Python cfg.DATA_DIR属性代码示例

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def demo(sess, net, image_name):
  """Detect pedestrians in an image using pre-computed model."""

  # Load the demo image
  im1_file = os.path.join(cfg.DATA_DIR, 'demo', image_name + '_visible.png')
  im1 = cv2.imread(im1_file)
  im2_file = os.path.join(cfg.DATA_DIR, 'demo', image_name + '_lwir.png')
  im2 = cv2.imread(im2_file)
  im = [im1, im2]

  # Detect all object classes and regress object bounds
  timer = Timer()
  timer.tic()
  boxes, scores = im_detect_demo(sess, net, im)
  timer.toc()
  print('Detection took {:.3f}s for {:d} object proposals'.format(timer.total_time, boxes.shape[0]))

  # Visualize detections for each class
  CONF_THRESH = 0.5
  NMS_THRESH = 0.3

  dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
  keep = nms(dets, NMS_THRESH)
  dets = dets[keep, :]
  vis_detections(im, dets, thresh=CONF_THRESH) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def __init__(self, image_set, year):
    imdb.__init__(self, 'coco_' + year + '_' + image_set)
    # COCO specific config options
    self.config = {'use_salt': True,
                   'cleanup': True}
    # name, paths
    self._year = year
    self._image_set = image_set
    self._data_path = osp.join(cfg.DATA_DIR, 'coco')
    # load COCO API, classes, class <-> id mappings
    self._COCO = COCO(self._get_ann_file())
    cats = self._COCO.loadCats(self._COCO.getCatIds())
    self._classes = tuple(['__background__'] + [c['name'] for c in cats])
    self._class_to_ind = dict(list(zip(self.classes, list(range(self.num_classes)))))
    self._class_to_coco_cat_id = dict(list(zip([c['name'] for c in cats],
                                               self._COCO.getCatIds())))
    self._image_index = self._load_image_set_index()
    # Default to roidb handler
    self.set_proposal_method('gt')
    self.competition_mode(False)

    # Some image sets are "views" (i.e. subsets) into others.
    # For example, minival2014 is a random 5000 image subset of val2014.
    # This mapping tells us where the view's images and proposals come from.
    self._view_map = {
      'minival2014': 'val2014',  # 5k val2014 subset
      'valminusminival2014': 'val2014',  # val2014 \setminus minival2014
      'test-dev2015': 'test2015',
    }
    coco_name = image_set + year  # e.g., "val2014"
    self._data_name = (self._view_map[coco_name]
                       if coco_name in self._view_map
                       else coco_name)
    # Dataset splits that have ground-truth annotations (test splits
    # do not have gt annotations)
    self._gt_splits = ('train', 'val', 'minival') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def cache_path(self):
    cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
    if not os.path.exists(cache_path):
      os.makedirs(cache_path)
    return cache_path 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def demo(net, image_name):
    """Detect object classes in an image using pre-computed object proposals."""

    # Load the demo image
    im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
    im = cv2.imread(im_file)

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(net, im)
    timer.toc()
    print('Detection took {:.3f}s for {:d} object proposals'.format(timer.total_time(), boxes.shape[0]))

    # Visualize detections for each class
    CONF_THRESH = 0.8
    NMS_THRESH = 0.3
    for cls_ind, cls in enumerate(CLASSES[1:]):
        cls_ind += 1 # because we skipped background
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        dets = np.hstack((cls_boxes,
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(torch.from_numpy(dets), NMS_THRESH)
        dets = dets[keep.numpy(), :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def cache_path(self):
        cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
        if not os.path.exists(cache_path):
            os.makedirs(cache_path)
        return cache_path 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
        """
        Return the default path where Wider Face is expected to be installed.
        """
        return os.path.join(cfg.DATA_DIR, 'WIDER/WIDER_' + self._image_set) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
        """
        Return the default path where PASCAL VOC is expected to be installed.
        """
        return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    return os.path.join(cfg.DATA_DIR, 'NC2016_Test0613') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    return os.path.join(cfg.DATA_DIR, 'swapme') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    #return os.path.join(cfg.DATA_DIR, 'CASIA2')
    return os.path.join(cfg.DATA_DIR, 'cocostuff/coco/splicing') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    return os.path.join(cfg.DATA_DIR, 'CASIA1') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def demo(sess, net, image_name):
    """Detect object classes in an image using pre-computed object proposals."""

    # Load the demo image
    im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
    im = cv2.imread(im_file)

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(sess, net, im)
    timer.toc()
    print('Detection took {:.3f}s for {:d} object proposals'.format(timer.total_time, boxes.shape[0]))

    # Visualize detections for each class
    CONF_THRESH = 0.8
    NMS_THRESH = 0.3
    for cls_ind, cls in enumerate(CLASSES[1:]):
        cls_ind += 1 # because we skipped background
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        dets = np.hstack((cls_boxes,
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def _get_default_path(self):
    """
    Return the default path where PASCAL VOC is expected to be installed.
    """
    return os.path.join(cfg.DATA_DIR, 'kaist') 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import DATA_DIR [as 别名]
def __init__(self, image_set, count=5):
    imdb.__init__(self, 'visual_genome_%s_%d' % (image_set, count))
    self._image_set = image_set
    self._root_path = osp.join(cfg.DATA_DIR, 'visual_genome')
    self._name_file = osp.join(self._root_path, 'synsets.txt')
    self._anno_file = osp.join(self._root_path, self._image_set + '.json')
    self._image_file = osp.join(self._root_path, 'image_data.json')
    with open(self._name_file) as fid:
      lines = fid.readlines()
      self._raw_names = []
      self._raw_counts = []
      for line in lines:
        name, cc = line.strip().split(':')
        cc = int(cc)
        self._raw_names.append(name)
        self._raw_counts.append(cc)
      self._len_raw = len(self._raw_names)

    self._raw_counts = np.array(self._raw_counts)
    # First class is always background
    self._vg_inds = [0] + list(np.where(self._raw_counts >= count)[0])
    self._classes = ['__background__']

    for idx in self._vg_inds:
      if idx == 0:
        continue
      vg_name = self._raw_names[idx]
      self._classes.append(vg_name)

    self._classes = tuple(self._classes)
    self._class_to_ind = dict(list(zip(self.classes, list(range(self.num_classes)))))
    self.set_proposal_method('gt')
    # Call to get one
    self.roidb