def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
python类nthu()的实例源码
nthu.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 19
收藏 0
点赞 0
评论 0
nthu.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 17
收藏 0
点赞 0
评论 0
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_detections_one_file(self, all_boxes, output_dir):
# open results file
filename = os.path.join(output_dir, 'detections.txt')
print 'Writing all nthu results to file ' + filename
with open(filename, 'wt') as f:
# for each image
for im_ind, index in enumerate(self.image_index):
# 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
f.write('{:s} {:s} {:f} {:f} {:f} {:f} {:d} {:f}\n'.format(\
index, cls, dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], subcls, dets[k, 4]))
def evaluate_proposals(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu 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]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
nthu.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 21
收藏 0
点赞 0
评论 0
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
nthu.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 16
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)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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
nthu.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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def _get_default_path(self):
"""
Return the default path where nthu is expected to be installed.
"""
return os.path.join(datasets.ROOT_DIR, 'data', 'NTHU')
def evaluate_detections(self, all_boxes, output_dir):
# load the mapping for subcalss the alpha (viewpoint)
filename = os.path.join(self._nthu_path, '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 nthu 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]):
subcls = int(dets[k, 5])
cls_name = self.classes[self.subclass_mapping[subcls]]
assert (cls_name == cls), 'subclass not in class'
alpha = mapping[subcls]
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 evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing nthu results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
