width
                ymax = float(bounding_box.find('ymax').text)/height
            bounding_box = [xmin,ymin,xmax,ymax]
            bounding_boxes.append(bounding_box)
            class_name = object_tree.find('name').text
            one_hot_class = self._to_one_hot(class_name)
            one_hot_classes.append(one_hot_class)
        image_name = root.find('filename').text
        bounding_boxes = np.asarray(bounding_boxes)
        one_hot_classes = np.asarray(one_hot_classes)
        image_data = np.hstack((bounding_boxes, one_hot_classes))
        self.data[image_name] = image_data

def _to_one_hot(self,name):
    one_hot_vector = [0] * self.num_classes
    if name == 'aeroplane':
        one_hot_vector[0] = 1
    elif name == 'bicycle':
        one_hot_vector[1] = 1
    elif name == 'bird':
        one_hot_vector[2] = 1
    elif name == 'boat':
        one_hot_vector[3] = 1
    elif name == 'bottle':
        one_hot_vector[4] = 1
    elif name == 'bus':
        one_hot_vector[5] = 1
    elif name == 'car':
        one_hot_vector[6] = 1
    elif name == 'cat':
        one_hot_vector[7] = 1
    elif name == 'chair':
        one_hot_vector[8] = 1
    elif name == 'cow':
        one_hot_vector[9] = 1
    elif name == 'diningtable':
        one_hot_vector[10] = 1
    elif name == 'dog':
        one_hot_vector[11] = 1
    elif name == 'horse':
        one_hot_vector[12] = 1
    elif name == 'motorbike':
        one_hot_vector[13] = 1
    elif name == 'person':
        one_hot_vector[14] = 1
    elif name == 'pottedplant':
        one_hot_vector[15] = 1
    elif name == 'sheep':
        one_hot_vector[16] = 1
    elif name == 'sofa':
        one_hot_vector[17] = 1
    elif name == 'train':
        one_hot_vector[18] = 1
    elif name == 'tvmonitor':
        one_hot_vector[19] = 1
    else:
        print('unknown label: %s' %name)

    return one_hot_vector

import pickle
data = XML_preprocessor('VOCdevkit/VOC2007/Annotations/').data
pickle.dump(data,open('VOC2007.pkl','wb'))

xmlファイル
<annotation>
<folder>VOC2007</folder>
<filename>000005.jpg</filename>
<source>
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
<flickrid>325991873</flickrid>
</source>
<owner>
<flickrid>archintent louisville</flickrid>
<name>?</name>
</owner>
<size>
<width>500</width>
<height>375</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>chair</name>
<pose>Rear</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>263</xmin>
<ymin>211</ymin>
<xmax>324</xmax>
<ymax>339</ymax>
</bndbox>
</object>
<object>
<name>chair</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>165</xmin>
<ymin>264</ymin>
<xmax>253</xmax>
<ymax>372</ymax>
</bndbox>
</object>
<object>
<name>chair</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>1</difficult>
<bndbox>
<xmin>5</xmin>
<ymin>244</ymin>
<xmax>67</xmax>
<ymax>374</ymax>
</bndbox>
</object>
<object>
<name>chair</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>241</xmin>
<ymin>194</ymin>
<xmax>295</xmax>
<ymax>299</ymax>
</bndbox>
</object>
<object>
<name>chair</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>1</difficult>
<bndbox>
<xmin>277</xmin>
<ymin>186</ymin>
<xmax>312</xmax>
<ymax>220</ymax>
</bndbox>
</object>
</annotation>