def load_selective_search_roidb(self, gt_roidb):
"""
turn selective search proposals into selective search roidb
:param gt_roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
:return: roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
"""
import scipy.io
matfile = os.path.join(self.root_path, 'selective_search_data',
self.name + '.mat')
assert os.path.exists(
matfile), 'selective search data does not exist: {}'.format(
matfile)
raw_data = scipy.io.loadmat(
matfile)['boxes'].ravel() # original was dict ['images', 'boxes']
box_list = []
for i in range(raw_data.shape[0]):
boxes = raw_data[i][:,
(1, 0, 3,
2)] - 1 # pascal voc dataset starts from 1.
keep = unique_boxes(boxes)
boxes = boxes[keep, :]
keep = filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
box_list.append(boxes)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def _load_proposals(self, method, gt_roidb):
"""
Load pre-computed proposals in the format provided by Jan Hosang:
http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
computing/research/object-recognition-and-scene-understanding/how-
good-are-detection-proposals-really/
For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
CS/vision/grouping/mcg/ and convert the file layout using
lib/datasets/tools/mcg_munge.py.
"""
box_list = []
top_k = self.config['top_k']
valid_methods = [
'MCG',
'selective_search',
'edge_boxes_AR',
'edge_boxes_70']
assert method in valid_methods
print('Loading {} boxes'.format(method))
for i, index in enumerate(self._image_index):
if i % 1000 == 0:
print('{:d} / {:d}'.format(i + 1, len(self._image_index)))
box_file = osp.join(
cfg.DATA_DIR, 'coco_proposals', method, 'mat',
self._get_box_file(index))
raw_data = sio.loadmat(box_file)['boxes']
boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
if method == 'MCG':
# Boxes from the MCG website are in (y1, x1, y2, x2) order
boxes = boxes[:, (1, 0, 3, 2)]
# Remove duplicate boxes and very small boxes and then take top k
keep = ds_utils.unique_boxes(boxes)
boxes = boxes[keep, :]
keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
boxes = boxes[:top_k, :]
box_list.append(boxes)
# Sanity check
im_ann = self._COCO.loadImgs(index)[0]
width = im_ann['width']
height = im_ann['height']
ds_utils.validate_boxes(boxes, width=width, height=height)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def _load_proposals(self, method, gt_roidb):
"""
Load pre-computed proposals in the format provided by Jan Hosang:
http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-
computing/research/object-recognition-and-scene-understanding/how-
good-are-detection-proposals-really/
For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/
CS/vision/grouping/mcg/ and convert the file layout using
lib/datasets/tools/mcg_munge.py.
"""
box_list = []
top_k = self.config['top_k']
valid_methods = [
'MCG',
'selective_search',
'edge_boxes_AR',
'edge_boxes_70']
assert method in valid_methods
print 'Loading {} boxes'.format(method)
for i, index in enumerate(self._image_index):
if i % 1000 == 0:
print '{:d} / {:d}'.format(i + 1, len(self._image_index))
box_file = osp.join(
cfg.DATA_DIR, 'coco_proposals', method, 'mat',
self._get_box_file(index))
raw_data = sio.loadmat(box_file)['boxes']
boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
if method == 'MCG':
# Boxes from the MCG website are in (y1, x1, y2, x2) order
boxes = boxes[:, (1, 0, 3, 2)]
# Remove duplicate boxes and very small boxes and then take top k
keep = ds_utils.unique_boxes(boxes)
boxes = boxes[keep, :]
keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
boxes = boxes[:top_k, :]
box_list.append(boxes)
# Sanity check
im_ann = self._COCO.loadImgs(index)[0]
width = im_ann['width']
height = im_ann['height']
ds_utils.validate_boxes(boxes, width=width, height=height)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def _load_selective_search_roidb(self, gt_roidb):
filename = os.path.abspath(
os.path.join(cfg.DATA_DIR, 'selective_search_data',
self.name + '.mat'))
assert os.path.exists(filename), \
'Selective search data not found at: {}'.format(filename)
raw_data = sio.loadmat(filename)['boxes'].ravel()
box_list = []
for i in xrange(raw_data.shape[0]):
boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
keep = ds_utils.unique_boxes(boxes)
boxes = boxes[keep, :]
keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
box_list.append(boxes)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def _load_selective_search_roidb(self, gt_roidb):
filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
'selective_search_data',
self.name + '.mat'))
assert os.path.exists(filename), \
'Selective search data not found at: {}'.format(filename)
raw_data = sio.loadmat(filename)['boxes'].ravel()
box_list = []
for i in xrange(raw_data.shape[0]):
boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
keep = ds_utils.unique_boxes(boxes)
boxes = boxes[keep, :]
keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
box_list.append(boxes)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def load_selective_search_roidb(self, gt_roidb):
"""
turn selective search proposals into selective search roidb
:param gt_roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
:return: roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
"""
import scipy.io
matfile = os.path.join(self.root_path, 'selective_search_data', self.name + '.mat')
assert os.path.exists(matfile), 'selective search data does not exist: {}'.format(matfile)
raw_data = scipy.io.loadmat(matfile)['boxes'].ravel() # original was dict ['images', 'boxes']
box_list = []
for i in range(raw_data.shape[0]):
boxes = raw_data[i][:, (1, 0, 3, 2)] - 1 # pascal voc dataset starts from 1.
keep = unique_boxes(boxes)
boxes = boxes[keep, :]
keep = filter_small_boxes(boxes, self.config['min_size'])
boxes = boxes[keep, :]
box_list.append(boxes)
return self.create_roidb_from_box_list(box_list, gt_roidb)
