imdb对象是一个pascol _voc的类实例，该类继承自imdb，用于数据交互。
初始化函数
在初始化自身的同时，先调用了父类的初始化方法，将imdb _name传入，例如(‘voc_2007_trainval’)
class pascal _voc(imdb):
def __init_
_(
self, image_set, year, devkit_path=
None)
:
imdb.__init_
_(
self,
'voc_' + year +
'_' + image_set)
self._year = year
self._image_set = image_set
self._devkit_path =
self._get_default_path()
if devkit_path is
None
else devkit_path
self._data_path = os.path.join(
self._devkit_path,
'VOC' +
self._year)
self._classes = (
'__background__',
'aeroplane',
'bicycle',
'bird',
'boat',
'bottle',
'bus',
'car',
'cat',
'chair',
'cow',
'diningtable',
'dog',
'horse',
'motorbike',
'person',
'pottedplant',
'sheep',
'sofa',
'train',
'tvmonitor')
self._class_to_ind = dict(zip(
self.classes, xrange(
self.num_classes)))
self._image_ext =
'.jpg'
self._image_index =
self._load_image_set_index()
self._roidb_handler =
self.selective_search_roidb
self._salt = str(uuid.uuid4())
self._comp_id =
'comp4'
self.config = {
'cleanup' : True,
'use_salt' : True,
'use_diff' : False,
'matlab_eval' : False,
'rpn_file' : None,
'min_size' : 2}
assert os.path.exists(
self._devkit_path),
'VOCdevkit path does not exist: {}'.format(
self._devkit_path)
assert os.path.exists(
self._data_path),
'Path does not exist: {}'.format(
self._data_path)
1234567891011121314151617181920212223242526272829303132333435
1234567891011121314151617181920212223242526272829303132333435
image _path _from _index
根据图片的索引，比如‘000001’获取在JPEGImages下对应的图片路径
def image_path_at(self, i):
"""
Return the absolute path to image i in the image sequence.
"""
return self.image_path_from_index(self._image_index[i])
def image_path_from_index(self, index):
"""
Construct an image path from the image's "index" identifier.
"""
image_path = os.path.join(self._data_path,
'JPEGImages',
index + self._image_ext)
assert os.path.exists(image_path),
'Path does not exist: {}'.format(image_path)
return image_path
def _load_image_set_index(self):
"""
Load the indexes listed in this dataset's image set file.
"""
image_set_file = os.path.join(self._data_path,
'ImageSets',
'Main',
self._image_set +
'.txt')
assert os.path.exists(image_set_file),
'Path does not exist: {}'.format(image_set_file)
with open(image_set_file)
as f:
image_index = [x.strip()
for x
in f.readlines()]
return image_index
123456789101112131415161718192021222324252627282930313233
123456789101112131415161718192021222324252627282930313233
_get _default _path
返回默认的数据源路径，这里是放在data下的VOCDevkit2007
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR,
'VOCdevkit' + self._year)
123456
123456
gt _roidb
这个函数返回roidb数据对象。首先它会在cache路径下找到以扩展名’.pkl’结尾的缓存，这个文件是通过cPickle工具将roidb序列化存储的。如果该文件存在，那么它会先读取这里的内容，以提高效率(所以如果你换数据集的时候，要先把cache文件给删除，否则会造成错误)。接着，它将调用 _load _pascal _annotation这个私有函数加载roidb中的数据，并将其保存在缓存文件中，返回roidb。
def gt_roidb(self):
"""
Return the database of ground-truth regions of interest.
This function loads/saves from/to a cache file to speed up future calls.
"""
cache_file = os.path.join(self.cache_path, self.name + '_gt_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} gt roidb loaded from {}'.format(self.name, cache_file)
return roidb
gt_roidb = [self._load_pascal_annotation(index)
for index in self.image_index]
with open(cache_file, 'wb') as fid:
cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote gt roidb to {}'.format(cache_file)
return gt_roidb
4567891011121314151617181920212223
123456789101112131415161718
123456789101112131415161718
_load _pascal _annotation
根据每个图像的索引，到Annotations这个文件夹下去找相应的xml标注数据，然后加载所有的bounding box对象。
最后将这些成员变量组装成roidb返回
def _load_pascal_annotation(self, index):
"""
Load image and bounding boxes info from XML file in the PASCAL VOC
format.
"""
filename = os.path.join(self._data_path,
'Annotations', index +
'.xml')
tree = ET.parse(filename)
objs = tree.findall(
'object')
if not self.config[
'use_diff']:
non_diff_objs = [
obj
for obj
in objs
if int(obj.find(
'difficult').text) ==
0]
objs = non_diff_objs
num_objs = len(objs)
boxes = np.zeros((num_objs,
4), dtype=np.uint16)
gt_classes = np.zeros((num_objs), dtype=np.int32)
overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)
seg_areas = np.zeros((num_objs), dtype=np.float32)
for ix, obj
in enumerate(objs):
bbox = obj.find(
'bndbox')
x1 = float(bbox.find(
'xmin').text) -
1
y1 = float(bbox.find(
'ymin').text) -
1
x2 = float(bbox.find(
'xmax').text) -
1
y2 = float(bbox.find(
'ymax').text) -
1
cls = self._class_to_ind[obj.find(
'name').text.lower().strip()]
boxes[ix, :] = [x1, y1, x2, y2]
gt_classes[ix] = cls
overlaps[ix, cls] =
1.0
seg_areas[ix] = (x2 - x1 +
1) * (y2 - y1 +
1)
overlaps = scipy.sparse.csr_matrix(overlaps)
return {
'boxes' : boxes,
'gt_classes': gt_classes,
'gt_overlaps' : overlaps,
'flipped' :
False,
'seg_areas' : seg_areas}
123456789101112131415161718192021222324252627282930313233343536373839404142434445
123456789101112131415161718192021222324252627282930313233343536373839404142434445
1234
1234
rpn _roidb
经过RPN网络产生了proposal以后，这个函数作用是将这些proposal 的 roi与groudtruth结合起来，送入网络训练。最后用merge _roidbs将gr _roidb与rpn _roidb合并输出。
def rpn_roidb(self):
if int(self._year) ==
2007 or self._image_set !=
'test':
gt_roidb = self.gt_roidb()
rpn_roidb = self._load_rpn_roidb(gt_roidb)
roidb = imdb.merge_roidbs(gt_roidb, rpn_roidb)
else:
roidb = self._load_rpn_roidb(
None)
return roidb
def _load_rpn_roidb(self, gt_roidb):
filename = self.config[
'rpn_file']
print 'loading {}'.format(filename)
assert os.path.exists(filename),
'rpn data not found at: {}'.format(filename)
with open(filename,
'rb')
as f:
box_list = cPickle.load(f)
return self.create_roidb_from_box_list(box_list, gt_roidb)
12345678910111213141516171819
123456789101112131415161718
