Python numpy.ndarray() Examples

def xyxy2xywh(self, bbox):
        """Convert ``xyxy`` style bounding boxes to ``xywh`` style for COCO
        evaluation.

        Args:
            bbox (numpy.ndarray): The bounding boxes, shape (4, ), in
                ``xyxy`` order.

        Returns:
            list[float]: The converted bounding boxes, in ``xywh`` order.
        """

        _bbox = bbox.tolist()
        return [
            _bbox[0],
            _bbox[1],
            _bbox[2] - _bbox[0],
            _bbox[3] - _bbox[1],
        ] 

def get_cls_results(det_results, annotations, class_id):
    """Get det results and gt information of a certain class.

    Args:
        det_results (list[list]): Same as `eval_map()`.
        annotations (list[dict]): Same as `eval_map()`.
        class_id (int): ID of a specific class.

    Returns:
        tuple[list[np.ndarray]]: detected bboxes, gt bboxes, ignored gt bboxes
    """
    cls_dets = [img_res[class_id] for img_res in det_results]
    cls_gts = []
    cls_gts_ignore = []
    for ann in annotations:
        gt_inds = ann['labels'] == class_id
        cls_gts.append(ann['bboxes'][gt_inds, :])

        if ann.get('labels_ignore', None) is not None:
            ignore_inds = ann['labels_ignore'] == class_id
            cls_gts_ignore.append(ann['bboxes_ignore'][ignore_inds, :])
        else:
            cls_gts_ignore.append(np.empty((0, 4), dtype=np.float32))

    return cls_dets, cls_gts, cls_gts_ignore 

def __init__(self, masks, height, width):
        self.height = height
        self.width = width
        if len(masks) == 0:
            self.masks = np.empty((0, self.height, self.width), dtype=np.uint8)
        else:
            assert isinstance(masks, (list, np.ndarray))
            if isinstance(masks, list):
                assert isinstance(masks[0], np.ndarray)
                assert masks[0].ndim == 2  # (H, W)
            else:
                assert masks.ndim == 3  # (N, H, W)

            self.masks = np.stack(masks).reshape(-1, height, width)
            assert self.masks.shape[1] == self.height
            assert self.masks.shape[2] == self.width 

def _serialize_data(self, data):

        # Default to raw bytes
        type_ = _BYTES

        if isinstance(data, np.ndarray):
        # When the data is a numpy array, use the more compact native
        # numpy format.
            buf = io.BytesIO()
            np.save(buf, data)
            data = buf.getvalue()
            type_ = _NUMPY

        elif not isinstance(data, (bytearray, bytes)):
        # Everything else except byte data is serialized in pickle format.
            data = pickle.dumps(data)
            type_ = _PICKLE

        if self.compress:
        # Optional compression
            data = lz4.frame.compress(data)

        return type_, data 

def __call__(self, video):
    """
    Args:
        video (numpy.ndarray): Video to be scaled.
    Returns:
        numpy.ndarray: Rescaled video.
    """
    if isinstance(self.size, int):
      w, h = video.shape[-2], video.shape[-3]
      if (w <= h and w == self.size) or (h <= w and h == self.size):
        return video
      if w < h:
        ow = self.size
        oh = int(self.size*h/w)
        return resize(video, (ow, oh), self.interpolation)
      else:
        oh = self.size
        ow = int(self.size*w/h)
        return resize(video, (ow, oh), self.interpolation)
    else:
      return resize(video, self.size, self.interpolation) 

def __call__(self, video):
    """
    Args:
        video (np.ndarray): Video to be cropped.
    Returns:
        np.ndarray: Cropped video.
    """
    if self.padding > 0:
      pad = Pad(self.padding, 0)
      video = pad(video)

    w, h = video.shape[-2], video.shape[-3]
    th, tw = self.size
    if w == tw and h == th:
      return video

    x1 = random.randint(0, w-tw)
    y1 = random.randint(0, h-th)
    return video[..., y1:y1+th, x1:x1+tw, :] 

def read_common_mat(fd):
    """ 
        Read common matrix(for class Matrix in kaldi setup)
        see matrix/kaldi-matrix.cc::
            void Matrix<Real>::Read(std::istream & is, bool binary, bool add)
        Return a numpy ndarray object
    """
    mat_type = read_token(fd)
    print_info(f'\tType of the common matrix: {mat_type}')
    if mat_type not in ["FM", "DM"]:
        raise RuntimeError(f"Unknown matrix type in kaldi: {mat_type}")
    float_size = 4 if mat_type == 'FM' else 8
    float_type = np.float32 if mat_type == 'FM' else np.float64
    num_rows = read_int32(fd)
    num_cols = read_int32(fd)
    print_info(f'\tSize of the common matrix: {num_rows} x {num_cols}')
    mat_data = fd.read(float_size * num_cols * num_rows)
    mat = np.fromstring(mat_data, dtype=float_type)
    return mat.reshape(num_rows, num_cols) 

def read_compress_mat(fd):
    """ 
        Reference to function Read in CompressMatrix
        Return a numpy ndarray object
    """
    cps_type = read_token(fd)
    print_info(f'\tFollowing matrix type: {cps_type}')
    head = struct.unpack('ffii', fd.read(16))
    print_info(f'\tCompress matrix header: {head}')
    # 8: sizeof PerColHeader
    # head: {min_value, range, num_rows, num_cols}
    num_rows, num_cols = head[2], head[3]
    if cps_type == 'CM':
        remain_size = num_cols * (8 + num_rows)
    elif cps_type == 'CM2':
        remain_size = 2 * num_rows * num_cols
    elif cps_type == 'CM3':
        remain_size = num_rows * num_cols
    else:
        throw_on_error(False, f'Unknown matrix compressing type: {cps_type}')
    # now uncompress it
    compress_data = fd.read(remain_size)
    mat = uncompress(compress_data, cps_type, head)
    return mat 

def serialize_ndarray_b64(o):
    """
    Serializes a :obj:`numpy.ndarray` in a format where the datatype and shape are
    human-readable, but the array data itself is binary64 encoded.

    Args:
        o (:obj:`numpy.ndarray`): :obj:`ndarray` to be serialized.

    Returns:
        A dictionary that can be passed to :obj:`json.dumps`.
    """
    if o.flags['C_CONTIGUOUS']:
        o_data = o.data
    else:
        o_data = np.ascontiguousarray(o).data
    data_b64 = base64.b64encode(o_data)
    return dict(
        _type='np.ndarray',
        data=data_b64.decode('utf-8'),
        dtype=o.dtype,
        shape=o.shape) 

def serialize_ndarray_npy(o):
    """
    Serializes a :obj:`numpy.ndarray` using numpy's built-in :obj:`save` function.
    This produces totally unreadable (and very un-JSON-like) results (in "npy"
    format), but it's basically guaranteed to work in 100% of cases.

    Args:
        o (:obj:`numpy.ndarray`): :obj:`ndarray` to be serialized.

    Returns:
        A dictionary that can be passed to :obj:`json.dumps`.
    """
    with io.BytesIO() as f:
        np.save(f, o)
        f.seek(0)
        serialized = json.dumps(f.read().decode('latin-1'))
    return dict(
        _type='np.ndarray',
        npy=serialized) 

def deserialize_ndarray_npy(d):
    """
    Deserializes a JSONified :obj:`numpy.ndarray` that was created using numpy's
    :obj:`save` function.

    Args:
        d (:obj:`dict`): A dictionary representation of an :obj:`ndarray` object, created
            using :obj:`numpy.save`.

    Returns:
        An :obj:`ndarray` object.
    """
    with io.BytesIO() as f:
        f.write(json.loads(d['npy']).encode('latin-1'))
        f.seek(0)
        return np.load(f) 

def plot_iou_recall(recalls, iou_thrs):
    """Plot IoU-Recalls curve.

    Args:
        recalls(ndarray or list): shape (k,)
        iou_thrs(ndarray or list): same shape as `recalls`
    """
    if isinstance(iou_thrs, np.ndarray):
        _iou_thrs = iou_thrs.tolist()
    else:
        _iou_thrs = iou_thrs
    if isinstance(recalls, np.ndarray):
        _recalls = recalls.tolist()
    else:
        _recalls = recalls

    import matplotlib.pyplot as plt
    f = plt.figure()
    plt.plot(_iou_thrs + [1.0], _recalls + [0.])
    plt.xlabel('IoU')
    plt.ylabel('Recall')
    plt.axis([iou_thrs.min(), 1, 0, 1])
    f.show() 

def tensor2imgs(tensor, mean=(0, 0, 0), std=(1, 1, 1), to_rgb=True):
    """Convert tensor to images.

    Args:
        tensor (torch.Tensor): Tensor that contains multiple images
        mean (tuple[float], optional): Mean of images. Defaults to (0, 0, 0).
        std (tuple[float], optional): Standard deviation of images.
            Defaults to (1, 1, 1).
        to_rgb (bool, optional): Whether convert the images to RGB format.
            Defaults to True.

    Returns:
        list[np.ndarray]: A list that contains multiple images.
    """
    num_imgs = tensor.size(0)
    mean = np.array(mean, dtype=np.float32)
    std = np.array(std, dtype=np.float32)
    imgs = []
    for img_id in range(num_imgs):
        img = tensor[img_id, ...].cpu().numpy().transpose(1, 2, 0)
        img = mmcv.imdenormalize(
            img, mean, std, to_bgr=to_rgb).astype(np.uint8)
        imgs.append(np.ascontiguousarray(img))
    return imgs 

def crop_and_resize(self,
                        bboxes,
                        out_shape,
                        inds,
                        device,
                        interpolation='bilinear'):
        """Crop and resize masks by the given bboxes.

        This function is mainly used in mask targets computation.
        It firstly align mask to bboxes by assigned_inds, then crop mask by the
        assigned bbox and resize to the size of (mask_h, mask_w)

        Args:
            bboxes (Tensor): Bboxes in format [x1, y1, x2, y2], shape (N, 4)
            out_shape (tuple[int]): Target (h, w) of resized mask
            inds (ndarray): Indexes to assign masks to each bbox
            device (str): Device of bboxes
            interpolation (str): See `mmcv.imresize`

        Return:
            BaseInstanceMasks: the cropped and resized masks.
        """
        pass 

def crop(self, bbox):
        """See :func:`BaseInstanceMasks.crop`."""
        assert isinstance(bbox, np.ndarray)
        assert bbox.ndim == 1

        # clip the boundary
        bbox = bbox.copy()
        bbox[0::2] = np.clip(bbox[0::2], 0, self.width)
        bbox[1::2] = np.clip(bbox[1::2], 0, self.height)
        x1, y1, x2, y2 = bbox
        w = np.maximum(x2 - x1, 1)
        h = np.maximum(y2 - y1, 1)

        if len(self.masks) == 0:
            cropped_masks = np.empty((0, h, w), dtype=np.uint8)
        else:
            cropped_masks = self.masks[:, y1:y1 + h, x1:x1 + w]
        return BitmapMasks(cropped_masks, h, w) 

def __getitem__(self, index):
        """Index the polygon masks.

        Args:
            index (ndarray | List): The indices.

        Returns:
            :obj:`PolygonMasks`: The indexed polygon masks.
        """
        if isinstance(index, np.ndarray):
            index = index.tolist()
        if isinstance(index, list):
            masks = [self.masks[i] for i in index]
        else:
            try:
                masks = self.masks[index]
            except Exception:
                raise ValueError(
                    f'Unsupported input of type {type(index)} for indexing!')
        if isinstance(masks[0], np.ndarray):
            masks = [masks]  # ensure a list of three levels
        return PolygonMasks(masks, self.height, self.width) 

def predict(limit):
    _limit = limit if limit > 0 else 5

    td = TrainingData(LABEL_FILE, img_root=IMAGES_ROOT, mean_image_file=MEAN_IMAGE_FILE, image_property=IMAGE_PROP)
    label_def = LabelingMachine.read_label_def(LABEL_DEF_FILE)
    model = alex.Alex(len(label_def))
    serializers.load_npz(MODEL_FILE, model)

    i = 0
    for arr, im in td.generate():
        x = np.ndarray((1,) + arr.shape, arr.dtype)
        x[0] = arr
        x = chainer.Variable(np.asarray(x), volatile="on")
        y = model.predict(x)
        p = np.argmax(y.data)
        print("predict {0}, actual {1}".format(label_def[p], label_def[im.label]))
        im.image.show()
        i += 1
        if i >= _limit:
            break 

def extract_mfcc(y, sr, size=3):
    """
    extract MFCC feature
    :param y: np.ndarray [shape=(n,)], real-valued the input signal (audio time series)
    :param sr: sample rate of 'y'
    :param size: the length (seconds) of random crop from original audio, default as 3 seconds
    :return: MFCC feature
    """
    # normalization
    y = y.astype(np.float32)
    normalization_factor = 1 / np.max(np.abs(y))
    y = y * normalization_factor

    # random crop
    start = random.randint(0, len(y) - size * sr)
    y = y[start: start + size * sr]

    # extract log mel spectrogram #####
    melspectrogram = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=2048, hop_length=1024)
    mfcc = librosa.feature.mfcc(S=librosa.power_to_db(melspectrogram), n_mfcc=20)
    mfcc_delta = librosa.feature.delta(mfcc)
    mfcc_delta_delta = librosa.feature.delta(mfcc_delta)
    mfcc_comb = np.concatenate([mfcc, mfcc_delta, mfcc_delta_delta], axis=0)

    return mfcc_comb 

def extract_sample(img, image_mean=None, resize=-1):
    """Extract image content from image string or from file
    TAKE:
    input - either file content as string or numpy array
    image_mean - numpy array of image mean or a values of size (1,3)
    resize - to resize image, set resize > 0; otherwise, don't resize
    """
    try:
        # if input is a file name, then read image; otherwise decode_imgstr
        if type(img) is np.ndarray:
            img_data = img
        else:
            img_data = decode_imgstr(img)
        if type(resize) in [tuple, list]:
            # resize in two dimensions
            img_data = scipy.misc.imresize(img_data, (resize[0], resize[1]))
        elif resize > 0:
            img_data = scipy.misc.imresize(img_data, (resize, resize))
        img_data = img_data.astype(np.float32, copy=False)
        img_data = img_data[:, :, ::-1]
        # change channel for caffe:
        img_data = img_data.transpose(2, 0, 1)  # to CxHxW
        # substract_mean
        if image_mean is not None:
            img_data = substract_mean(img_data, image_mean)
        return img_data
    except:
        print sys.exc_info()[0], sys.exc_info()[1]
        return 

def _convert(self, vals):
        res = {}
        for k, v in vals.items():
            if isinstance(v, (np.int, np.int8, np.int16, np.int32, np.int64)):
                v = int(v)
            elif isinstance(v, (np.float, np.float16, np.float32, np.float64)):
                v = float(v)
            elif isinstance(v, Labels):
                v = list(v)
            elif isinstance(v, np.ndarray):
                v = v.tolist()
            elif isinstance(v, dict):
                v = self._convert(v)
            res[k] = v
        return res 

def fix_by_image_dimensions(self, height, width=None):
        if isinstance(height, (tuple, list)):
            assert width is None
            height, width = height[0], height[1]
        elif isinstance(height, (np.ndarray, np.generic)):
            assert width is None
            height, width = height.shape[0], height.shape[1]
        else:
            assert width is not None
            assert isinstance(height, int)
            assert isinstance(width, int)

        self.x1 = int(np.clip(self.x1, 0, width-1))
        self.x2 = int(np.clip(self.x2, 0, width-1))
        self.y1 = int(np.clip(self.y1, 0, height-1))
        self.y2 = int(np.clip(self.y2, 0, height-1))

        if self.x1 > self.x2:
            self.x1, self.x2 = self.x2, self.x1
        if self.y1 > self.y2:
            self.y1, self.y2 = self.y2, self.y1

        if self.x1 == self.x2:
            if self.x1 > 0:
                self.x1 = self.x1 - 1
            else:
                self.x2 = self.x2 + 1

        if self.y1 == self.y2:
            if self.y1 > 0:
                self.y1 = self.y1 - 1
            else:
                self.y2 = self.y2 + 1

        #self.width = self.x2 - self.x1
        #self.height = self.y2 - self.y1 

def time_label(intvl, return_val=True):
    """Create time interval label for aospy data I/O."""
    # Monthly labels are 2 digit integers: '01' for jan, '02' for feb, etc.
    if type(intvl) in [list, tuple, np.ndarray] and len(intvl) == 1:
        label = '{:02}'.format(intvl[0])
        value = np.array(intvl)
    elif type(intvl) == int and intvl in range(1, 13):
        label = '{:02}'.format(intvl)
        value = np.array([intvl])
    # Seasonal and annual time labels are short strings.
    else:
        labels = {'jfm': (1, 2, 3),
                  'fma': (2, 3, 4),
                  'mam': (3, 4, 5),
                  'amj': (4, 5, 6),
                  'mjj': (5, 6, 7),
                  'jja': (6,  7,  8),
                  'jas': (7, 8, 9),
                  'aso': (8, 9, 10),
                  'son': (9, 10, 11),
                  'ond': (10, 11, 12),
                  'ndj': (11, 12, 1),
                  'djf': (1, 2, 12),
                  'jjas': (6, 7, 8, 9),
                  'djfm': (12, 1, 2, 3),
                  'ann': range(1, 13)}
        for lbl, vals in labels.items():
            if intvl == lbl or set(intvl) == set(vals):
                label = lbl
                value = np.array(vals)
                break
    if return_val:
        return label, value
    else:
        return label 

def bbox_overlaps(boxes, query_boxes):
    """
    Parameters
    ----------
    boxes: (N, 4) ndarray or tensor or variable
    query_boxes: (K, 4) ndarray or tensor or variable
    Returns
    -------
    overlaps: (N, K) overlap between boxes and query_boxes
    """
    if isinstance(boxes, np.ndarray):
        boxes = torch.from_numpy(boxes)
        query_boxes = torch.from_numpy(query_boxes)
        out_fn = lambda x: x.numpy() # If input is ndarray, turn the overlaps back to ndarray when return
    else:
        out_fn = lambda x: x

    box_areas = (boxes[:, 2] - boxes[:, 0] + 1) * \
            (boxes[:, 3] - boxes[:, 1] + 1)
    query_areas = (query_boxes[:, 2] - query_boxes[:, 0] + 1) * \
            (query_boxes[:, 3] - query_boxes[:, 1] + 1)

    iw = (torch.min(boxes[:, 2:3], query_boxes[:, 2:3].t()) - torch.max(boxes[:, 0:1], query_boxes[:, 0:1].t()) + 1).clamp(min=0)
    ih = (torch.min(boxes[:, 3:4], query_boxes[:, 3:4].t()) - torch.max(boxes[:, 1:2], query_boxes[:, 1:2].t()) + 1).clamp(min=0)
    ua = box_areas.view(-1, 1) + query_areas.view(1, -1) - iw * ih
    overlaps = iw * ih / ua
    return out_fn(overlaps) 

def _merge_a_into_b(a, b):
  """Merge config dictionary a into config dictionary b, clobbering the
  options in b whenever they are also specified in a.
  """
  if type(a) is not edict:
    return

  for k, v in a.items():
    # a must specify keys that are in b
    if k not in b:
      raise KeyError('{} is not a valid config key'.format(k))

    # the types must match, too
    old_type = type(b[k])
    if old_type is not type(v):
      if isinstance(b[k], np.ndarray):
        v = np.array(v, dtype=b[k].dtype)
      else:
        raise ValueError(('Type mismatch ({} vs. {}) '
                          'for config key: {}').format(type(b[k]),
                                                       type(v), k))

    # recursively merge dicts
    if type(v) is edict:
      try:
        _merge_a_into_b(a[k], b[k])
      except:
        print(('Error under config key: {}'.format(k)))
        raise
    else:
      b[k] = v 

def __call__(self, arr):
    if isinstance(arr, np.ndarray):
      video = torch.from_numpy(np.rollaxis(arr, axis=-1, start=-3))

      if self.scale:
        return video.float().div(255)
      else:
        return video.float()
    else:
      raise NotImplementedError 

def __call__(self, video):
    """
    Args:
        video (np.ndarray): Video to be padded.
    Returns:
        np.ndarray: Padded video.
    """
    pad_width = ((0, 0), (self.padding, self.padding), (self.padding, self.padding), (0, 0))
    return np.pad(video, pad_width=pad_width, mode='constant', constant_values=self.fill) 

def to_numpy(array):
  """
  :param array: Variable, GPU tensor, or CPU tensor
  :return: numpy
  """
  if isinstance(array, np.ndarray):
    return array
  if isinstance(array, torch.autograd.Variable):
    array = array.data
  if array.is_cuda:
    array = array.cpu()

  return array.numpy() 

def return_predict(self, im):
    assert isinstance(im, np.ndarray), \
				'Image is not a np.ndarray'
    h, w, _ = im.shape
    im = self.framework.resize_input(im)
    this_inp = np.expand_dims(im, 0)
    feed_dict = {self.inp : this_inp}

    out = self.sess.run(self.out, feed_dict)[0]
    boxes = self.framework.findboxes(out)
    threshold = self.FLAGS.threshold
    boxesInfo = list()
    for box in boxes:
        tmpBox = self.framework.process_box(box, h, w, threshold)
        if tmpBox is None:
            continue
        boxesInfo.append({
            "label": tmpBox[4],
            "confidence": tmpBox[6],
            "topleft": {
                "x": tmpBox[0],
                "y": tmpBox[2]},
            "bottomright": {
                "x": tmpBox[1],
                "y": tmpBox[3]}
        })
    return boxesInfo 

def preprocess(self, im, allobj = None):
	"""
	Takes an image, return it as a numpy tensor that is readily
	to be fed into tfnet. If there is an accompanied annotation (allobj),
	meaning this preprocessing is serving the train process, then this
	image will be transformed with random noise to augment training data,
	using scale, translation, flipping and recolor. The accompanied
	parsed annotation (allobj) will also be modified accordingly.
	"""
	if type(im) is not np.ndarray:
		im = cv2.imread(im)

	if allobj is not None: # in training mode
		result = imcv2_affine_trans(im)
		im, dims, trans_param = result
		scale, offs, flip = trans_param
		for obj in allobj:
			_fix(obj, dims, scale, offs)
			if not flip: continue
			obj_1_ =  obj[1]
			obj[1] = dims[0] - obj[3]
			obj[3] = dims[0] - obj_1_
		im = imcv2_recolor(im)

	im = self.resize_input(im)
	if allobj is None: return im
	return im#, np.array(im) # for unit testing 

def _shape(tensor): # work for both tf.Tensor & np.ndarray
    if type(tensor) in [tf.Variable, tf.Tensor]: 
        return tensor.get_shape()
    else: return tensor.shape