Python glog.error方法代碼示例

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def normalize(gt_image, gt_binary_image, gt_instance_image):
    """
    Normalize the image data by substracting the imagenet mean value
    :param gt_image:
    :param gt_binary_image:
    :param gt_instance_image:
    :return:
    """

    if gt_image.get_shape().as_list()[-1] != 3 \
            or gt_binary_image.get_shape().as_list()[-1] != 1 \
            or gt_instance_image.get_shape().as_list()[-1] != 1:
        log.error(gt_image.get_shape())
        log.error(gt_binary_image.get_shape())
        log.error(gt_instance_image.get_shape())
        raise ValueError('Input must be of size [height, width, C>0]')

    gt_image = tf.cast(gt_image, dtype=tf.float32)
    gt_image = tf.subtract(tf.divide(gt_image, tf.constant(127.5, dtype=tf.float32)),
                           tf.constant(1.0, dtype=tf.float32))

    return gt_image, gt_binary_image, gt_instance_image 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _cluster(prediction, bandwidth):
        """
        實現論文SectionⅡ的cluster部分
        :param prediction:
        :param bandwidth:
        :return:
        """
        ms = MeanShift(bandwidth, bin_seeding=True)
        log.info('開始Mean shift聚類 ...')
        tic = time.time()
        try:
            ms.fit(prediction)
        except ValueError as err:
            log.error(err)
            return 0, [], []
        log.info('Mean Shift耗時: {:.5f}s'.format(time.time() - tic))
        labels = ms.labels_
        cluster_centers = ms.cluster_centers_

        num_clusters = cluster_centers.shape[0]

        log.info('聚類簇個數為: {:d}'.format(num_clusters))

        return num_clusters, labels, cluster_centers 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def imread(filename, dtype=np.float32, sfactor=1.0, image_type='rgb', flip=False):
    if exists(filename):
        image = cv2.imread(filename)
        if image_type == 'gray':
            image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        elif image_type == 'rgb':
            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        else:
            glog.error('Unknown format')

        if dtype == np.float32 or dtype == np.float64:
            image = image.astype(dtype)
            image /= 255.

        if sfactor != 1.0:
            image = cv2.resize(image, None, fx=sfactor, fy=sfactor)

        if flip:
            image = image[:, ::-1, :]
    else:
        glog.error('File {0} not found'.format(filename))
        image = np.array([-1])

    return image 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def get_dataset_info(path_to_dataset, info_file='info.txt'):
    fname = os.path.join(path_to_dataset, info_file)
    if os.path.exists(fname):
        info = np.loadtxt(fname, delimiter=':', dtype=str)
        out = {}
        for i in range(info.shape[0]):
            out[info[i, 0]] = info[i, 1]
        out['fps'] = int(out['fps'])
        out['height'] = int(out['height'])
        out['width'] = int(out['width'])
        out['ext'] = out['extension'][1:]

        if 'flipped' not in out:
            out['flipped'] = 0
        else:
            out['flipped'] = int(out['flipped'])

        return out
    else:
        glog.error('There is no info file in folder {0}'.format(path_to_dataset))
        return -1 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _embedding_feats_dbscan_cluster(embedding_image_feats):
        """
        dbscan cluster
        :param embedding_image_feats:
        :return:
        """
        db = DBSCAN(eps=CFG.POSTPROCESS.DBSCAN_EPS, min_samples=CFG.POSTPROCESS.DBSCAN_MIN_SAMPLES)
        try:
            features = StandardScaler().fit_transform(embedding_image_feats)
            db.fit(features)
        except Exception as err:
            log.error(err)
            ret = {
                'origin_features': None,
                'cluster_nums': 0,
                'db_labels': None,
                'unique_labels': None,
                'cluster_center': None
            }
            return ret
        db_labels = db.labels_
        unique_labels = np.unique(db_labels)

        num_clusters = len(unique_labels)
        cluster_centers = db.components_

        ret = {
            'origin_features': features,
            'cluster_nums': num_clusters,
            'db_labels': db_labels,
            'unique_labels': unique_labels,
            'cluster_center': cluster_centers
        }

        return ret 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _lane_fit(lane_pts):
        """
        車道線多項式擬合
        :param lane_pts:
        :return:
        """
        if not isinstance(lane_pts, np.ndarray):
            lane_pts = np.array(lane_pts, np.float32)

        x = lane_pts[:, 0]
        y = lane_pts[:, 1]
        x_fit = []
        y_fit = []
        with warnings.catch_warnings():
            warnings.filterwarnings('error')
            try:
                f1 = np.polyfit(y, x, 3)
                p1 = np.poly1d(f1)
                y_min = int(np.min(y))
                y_max = int(np.max(y))
                y_fit = []
                for i in range(y_min, y_max + 1):
                    y_fit.append(i)
                x_fit = p1(y_fit)
            except Warning as e:
                x_fit = x
                y_fit = y
            finally:
                return zip(x_fit, y_fit) 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _write_tfrecords(tfrecords_writer):
    """

    :param tfrecords_writer:
    :return:
    """
    while True:
        sample_info = _SAMPLE_INFO_QUEUE.get()

        if sample_info == _SENTINEL:
            log.info('Process {:d} finished writing work'.format(os.getpid()))
            tfrecords_writer.close()
            break

        sample_path = sample_info[0]
        sample_label = sample_info[1]

        if _is_valid_jpg_file(sample_path):
            log.error('Image file: {:d} is not a valid jpg file'.format(sample_path))
            continue

        try:
            image = cv2.imread(sample_path, cv2.IMREAD_COLOR)
            if image is None:
                continue
            image = cv2.resize(image, dsize=tuple(CFG.ARCH.INPUT_SIZE), interpolation=cv2.INTER_LINEAR)
            image = image.tostring()
        except IOError as err:
            log.error(err)
            continue

        features = tf.train.Features(feature={
            'labels': _int64_feature(sample_label),
            'images': _bytes_feature(image),
            'imagepaths': _bytes_feature(sample_path)
        })
        tf_example = tf.train.Example(features=features)
        tfrecords_writer.write(tf_example.SerializeToString())
        log.debug('Process: {:d} get sample from sample_info_queue[current_size={:d}], '
                  'and write it to local file at time: {}'.format(
                   os.getpid(), _SAMPLE_INFO_QUEUE.qsize(), time.strftime('%H:%M:%S'))) 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _init_example_info_queue(self):
        """
        Read index file and put example info into SAMPLE_INFO_QUEUE
        :return:
        """
        log.info('Start filling {:s} dataset sample information queue...'.format(self._dataset_flag))

        t_start = time.time()
        for annotation_info in tqdm.tqdm(self._annotation_infos):
            image_path = annotation_info[0]
            lexicon_index = annotation_info[1]

            try:
                lexicon_label = [self._lexicon_infos[lexicon_index]]
                encoded_label, _ = self.encode_labels(lexicon_label)

                _SAMPLE_INFO_QUEUE.put((image_path, encoded_label[0]))
            except IndexError:
                log.error('Lexicon doesn\'t contain lexicon index {:d}'.format(lexicon_index))
                continue
        for i in range(self._writer_process_nums):
            _SAMPLE_INFO_QUEUE.put(_SENTINEL)
        log.debug('Complete filling dataset sample information queue[current size: {:d}], cost time: {:.5f}s'.format(
            _SAMPLE_INFO_QUEUE.qsize(),
            time.time() - t_start
        )) 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def imagesc(matrix, points=None, ax=None, cmap='jet', grid=True, show_axis=True, vmin=None, vmax=None):

    if len(matrix.shape) > 2:
        glog.error('Input has 3 dimensions, maybe use imshow?')
    else:
        show = False
        if ax is None:
            fig = plt.figure()
            ax = fig.add_subplot(111)
            show = True

        if points is not None:
            ax.plot(points[:, 0], points[:, 1], 'c.')

        if vmin is None:
            vmin = np.min(matrix)

        if vmax is None:
            vmax = np.max(matrix)

        ax.imshow(matrix, interpolation='nearest', cmap=cmap, vmin=vmin, vmax=vmax)
        if grid:
            ax.grid('on')
        if not show_axis:
            ax.axis('off')
        if show:
            plt.show() 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def read_flo(filename):

    with open(filename, 'rb') as f:
        magic = np.fromfile(f, np.float32, count=1)
        if 202021.25 != magic:
            glog.error('Magic number incorrect. Invalid .flo file')
            flow = -1
        else:
            w = np.fromfile(f, np.int32, count=1)[0]
            h = np.fromfile(f, np.int32, count=1)[0]
            data = np.fromfile(f, np.float32, count=2 * w * h)
            flow = np.resize(data, (h, w, 2))

    return flow 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def _preprocess_data(encoder_client, hparams, data_dir):
    """Reads the data from the files, encodes it and parses the labels

    Args:
        encoder_client: an EncoderClient
        hparams: a tf.contrib.training.HParams object containing the model
            and training hyperparameters
        data_dir: The directory where the inten data has been downloaded

    Returns:
        categories, encodings, labels

    """
    if hparams.data_regime == "full":
        train_file = "train"
    elif hparams.data_regime == "10":
        train_file = "train_10"
    elif hparams.data_regime == "30":
        train_file = "train_30"
    else:
        glog.error(f"Invalid data regime: {hparams.data_regime}")
    train_data = os.path.join(
        data_dir, hparams.task, f"{train_file}.csv")
    test_data = os.path.join(data_dir, hparams.task, "test.csv")
    categories_file = os.path.join(data_dir, hparams.task, "categories.json")

    with tf.gfile.Open(categories_file, "r") as categories_file:
        categories = json.load(categories_file)

    labels = {}
    encodings = {}

    with tf.gfile.Open(train_data, "r") as data_file:
        data = np.array(list(csv.reader(data_file))[1:])
        labels[_TRAIN] = data[:, 1]
        encodings[_TRAIN] = encoder_client.encode_sentences(data[:, 0])

    with tf.gfile.Open(test_data, "r") as data_file:
        data = np.array(list(csv.reader(data_file))[1:])
        labels[_TEST] = data[:, 1]
        encodings[_TEST] = encoder_client.encode_sentences(data[:, 0])

    # convert labels to integers
    labels = {
        k: np.array(
            [categories.index(x) for x in v]) for k, v in labels.items()
    }

    return categories, encodings, labels 

# 需要導入模塊: import glog [as 別名]
# 或者: from glog import error [as 別名]
def calibrate_camera(self, vis_every=-1):
        if not exists(join(self.path_to_dataset, 'calib')):
            os.mkdir(join(self.path_to_dataset, 'calib'))

        calib_file = join(self.path_to_dataset, 'metadata', 'calib.p')
        if exists(calib_file):
            glog.info('Loading coarse detections from: {0}'.format(calib_file))
            with open(calib_file, 'rb') as f:
                self.calib = pickle.load(f)

        else:

            if not self.file_lists_match(listdir(join(self.path_to_dataset, 'calib'))):

                # The first frame is estimated by manual clicking
                manual_calib = join(self.path_to_dataset, 'calib', '{0}.npy'.format(self.frame_basenames[0]))
                if exists(manual_calib):
                    calib_npy = np.load(manual_calib).item()
                    A, R, T = calib_npy['A'], calib_npy['R'], calib_npy['T']
                else:
                    img = self.get_frame(0)
                    coarse_mask = self.get_mask_from_detectron(0)
                    A, R, T = calibration.calibrate_by_click(img, coarse_mask)

                if A is None:
                    glog.error('Manual calibration failed!')
                else:
                    np.save(join(self.path_to_dataset, 'calib', '{0}'.format(self.frame_basenames[0])),
                            {'A': A, 'R': R, 'T': T})
                    for i in tqdm(range(1, self.n_frames)):
                        # glog.info('Calibrating frame {0} ({1}/{2})'.format(self.frame_basenames[i], i, self.n_frames))
                        img = self.get_frame(i)
                        coarse_mask = self.get_mask_from_detectron(i)

                        if i % vis_every == 0:
                            vis = True
                        else:
                            vis = False
                        A, R, T, __ = calibration.calibrate_from_initialization(img, coarse_mask, A, R, T, vis)

                        np.save(join(self.path_to_dataset, 'calib', '{0}'.format(self.frame_basenames[i])),
                                {'A': A, 'R': R, 'T': T})

            for i, basename in enumerate(tqdm(self.frame_basenames)):
                calib_npy = np.load(join(self.path_to_dataset, 'calib', '{0}.npy'.format(basename))).item()
                A, R, T = calib_npy['A'], calib_npy['R'], calib_npy['T']
                self.calib[basename] = {'A': A, 'R': R, 'T': T}

            with open(calib_file, 'wb') as f:
                pickle.dump(self.calib, f)

    # ------------------------------------------------------------------------------------------------------------------