def gt_roidb(self):
"""
Return the database of ground-truth regions of interest.
"""
cache_file = os.path.join(self.cache_path, self.name + '_' + cfg.SUBCLS_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_kitti_voxel_exemplar_annotation(index)
for index in self.image_index]
if cfg.IS_RPN:
# print out recall
for i in xrange(1, self.num_classes):
print '{}: Total number of boxes {:d}'.format(self.classes[i], self._num_boxes_all[i])
print '{}: Number of boxes covered {:d}'.format(self.classes[i], self._num_boxes_covered[i])
print '{}: Recall {:f}'.format(self.classes[i], float(self._num_boxes_covered[i]) / float(self._num_boxes_all[i]))
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
python类SUBCLS_NAME的实例源码
def region_proposal_roidb(self):
"""
Return the database of regions of interest.
Ground-truth ROIs are also included.
This function loads/saves from/to a cache file to speed up future calls.
"""
cache_file = os.path.join(self.cache_path,
self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} roidb loaded from {}'.format(self.name, cache_file)
return roidb
if self._image_set != 'testing':
gt_roidb = self.gt_roidb()
print 'Loading region proposal network boxes...'
if self._image_set == 'trainval':
model = cfg.REGION_PROPOSAL + '_trainval/'
else:
model = cfg.REGION_PROPOSAL + '_train/'
rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
print 'Region proposal network boxes loaded'
roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
else:
print 'Loading region proposal network boxes...'
model = cfg.REGION_PROPOSAL + '_trainval/'
roidb = self._load_rpn_roidb(None, model)
print 'Region proposal network boxes loaded'
print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote roidb to {}'.format(cache_file)
return 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 + '_' + cfg.SUBCLS_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_pascal3d_voxel_exemplar_annotation(index)
for index in self.image_index]
if cfg.IS_RPN:
# print out recall
for i in xrange(1, self.num_classes):
print '{}: Total number of boxes {:d}'.format(self.classes[i], self._num_boxes_all[i])
print '{}: Number of boxes covered {:d}'.format(self.classes[i], self._num_boxes_covered[i])
print '{}: Recall {:f}'.format(self.classes[i], float(self._num_boxes_covered[i]) / float(self._num_boxes_all[i]))
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
def region_proposal_roidb(self):
"""
Return the database of regions of interest.
Ground-truth ROIs are also included.
This function loads/saves from/to a cache file to speed up future calls.
"""
cache_file = os.path.join(self.cache_path,
self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} roidb loaded from {}'.format(self.name, cache_file)
return roidb
if self._image_set != 'test':
gt_roidb = self.gt_roidb()
print 'Loading region proposal network boxes...'
model = cfg.REGION_PROPOSAL
rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
print 'Region proposal network boxes loaded'
roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
else:
print 'Loading region proposal network boxes...'
model = cfg.REGION_PROPOSAL
roidb = self._load_rpn_roidb(None, model)
print 'Region proposal network boxes loaded'
print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote roidb to {}'.format(cache_file)
return roidb
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the azimuth (viewpoint)
filename = os.path.join(self._pascal3d_path, cfg.SUBCLS_NAME, 'mapping.txt')
assert os.path.exists(filename), \
'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.float)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = float(words[2])
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
print 'Writing {} VOC results file'.format(cls)
filename = os.path.join(output_dir, 'det_' + self._image_set + '_' + cls + '.txt')
print filename
with open(filename, 'wt') as f:
for im_ind, index in enumerate(self.image_index):
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
# the VOCdevkit expects 1-based indices
for k in xrange(dets.shape[0]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
azimuth = mapping[subcls]
f.write('{:s} {:.3f} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
format(index, dets[k, 4], azimuth,
dets[k, 0] + 1, dets[k, 1] + 1,
dets[k, 2] + 1, dets[k, 3] + 1))
# evaluate detection results
def gt_roidb(self):
"""
Return the database of ground-truth regions of interest.
"""
cache_file = os.path.join(self.cache_path, self.name + '_' + cfg.SUBCLS_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_mot_voxel_exemplar_annotation(index)
for index in self.image_index]
if cfg.IS_RPN:
# print out recall
for i in xrange(1, self.num_classes):
print '{}: Total number of boxes {:d}'.format(self.classes[i], self._num_boxes_all[i])
print '{}: Number of boxes covered {:d}'.format(self.classes[i], self._num_boxes_covered[i])
print '{}: Recall {:f}'.format(self.classes[i], float(self._num_boxes_covered[i]) / float(self._num_boxes_all[i]))
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
def region_proposal_roidb(self):
"""
Return the database of regions of interest.
Ground-truth ROIs are also included.
This function loads/saves from/to a cache file to speed up future calls.
"""
cache_file = os.path.join(self.cache_path,
self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
roidb = cPickle.load(fid)
print '{} roidb loaded from {}'.format(self.name, cache_file)
return roidb
if self._image_set != 'test':
gt_roidb = self.gt_roidb()
print 'Loading region proposal network boxes...'
model = 'train/'
rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
print 'Region proposal network boxes loaded'
roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
else:
print 'Loading region proposal network boxes...'
model = 'test/'
roidb = self._load_rpn_roidb(None, model)
print 'Region proposal network boxes loaded'
print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))
with open(cache_file, 'wb') as fid:
cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote roidb to {}'.format(cache_file)
return 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 + '_' + cfg.SUBCLS_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_imagenet3d_annotation(index)
for index in self.image_index]
if cfg.IS_RPN:
# print out recall
for i in xrange(1, self.num_classes):
print '{}: Total number of boxes {:d}'.format(self.classes[i], self._num_boxes_all[i])
print '{}: Number of boxes covered {:d}'.format(self.classes[i], self._num_boxes_covered[i])
print '{}: Recall {:f}'.format(self.classes[i], float(self._num_boxes_covered[i]) / float(self._num_boxes_all[i]))
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
def gt_roidb(self):
"""
Return the database of ground-truth regions of interest.
"""
cache_file = os.path.join(self.cache_path, self.name + '_' + cfg.SUBCLS_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_kitti_voxel_exemplar_annotation(index)
for index in self.image_index]
if cfg.IS_RPN:
# print out recall
for i in xrange(1, self.num_classes):
print '{}: Total number of boxes {:d}'.format(self.classes[i], self._num_boxes_all[i])
print '{}: Number of boxes covered {:d}'.format(self.classes[i], self._num_boxes_covered[i])
print '{}: Recall {:f}'.format(self.classes[i], float(self._num_boxes_covered[i]) / float(self._num_boxes_all[i]))
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
pascal3d.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 20
收藏 0
点赞 0
评论 0
def __init__(self, image_set, pascal3d_path = None):
datasets.imdb.__init__(self, 'pascal3d_' + image_set)
self._year = '2012'
self._image_set = image_set
self._pascal3d_path = self._get_default_path() if pascal3d_path is None \
else pascal3d_path
self._data_path = os.path.join(self._pascal3d_path, 'VOCdevkit' + self._year, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'aeroplane', 'bicycle', 'boat',
'bottle', 'bus', 'car', 'chair',
'diningtable', 'motorbike',
'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
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if cfg.SUBCLS_NAME == 'voxel_exemplars':
self._num_subclasses = 337 + 1
elif cfg.SUBCLS_NAME == 'pose_exemplars':
self._num_subclasses = 260 + 1
else:
assert (1), 'cfg.SUBCLS_NAME not supported!'
# load the mapping for subcalss to class
filename = os.path.join(self._pascal3d_path, cfg.SUBCLS_NAME, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
# PASCAL specific config options
self.config = {'cleanup' : True,
'use_salt' : True,
'top_k' : 2000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._pascal3d_path), \
'PASCAL3D path does not exist: {}'.format(self._pascal3d_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
kitti.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 28
收藏 0
点赞 0
评论 0
def __init__(self, image_set, kitti_path=None):
datasets.imdb.__init__(self, 'kitti_' + image_set)
self._image_set = image_set
self._kitti_path = self._get_default_path() if kitti_path is None \
else kitti_path
self._data_path = os.path.join(self._kitti_path, 'data_object_image_2')
self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.png'
self._image_index = self._load_image_set_index()
# Default to roidb handler
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if image_set == 'train' or image_set == 'val':
self._num_subclasses = 125 + 24 + 24 + 1
prefix = 'validation'
else:
self._num_subclasses = 227 + 36 + 36 + 1
prefix = 'test'
# load the mapping for subcalss to class
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
self.config = {'top_k': 100000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._kitti_path), \
'KITTI path does not exist: {}'.format(self._kitti_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
kitti.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 25
收藏 0
点赞 0
评论 0
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
if self._image_set == 'val':
prefix = 'validation'
elif self._image_set == 'test':
prefix = 'test'
else:
prefix = ''
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), \
'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.float)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = float(words[3])
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
# for each class
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
if cfg.TEST.SUBCLS:
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
else:
alpha = -10
f.write('{:s} -1 -1 {:f} {:f} {:f} {:f} {:f} -1 -1 -1 -1 -1 -1 -1 {:.32f}\n'.format(\
cls, alpha, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
# write detection results into one file
def __init__(self, image_set, pascal3d_path = None):
datasets.imdb.__init__(self, 'pascal3d_' + image_set)
self._year = '2012'
self._image_set = image_set
self._pascal3d_path = self._get_default_path() if pascal3d_path is None \
else pascal3d_path
self._data_path = os.path.join(self._pascal3d_path, 'VOCdevkit' + self._year, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'aeroplane', 'bicycle', 'boat',
'bottle', 'bus', 'car', 'chair',
'diningtable', 'motorbike',
'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
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if cfg.SUBCLS_NAME == 'voxel_exemplars':
self._num_subclasses = 337 + 1
elif cfg.SUBCLS_NAME == 'pose_exemplars':
self._num_subclasses = 260 + 1
else:
assert (1), 'cfg.SUBCLS_NAME not supported!'
# load the mapping for subcalss to class
filename = os.path.join(self._pascal3d_path, cfg.SUBCLS_NAME, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
# PASCAL specific config options
self.config = {'cleanup' : True,
'use_salt' : True,
'top_k' : 2000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._pascal3d_path), \
'PASCAL3D path does not exist: {}'.format(self._pascal3d_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
def __init__(self, image_set, kitti_path=None):
datasets.imdb.__init__(self, 'kitti_' + image_set)
self._image_set = image_set
self._kitti_path = self._get_default_path() if kitti_path is None \
else kitti_path
self._data_path = os.path.join(self._kitti_path, 'data_object_image_2')
self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.png'
self._image_index = self._load_image_set_index()
# Default to roidb handler
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if image_set == 'train' or image_set == 'val':
self._num_subclasses = 125 + 24 + 24 + 1
prefix = 'validation'
else:
self._num_subclasses = 227 + 36 + 36 + 1
prefix = 'test'
# load the mapping for subcalss to class
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
self.config = {'top_k': 100000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._kitti_path), \
'KITTI path does not exist: {}'.format(self._kitti_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
if self._image_set == 'val':
prefix = 'validation'
elif self._image_set == 'test':
prefix = 'test'
else:
prefix = ''
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), \
'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.float)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = float(words[3])
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
# for each class
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
if cfg.TEST.SUBCLS:
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
else:
alpha = -10
f.write('{:s} -1 -1 {:f} {:f} {:f} {:f} {:f} -1 -1 -1 -1 -1 -1 -1 {:.32f}\n'.format(\
cls, alpha, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
# write detection results into one file
def __init__(self, image_set, pascal3d_path = None):
datasets.imdb.__init__(self, 'pascal3d_' + image_set)
self._year = '2012'
self._image_set = image_set
self._pascal3d_path = self._get_default_path() if pascal3d_path is None \
else pascal3d_path
self._data_path = os.path.join(self._pascal3d_path, 'VOCdevkit' + self._year, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'aeroplane', 'bicycle', 'boat',
'bottle', 'bus', 'car', 'chair',
'diningtable', 'motorbike',
'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
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if cfg.SUBCLS_NAME == 'voxel_exemplars':
self._num_subclasses = 337 + 1
elif cfg.SUBCLS_NAME == 'pose_exemplars':
self._num_subclasses = 260 + 1
else:
assert (1), 'cfg.SUBCLS_NAME not supported!'
# load the mapping for subcalss to class
filename = os.path.join(self._pascal3d_path, cfg.SUBCLS_NAME, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
# PASCAL specific config options
self.config = {'cleanup' : True,
'use_salt' : True,
'top_k' : 2000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._pascal3d_path), \
'PASCAL3D path does not exist: {}'.format(self._pascal3d_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
def __init__(self, image_set, kitti_path=None):
datasets.imdb.__init__(self, 'kitti_' + image_set)
self._image_set = image_set
self._kitti_path = self._get_default_path() if kitti_path is None \
else kitti_path
self._data_path = os.path.join(self._kitti_path, 'data_object_image_2')
self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.png'
self._image_index = self._load_image_set_index()
# Default to roidb handler
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if image_set == 'train' or image_set == 'val':
self._num_subclasses = 125 + 24 + 24 + 1
prefix = 'validation'
else:
self._num_subclasses = 227 + 36 + 36 + 1
prefix = 'test'
# load the mapping for subcalss to class
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
self.config = {'top_k': 100000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._kitti_path), \
'KITTI path does not exist: {}'.format(self._kitti_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
if self._image_set == 'val':
prefix = 'validation'
elif self._image_set == 'test':
prefix = 'test'
else:
prefix = ''
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), \
'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.float)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = float(words[3])
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
# for each class
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
if cfg.TEST.SUBCLS:
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
else:
alpha = -10
f.write('{:s} -1 -1 {:f} {:f} {:f} {:f} {:f} -1 -1 -1 -1 -1 -1 -1 {:.32f}\n'.format(\
cls, alpha, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
# write detection results into one file
def __init__(self, image_set, pascal3d_path = None):
datasets.imdb.__init__(self, 'pascal3d_' + image_set)
self._year = '2012'
self._image_set = image_set
self._pascal3d_path = self._get_default_path() if pascal3d_path is None \
else pascal3d_path
self._data_path = os.path.join(self._pascal3d_path, 'VOCdevkit' + self._year, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'aeroplane', 'bicycle', 'boat',
'bottle', 'bus', 'car', 'chair',
'diningtable', 'motorbike',
'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
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if cfg.SUBCLS_NAME == 'voxel_exemplars':
self._num_subclasses = 337 + 1
elif cfg.SUBCLS_NAME == 'pose_exemplars':
self._num_subclasses = 260 + 1
else:
assert (1), 'cfg.SUBCLS_NAME not supported!'
# load the mapping for subcalss to class
filename = os.path.join(self._pascal3d_path, cfg.SUBCLS_NAME, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
# PASCAL specific config options
self.config = {'cleanup' : True,
'use_salt' : True,
'top_k' : 2000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._pascal3d_path), \
'PASCAL3D path does not exist: {}'.format(self._pascal3d_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
def __init__(self, image_set, kitti_path=None):
datasets.imdb.__init__(self, 'kitti_' + image_set)
self._image_set = image_set
self._kitti_path = self._get_default_path() if kitti_path is None \
else kitti_path
self._data_path = os.path.join(self._kitti_path, 'data_object_image_2')
self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.png'
self._image_index = self._load_image_set_index()
# Default to roidb handler
if cfg.IS_RPN:
self._roidb_handler = self.gt_roidb
else:
self._roidb_handler = self.region_proposal_roidb
# num of subclasses
if image_set == 'train' or image_set == 'val':
self._num_subclasses = 125 + 24 + 24 + 1
prefix = 'validation'
else:
self._num_subclasses = 227 + 36 + 36 + 1
prefix = 'test'
# load the mapping for subcalss to class
filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
mapping = np.zeros(self._num_subclasses, dtype=np.int)
with open(filename) as f:
for line in f:
words = line.split()
subcls = int(words[0])
mapping[subcls] = self._class_to_ind[words[1]]
self._subclass_mapping = mapping
self.config = {'top_k': 100000}
# statistics for computing recall
self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
self._num_boxes_proposal = 0
assert os.path.exists(self._kitti_path), \
'KITTI path does not exist: {}'.format(self._kitti_path)
assert os.path.exists(self._data_path), \
'Path does not exist: {}'.format(self._data_path)
