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 = 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
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 _load_musical_annotation(self, index):
"""
Load image and bounding boxes info from XML file in the PASCAL VOC
format.
"""
filename = os.path.join(self._data_path, 'xml_annotations',
index + '.xml')
tree = ET.parse(filename)
objs = tree.findall('object')
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" area for pascal is just the box area
seg_areas = np.zeros((num_objs), dtype=np.float32)
size = tree.find("size")
height = float(size.find("height").text)
width = float(size.find("width").text)
# Load object bounding boxes into a data frame.
for ix, obj in enumerate(objs):
bbox = obj.find('bndbox')
# Pixel indexes should already be 0 bases
x1 = np.floor(float(bbox.find('xmin').text) * width)
y1 = np.floor(float(bbox.find('ymin').text) * height)
x2 = np.floor(float(bbox.find('xmax').text) * width)
y2 = np.floor(float(bbox.find('ymax').text) * height)
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
}
def _load_pascal_annotation(self, index):
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)
# 按行来压缩
overlaps = scipy.sparse.csr_matrix(overlaps)
return {
'boxes': boxes,
'gt_classes': gt_classes,
'gt_overlaps': overlaps,
'flipped': False,
'seg_areas': seg_areas
}
