主要定義了一個pascal_voc類，在類的內部定義了它的一些屬性和方法。
def _init_(self, image_set, year, devkit_path=None) 構造器方法
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'voc_' + year + '_' + image_set)
self._year = year
self._image_set = image_set
# print '~~~~~~~~~~~~~~~~~~~PASCAL_VOC OBJECT _image_set: {}'.format(self._image_set) # trainval
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__', # always index 0
'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()
# Default to roidb handler
# self.selective_search_roidb是一個函數對象，把這個函數對象付給_roidb_handler屬性
self._roidb_handler = self.selective_search_roidb
self._salt = str(uuid.uuid4())
self._comp_id = 'comp4'
# PASCAL specific config options
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)def gt_roidb(self) 以’gt’ 方法生成roidb 。其中會調用_load_pascal_annotation方法從下載的數據文件annotation中載入圖像的ground-truth信息。
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_roidbdef _load_pascal_annotation(self, index) 從XML文件載入圖像信息，而且是ground-truth信息，比如boxes
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']:
# Exclude the samples labeled as difficult
non_diff_objs = [
obj for obj in objs if int(obj.find('difficult').text) == 0]
# if len(non_diff_objs) != len(objs):
# print 'Removed {} difficult objects'.format(
# len(objs) - len(non_diff_objs))
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爲 num_objs * K 的數組， K表示總共的類別數， num_objs表示當前這張圖片中box的個數
overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)
# "Seg" area for pascal is just the box area
seg_areas = np.zeros((num_objs), dtype=np.float32)
# Load object bounding boxes into a data frame.
for ix, obj in enumerate(objs):
bbox = obj.find('bndbox')
# Make pixel indexes 0-based
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
# 從anatation直接載入圖像的信息，因爲本身就是ground-truth , 所以overlap直接設爲1
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}def rpn_roidb(self)： 以‘rpn’ 方法生成roidb。先調用gt_roidb生成gt_roidb, 然後調用_load_rpn_roidb載入rpn_roidb， 最後調用其父類的靜態方法imdb.merge_roidbs將兩者合併，即對於最後生成的roidb中每一張圖像中，即包含gt_roidb中的box等信息，也包含rpn_roidb 中的box等信息。
def rpn_roidb(self):
if int(self._year) == 2007 or self._image_set != 'test':
gt_roidb = self.gt_roidb()
# 求取rpn_roidb需要以gt_roidb作爲參數才能得到
rpn_roidb = self._load_rpn_roidb(gt_roidb)
roidb = imdb.merge_roidbs(gt_roidb, rpn_roidb)
else:
roidb = self._load_rpn_roidb(None)
return roidbdef _load_rpn_roidb(self, gt_roidb) 調用父類方法create_roidb_from_box_list 從box_list 中讀取每張圖像的boxes
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:
# 讀取rpn_file裏的box，形成box_list; box_list爲一個列表，每張圖像對應其中的一個元素，
# 所以box_list 的大小要與gt_roidb 相同
box_list = cPickle.load(f)
return self.create_roidb_from_box_list(box_list, gt_roidb)def create_roidb_from_box_list(self, box_list, gt_roidb)： 從box_list 中讀取每張圖像的boxes
def create_roidb_from_box_list(self, box_list, gt_roidb):
# box_list 的大小要與gt_roidb 相同， 並且各圖像一一對應
assert len(box_list) == self.num_images, \
'Number of boxes must match number of ground-truth images'
roidb = []
for i in xrange(self.num_images):
# 遍歷每張圖像， 當前圖像中box的個數
boxes = box_list[i]
# 當前這張圖像中的box個數
num_boxes = boxes.shape[0]
# overlaps的shape始終爲：num_boxes × num_classes 。
overlaps = np.zeros((num_boxes, self.num_classes), dtype=np.float32)
if gt_roidb is not None and gt_roidb[i]['boxes'].size > 0:
gt_boxes = gt_roidb[i]['boxes']
gt_classes = gt_roidb[i]['gt_classes']
# 計算當前圖像的rpn_file中記錄的boxes與gtboxes的IOU overlap， 返回的gt_overlaps的
#shape爲 num_boxes × num_gtboxes， 後面要對gt_overlaps求max和argmax
gt_overlaps = bbox_overlaps(boxes.astype(np.float),
gt_boxes.astype(np.float))
# 對gt_overlaps 求argmax 和 max
argmaxes = gt_overlaps.argmax(axis=1)
maxes = gt_overlaps.max(axis=1)
# 返回 maxes > 0的位置信息
I = np.where(maxes > 0)[0]
overlaps[I, gt_classes[argmaxes[I]]] = maxes[I]
overlaps = scipy.sparse.csr_matrix(overlaps)
roidb.append({
'boxes' : boxes,
# gt_classes 爲一個全0一維數組（這是爲什麼？？？？）
'gt_classes' : np.zeros((num_boxes,), dtype=np.int32),
# 最終還是將shape爲num_boxes × num_classes 的數組進行存儲， 所以，以‘rpn’方法生成的
#rpn_roidb中的gt_overlaps是rpn_file中的box與gt_roidb中box的overlap，而不像
#gt_roidb()方法生成的gt_roidb中的gt_overlaps全部爲1.0
'gt_overlaps' : overlaps,
'flipped' : False,
'seg_areas' : np.zeros((num_boxes,), dtype=np.float32),
})
return roidb