.format(self._devkit_path, self._get_comp_id(),
self._image_set, output_dir)
print('Running:\n{}'.format(cmd))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, output_dir):
self._write_voc_results_file(all_boxes)
self._do_python_eval(output_dir)
if self.config['matlab_eval']:
self._do_matlab_eval(output_dir)
if self.config['cleanup']:
for cls in self._classes:
if cls == '__background__':
continue
filename = self._get_voc_results_file_template().format(cls)
os.remove(filename)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
if __name__ == '__main__':
from datasets.wider import wider
d = wider()
res = d.roidb
from IPython import embed; embed()
split, year, use_diff=True))
# Set up coco_2014_<split>
for year in ['2014']:
for split in ['train', 'val', 'minival', 'valminusminival', 'trainval']:
name = 'coco_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: coco(split, year))
# Set up coco_2015_<split>
for year in ['2015']:
for split in ['test', 'test-dev']:
name = 'coco_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: coco(split, year))
# Set up wider dataset
for split in ['train', 'val', 'test']:
name = 'WIDER_{}'.format(split)
__sets[name] = (lambda split=split: wider(split))
def get_imdb(name):
"""Get an imdb (image database) by name."""
if name not in __sets:
raise KeyError('Unknown dataset: {}'.format(name))
return __sets[name]()
def list_imdbs():
"""List all registered imdbs."""
return list(__sets.keys())
"""Factory method for easily getting imdbs by name."""
from datasets.wider import wider
import numpy as np
__sets = {}
for split in ['train', 'val', 'test', 'train_val']:
name = 'wider_{}'.format(split)
__sets[name] = (
lambda split=split: wider(split, wider_path='./data/wider'))
def get_imdb(name):
"""Get an imdb (image database) by name."""
if not __sets.has_key(name):
raise KeyError('Unknown dataset: {}'.format(name))
return __sets[name]()
def list_imdbs():
"""List all registered imdbs."""
return __sets.keys()
for split in ['train', 'val', 'trainval', 'test', 'val1', 'val2']:
name = 'psdbCrop_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: psdbCrop(split, year))
# Set up psdb_<year>_<split> using selective search "fast" mode
for year in ['2015']:
for split in ['train', 'val', 'trainval', 'test']:
name = 'psdb_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: psdb(split, year))
# Set up wider_<year>_<split> using selective search "fast" mode
for year in ['2015']:
for split in ['train', 'val', 'trainval', 'test']:
name = 'wider_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: wider(split, year))
# Set up aichal_<year>_<split> using selective search "fast" mode
for year in ['2017']:
for split in ['train', 'val', 'trainval', 'test']:
name = 'aichal_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: aichal(split, year))
# Set up aichalCrop_<year>_<split> using selective search "fast" mode
for year in ['2017']:
for split in ['train', 'val', 'trainval', 'test']:
name = 'aichalCrop_{}_{}'.format(year, split)
__sets[name] = (lambda split=split, year=year: aichalCrop(split, year))
print('Running:\n{}'.format(cmd))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, output_dir):
self._write_voc_results_file(all_boxes)
self._do_python_eval(output_dir)
if self.config['matlab_eval']:
self._do_matlab_eval(output_dir)
if self.config['cleanup']:
for cls in self._classes:
if cls == '__background__':
continue
filename = self._get_voc_results_file_template().format(cls)
os.remove(filename)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
if __name__ == '__main__':
from datasets.wider import wider
d = wider()
res = d.roidb
from IPython import embed
embed()
# ------------------------------------------------------------------------------------------------
# This file is a modified version of https://github.com/rbgirshick/py-faster-rcnn by Ross Girshick
# Modified by Mahyar Najibi
# ------------------------------------------------------------------------------------------------
from datasets.wider import wider
__sets = {}
for split in ['train','val','test']:
name = 'wider_{}'.format(split)
__sets[name] = (lambda split=split: wider(split))
def get_imdb(name):
"""Get an imdb (image database) by name."""
if not __sets.has_key(name):
raise KeyError('Unknown dataset: {}'.format(name))
return __sets[name]()
#
# def evaluate_detections(self, all_boxes, output_dir):
# self._write_voc_results_file(all_boxes)
# self._do_python_eval(output_dir)
# if self.config['matlab_eval']:
# self._do_matlab_eval(output_dir)
# if self.config['cleanup']:
# for cls in self._classes:
# if cls == '__background__':
# continue
# filename = self._get_voc_results_file_template().format(cls)
# os.remove(filename)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
if __name__ == '__main__':
from datasets.wider import wider
d = wider('train')
res = d.roidb
from IPython import embed
embed()