def __call__(self, im, im_info=None, label=None): """ Args: im (np.ndarray): The Image data. im_info (dict, optional): A dictionary maintains image info before this transformation. Default: None. label (np.ndarray, optional): The label data. Default: None. Returns: (tuple). When label is None, it returns (im, im_info), otherwise it returns (im, im_info, label). """ if self.min_value == self.max_value: random_size = self.max_value else: random_size = int( np.random.uniform(self.min_value, self.max_value) + 0.5) im = functional.resize_long(im, random_size, cv2.INTER_LINEAR) if label is not None: label = functional.resize_long(label, random_size, cv2.INTER_NEAREST) if label is None: return (im, im_info) else: return (im, im_info, label)
def __call__(self, im, label=None): """ Args: im (np.ndarray): The Image data. label (np.ndarray, optional): The label data. Default: None. Returns: (tuple). When label is None, it returns (im, ), otherwise it returns (im, label). """ h, w = im.shape[0], im.shape[1] long_edge = max(h, w) target = long_edge if (self.max_long is not None) and (long_edge > self.max_long): target = self.max_long elif (self.min_long is not None) and (long_edge < self.min_long): target = self.min_long if target != long_edge: im = functional.resize_long(im, target) if label is not None: label = functional.resize_long(label, target, cv2.INTER_NEAREST) if label is None: return (im, ) else: return (im, label)
def __call__(self, data): data['trans_info'].append(('resize', data['img'].shape[0:2])) data['img'] = functional.resize_long(data['img'], self.long_size) for key in data.get('gt_fields', []): data[key] = functional.resize_long(data[key], self.long_size, cv2.INTER_NEAREST) return data
def __call__(self, data): if self.min_value == self.max_value: random_size = self.max_value else: random_size = int( np.random.uniform(self.min_value, self.max_value) + 0.5) data['img'] = functional.resize_long(data['img'], random_size, cv2.INTER_LINEAR) for key in data.get('gt_fields', []): data[key] = functional.resize_long(data[key], random_size, cv2.INTER_NEAREST) return data
def __call__(self, data): h, w = data['img'].shape[:2] long_edge = max(h, w) target = long_edge if (self.max_long is not None) and (long_edge > self.max_long): target = self.max_long elif (self.min_long is not None) and (long_edge < self.min_long): target = self.min_long if target != long_edge: data['trans_info'].append(('resize', data['img'].shape[0:2])) data['img'] = functional.resize_long(data['img'], target) for key in data.get('gt_fields', []): data[key] = functional.resize_long(data[key], target) return data
def __call__(self, im, label=None): """ Args: im (np.ndarray): The Image data. label (np.ndarray, optional): The label data. Default: None. Returns: (tuple). When label is None, it returns (im, ), otherwise it returns (im, label). """ im = functional.resize_long(im, self.long_size) if label is not None: label = functional.resize_long(label, self.long_size, cv2.INTER_NEAREST) if label is None: return (im, ) else: return (im, label)
def __call__(self, im, im_info=None, label=None): """ Args: im (np.ndarray): The Image data. im_info (dict, optional): A dictionary maintains image info before this transformation. Default: None. label (np.ndarray, optional): The label data. Default: None. Returns: (tuple). When label is None, it returns (im, im_info), otherwise it returns (im, im_info, label). """ if im_info is None: im_info = list() im_info.append(('resize', im.shape[:2])) im = functional.resize_long(im, self.long_size) if label is not None: label = functional.resize_long(label, self.long_size, cv2.INTER_NEAREST) if label is None: return (im, im_info) else: return (im, im_info, label)