Python numpy.fromstring() Examples

def image(self, captcha_str):
        """
        Generate a greyscale captcha image representing number string

        Parameters
        ----------
        captcha_str: str
            string a characters for captcha image

        Returns
        -------
        numpy.ndarray
            Generated greyscale image in np.ndarray float type with values normalized to [0, 1]
        """
        img = self.captcha.generate(captcha_str)
        img = np.fromstring(img.getvalue(), dtype='uint8')
        img = cv2.imdecode(img, cv2.IMREAD_GRAYSCALE)
        img = cv2.resize(img, (self.h, self.w))
        img = img.transpose(1, 0)
        img = np.multiply(img, 1 / 255.0)
        return img 

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_float_vec(fd, direct_access=False):
    """
        Read float vector(for class Vector in kaldi setup)
        see matrix/kaldi-vector.cc
    """
    if direct_access:
        expect_binary(fd)
    vec_type = read_token(fd)
    print_info(f'\tType of the common vector: {vec_type}')
    if vec_type not in ["FV", "DV"]:
        raise RuntimeError(f"Unknown matrix type in kaldi: {vec_type}")
    float_size = 4 if vec_type == 'FV' else 8
    float_type = np.float32 if vec_type == 'FV' else np.float64
    dim = read_int32(fd)
    print_info(f'\tDim of the common vector: {dim}')
    vec_data = fd.read(float_size * dim)
    return np.fromstring(vec_data, dtype=float_type) 

def deserialize_ndarray(d):
    """
    Deserializes a JSONified :obj:`numpy.ndarray`. Can handle arrays serialized
    using any of the methods in this module: :obj:`"npy"`, :obj:`"b64"`,
    :obj:`"readable"`.

    Args:
        d (`dict`): A dictionary representation of an :obj:`ndarray` object.

    Returns:
        An :obj:`ndarray` object.
    """
    if 'data' in d:
        x = np.fromstring(
            base64.b64decode(d['data']),
            dtype=d['dtype'])
        x.shape = d['shape']
        return x
    elif 'value' in d:
        return np.array(d['value'], dtype=d['dtype'])
    elif 'npy' in d:
        return deserialize_ndarray_npy(d)
    else:
        raise ValueError('Malformed np.ndarray encoding.') 

def fig2data(fig):
    """
    @brief Convert a Matplotlib figure to a 4D numpy array with RGBA channels and return it
    @param fig a matplotlib figure
    @return a numpy 3D array of RGBA values
    """
    # draw the renderer
    fig.canvas.draw ( )

    # Get the RGB buffer from the figure
    w,h = fig.canvas.get_width_height()
    buf = np.fromstring (fig.canvas.tostring_rgb(), dtype=np.uint8)
    buf.shape = (w, h, 3)

    # canvas.tostring_argb give pixmap in ARGB mode. Roll the ALPHA channel to have it in RGBA mode
    buf = np.roll (buf, 3, axis=2)
    return buf 

def load_word_vectors(url):
    '''
    Load the word embeddings from the url
    :param url: to the word vectors
    :return: dict of word and vector values
    '''
    word_vectors = {}
    # print("Loading the word embeddings....................")
    # print('abs path: ', os.path.abspath(url))
    with open(url, mode='r', encoding='utf8') as f:
        for line in f:
            line = line.split(" ", 1)
            key = line[0]
            word_vectors[key] = np.fromstring(line[1], dtype="float32", sep=" ")
    # print("\tMDBT: The vocabulary contains about {} word embeddings".format(len(word_vectors)))
    return normalise_word_vectors(word_vectors) 

def _read_values(self):
        nc_type = self.fp.read(4)
        n = self._unpack_int()

        typecode, size = TYPEMAP[nc_type]

        count = n*size
        values = self.fp.read(int(count))
        self.fp.read(-count % 4)  # read padding

        if typecode is not 'c':
            values = fromstring(values, dtype='>%s' % typecode)
            if values.shape == (1,): values = values[0]
        else:
            values = values.rstrip(asbytes('\x00'))
        return values 

def frames():
        with PiCamera() as camera:
            camera.rotation = int(str(os.environ['CAMERA_ROTATION']))
            stream = io.BytesIO()
            for _ in camera.capture_continuous(stream, 'jpeg',
                                               use_video_port=True):
                # return current frame
                stream.seek(0)
                _stream = stream.getvalue()
                data = np.fromstring(_stream, dtype=np.uint8)
                img = cv2.imdecode(data, 1)
                yield img

                # reset stream for next frame
                stream.seek(0)
                stream.truncate() 

def read(filename, limit=None):
    """
    Reads any file supported by pydub (ffmpeg) and returns the data contained
    within. If file reading fails due to input being a 24-bit wav file,
    wavio is used as a backup.

    Can be optionally limited to a certain amount of seconds from the start
    of the file by specifying the `limit` parameter. This is the amount of
    seconds from the start of the file.

    returns: (channels, samplerate)
    """
    # pydub does not support 24-bit wav files, use wavio when this occurs
    try:
        audiofile = AudioSegment.from_file(filename)

        if limit:
            audiofile = audiofile[:limit * 1000]

        data = np.fromstring(audiofile._data, np.int16)

        channels = []
        for chn in xrange(audiofile.channels):
            channels.append(data[chn::audiofile.channels])

        fs = audiofile.frame_rate
    except audioop.error:
        fs, _, audiofile = wavio.readwav(filename)

        if limit:
            audiofile = audiofile[:limit * 1000]

        audiofile = audiofile.T
        audiofile = audiofile.astype(np.int16)

        channels = []
        for chn in audiofile:
            channels.append(chn)

    return channels, audiofile.frame_rate, unique_hash(filename) 

def _wav2array(nchannels, sampwidth, data):
    """data must be the string containing the bytes from the wav file."""
    num_samples, remainder = divmod(len(data), sampwidth * nchannels)
    if remainder > 0:
        raise ValueError('The length of data is not a multiple of '
                         'sampwidth * num_channels.')
    if sampwidth > 4:
        raise ValueError("sampwidth must not be greater than 4.")

    if sampwidth == 3:
        a = _np.empty((num_samples, nchannels, 4), dtype=_np.uint8)
        raw_bytes = _np.fromstring(data, dtype=_np.uint8)
        a[:, :, :sampwidth] = raw_bytes.reshape(-1, nchannels, sampwidth)
        a[:, :, sampwidth:] = (a[:, :, sampwidth - 1:sampwidth] >> 7) * 255
        result = a.view('<i4').reshape(a.shape[:-1])
    else:
        # 8 bit samples are stored as unsigned ints; others as signed ints.
        dt_char = 'u' if sampwidth == 1 else 'i'
        a = _np.fromstring(data, dtype='<%s%d' % (dt_char, sampwidth))
        result = a.reshape(-1, nchannels)
    return result 

def _load_poses(self):
        """Load ground truth poses (T_w_cam0) from file."""
        pose_file = os.path.join(self.pose_path, self.sequence + '.txt')

        # Read and parse the poses
        poses = []
        try:
            with open(pose_file, 'r') as f:
                lines = f.readlines()
                if self.frames is not None:
                    lines = [lines[i] for i in self.frames]

                for line in lines:
                    T_w_cam0 = np.fromstring(line, dtype=float, sep=' ')
                    T_w_cam0 = T_w_cam0.reshape(3, 4)
                    T_w_cam0 = np.vstack((T_w_cam0, [0, 0, 0, 1]))
                    poses.append(T_w_cam0)

        except FileNotFoundError:
            print('Ground truth poses are not available for sequence ' +
                  self.sequence + '.')

        self.poses = poses 

def stream_readchunk(self):
        """reads some audio and re-launches itself"""
        try:
            self.data = np.fromstring(self.stream.read(self.chunk),dtype=np.int16)
            self.fftx, self.fft = getFFT(self.data,self.rate)

        except Exception as E:
            print(" -- exception! terminating...")
            print(E,"\n"*5)
            self.keepRecording=False
        if self.keepRecording:
            self.stream_thread_new()
        else:
            self.stream.close()
            self.p.terminate()
            print(" -- stream STOPPED")
        self.chunksRead+=1 

def get_data(self):
        idxs = np.arange(len(self.train_list))
        if self.shuffle:
            self.rng.shuffle(idxs)

        caches = {}
        for i, k in enumerate(idxs):
            path = self.train_list[k]
            label = self.lb_list[k]

            if i % self.preload == 0:
                try:
                    caches = ILSVRCTenth._read_tenth_batch(self.train_list[idxs[i:i+self.preload]])
                except Exception as e:
                    logging.warning('tenth local cache failed, err=%s' % str(e))

            content = caches.get(path, '')
            if not content:
                content = ILSVRCTenth._read_tenth(path)

            img = cv2.imdecode(np.fromstring(content, dtype=np.uint8), cv2.IMREAD_COLOR)
            yield [img, label] 

def from_xml(cls, xmlelement):
        """Loads a Sparse object from an existing file."""

        binaryfp = xmlelement.binaryfp
        nelem = int(xmlelement[0].attrib['nelem'])
        nrows = int(xmlelement.attrib['nrows'])
        ncols = int(xmlelement.attrib['ncols'])

        if binaryfp is None:
            rowindex = np.fromstring(xmlelement[0].text, sep=' ').astype(int)
            colindex = np.fromstring(xmlelement[1].text, sep=' ').astype(int)
            sparsedata = np.fromstring(xmlelement[2].text, sep=' ')
        else:
            rowindex = np.fromfile(binaryfp, dtype='<i4', count=nelem)
            colindex = np.fromfile(binaryfp, dtype='<i4', count=nelem)
            sparsedata = np.fromfile(binaryfp, dtype='<d', count=nelem)

        return cls((sparsedata, (rowindex, colindex)), [nrows, ncols]) 

def Vector(elem):
        nelem = int(elem.attrib['nelem'])
        if nelem == 0:
            arr = np.ndarray((0,))
        else:
            # sep=' ' seems to work even when separated by newlines, see
            # http://stackoverflow.com/q/31882167/974555
            if elem.binaryfp is not None:
                arr = np.fromfile(elem.binaryfp, dtype='<d', count=nelem)
            else:
                arr = np.fromstring(elem.text, sep=' ')
            if arr.size != nelem:
                raise RuntimeError(
                    'Expected {:s} elements in Vector, found {:d}'
                    ' elements!'.format(elem.attrib['nelem'],
                                        arr.size))
        return arr 

def ComplexVector(elem):
        nelem = int(elem.attrib['nelem'])
        if nelem == 0:
            arr = np.ndarray((0,), dtype=np.complex128)
        else:
            # sep=' ' seems to work even when separated by newlines, see
            # http://stackoverflow.com/q/31882167/974555
            if elem.binaryfp is not None:
                arr = np.fromfile(elem.binaryfp, dtype=np.complex128,
                                  count=nelem)
            else:
                arr = np.fromstring(elem.text, sep=' ', dtype=np.float64)
                arr.dtype = np.complex128
            if arr.size != nelem:
                raise RuntimeError(
                    'Expected {:s} elements in Vector, found {:d}'
                    ' elements!'.format(elem.attrib['nelem'],
                                        arr.size))
        return arr 

def ComplexMatrix(elem):
        # turn dims around: in ARTS, [10 x 1 x 1] means 10 pages, 1 row, 1 col
        dimnames = [dim for dim in dimension_names
                    if dim in elem.attrib.keys()][::-1]
        dims = [int(elem.attrib[dim]) for dim in dimnames]
        if np.prod(dims) == 0:
            flatarr = np.ndarray(dims, dtype=np.complex128)
        elif elem.binaryfp is not None:
            flatarr = np.fromfile(elem.binaryfp, dtype=np.complex128,
                                  count=np.prod(np.array(dims)).item())
            flatarr = flatarr.reshape(dims)
        else:
            flatarr = np.fromstring(elem.text, sep=' ', dtype=np.float64)
            flatarr.dtype = np.complex128
            flatarr = flatarr.reshape(dims)
        return flatarr 

def __init__(self, filename):
        self._filename = filename
        print 'Loading BCF file to memory ... '+filename
        file = open(filename, 'rb')
        size = numpy.fromstring(file.read(8), dtype=numpy.uint64)
        file_sizes = numpy.fromstring(file.read(8*size), dtype=numpy.uint64)
        self._offsets = numpy.append(numpy.uint64(0),
                                     numpy.add.accumulate(file_sizes))
        self._memory = file.read()
        file.close() 

def __init__(self, filename):
        self._filename = filename
        print 'Opening BCF file ... '+filename
        self._file = open(filename, 'rb')
        size = numpy.fromstring(self._file.read(8), dtype=numpy.uint64)
        file_sizes = numpy.fromstring(self._file.read(8*size),
                                      dtype=numpy.uint64)
        self._offsets = numpy.append(numpy.uint64(0),
                                     numpy.add.accumulate(file_sizes)) 

def new_frame(self, data, frame_count, time_info, status):
        data = np.fromstring(data, 'int16')
        with self.lock:
            self.frames.append(data)
            if self.stop:
                return None, pyaudio.paComplete
        return None, pyaudio.paContinue 

def new_frame(self, data, frame_count, time_info, status):
        data = np.fromstring(data, 'int16')
        with self.lock:
            self.frames.append(data)
            if self.stop:
                return None, pyaudio.paComplete
        return None, pyaudio.paContinue 

def create_lsun(tfrecord_dir, lmdb_dir, resolution=256, max_images=None):
    print('Loading LSUN dataset from "%s"' % lmdb_dir)
    import lmdb # pip install lmdb
    import cv2 # pip install opencv-python
    import io
    with lmdb.open(lmdb_dir, readonly=True).begin(write=False) as txn:
        total_images = txn.stat()['entries']
        if max_images is None:
            max_images = total_images
        with TFRecordExporter(tfrecord_dir, max_images) as tfr:
            for idx, (key, value) in enumerate(txn.cursor()):
                try:
                    try:
                        img = cv2.imdecode(np.fromstring(value, dtype=np.uint8), 1)
                        if img is None:
                            raise IOError('cv2.imdecode failed')
                        img = img[:, :, ::-1] # BGR => RGB
                    except IOError:
                        img = np.asarray(PIL.Image.open(io.BytesIO(value)))
                    crop = np.min(img.shape[:2])
                    img = img[(img.shape[0] - crop) // 2 : (img.shape[0] + crop) // 2, (img.shape[1] - crop) // 2 : (img.shape[1] + crop) // 2]
                    img = PIL.Image.fromarray(img, 'RGB')
                    img = img.resize((resolution, resolution), PIL.Image.ANTIALIAS)
                    img = np.asarray(img)
                    img = img.transpose(2, 0, 1) # HWC => CHW
                    tfr.add_image(img)
                except:
                    print(sys.exc_info()[1])
                if tfr.cur_images == max_images:
                    break
        
#---------------------------------------------------------------------------- 

def parse_tfrecord_np(record):
    ex = tf.train.Example()
    ex.ParseFromString(record)
    shape = ex.features.feature['shape'].int64_list.value
    data = ex.features.feature['data'].bytes_list.value[0]
    return np.fromstring(data, np.uint8).reshape(shape)

#----------------------------------------------------------------------------
# Dataset class that loads data from tfrecords files. 

def read_data(label_url, image_url):
    with gzip.open(download_data(label_url)) as flbl:
        magic, num = struct.unpack(">II", flbl.read(8))
        label = np.fromstring(flbl.read(), dtype=np.int8)
    with gzip.open(download_data(image_url), 'rb') as fimg:
        magic, num, rows, cols = struct.unpack(">IIII", fimg.read(16))
        image = np.fromstring(fimg.read(), dtype=np.uint8).reshape(len(label), rows, cols)
    return label, image 

def read_data(label, image):
    """
    download and read data into numpy
    """
    base_url = 'http://yann.lecun.com/exdb/mnist/'
    with gzip.open(download_file(base_url+label, os.path.join('data',label))) as flbl:
        magic, num = struct.unpack(">II", flbl.read(8))
        label = np.fromstring(flbl.read(), dtype=np.int8)
    with gzip.open(download_file(base_url+image, os.path.join('data',image)), 'rb') as fimg:
        magic, num, rows, cols = struct.unpack(">IIII", fimg.read(16))
        image = np.fromstring(fimg.read(), dtype=np.uint8).reshape(len(label), rows, cols)
    return (label, image) 

def main():
        parser = argparse.ArgumentParser()
        parser.add_argument("font_path", help="Path to ttf font file")
        parser.add_argument("output", help="Output filename including extension (e.g. 'sample.jpg')")
        parser.add_argument("--num", help="Up to 4 digit number [Default: random]")
        args = parser.parse_args()

        captcha = ImageCaptcha(fonts=[args.font_path])
        captcha_str = args.num if args.num else DigitCaptcha.get_rand(3, 4)
        img = captcha.generate(captcha_str)
        img = np.fromstring(img.getvalue(), dtype='uint8')
        img = cv2.imdecode(img, cv2.IMREAD_GRAYSCALE)
        cv2.imwrite(args.output, img)
        print("Captcha image with digits {} written to {}".format([int(c) for c in captcha_str], args.output)) 

def __init__(self, num_classes='21', batch_images='1', batch_rois='128', fg_fraction='0.25',
                 fg_overlap='0.5', box_stds='(0.1, 0.1, 0.2, 0.2)'):
        super(ProposalTargetProp, self).__init__(need_top_grad=False)
        self._num_classes = int(num_classes)
        self._batch_images = int(batch_images)
        self._batch_rois = int(batch_rois)
        self._fg_fraction = float(fg_fraction)
        self._fg_overlap = float(fg_overlap)
        self._box_stds = tuple(np.fromstring(box_stds[1:-1], dtype=float, sep=',')) 

def cutoff(input_wav, output_wav):
    '''
    input_wav --- input wav file path
    output_wav --- output wav file path
    '''

    # read input wave file and get parameters.
    with wave.open(input_wav, 'r') as fw:
        params = fw.getparams()
        # print(params)
        nchannels, sampwidth, framerate, nframes = params[:4]

        strData = fw.readframes(nframes)
        waveData = np.fromstring(strData, dtype=np.int16)

        max_v = np.max(abs(waveData))
        for i in range(waveData.shape[0]):
            if abs(waveData[i]) > 0.08 * max_v:
                break

        for j in range(waveData.shape[0] - 1, 0, -1):
            if abs(waveData[j]) > 0.08 * max_v:
                break

    # write new wav file
    with wave.open(output_wav, 'w') as fw:
        params = list(params)
        params[3] = nframes - i - (waveData.shape[0] - 1 - j)
        fw.setparams(params)
        fw.writeframes(strData[2 * i:2 * (j + 1)]) 

def plot_lfads(train_bxtxd, train_model_vals,
               train_ext_input_bxtxi=None, train_truth_bxtxd=None,
               valid_bxtxd=None, valid_model_vals=None,
               valid_ext_input_bxtxi=None, valid_truth_bxtxd=None,
               bidx=None, cf=1.0, output_dist='poisson'):

  # Plotting
  f = plt.figure(figsize=(18,20), tight_layout=True)
  plot_lfads_timeseries(train_bxtxd, train_model_vals,
                        train_ext_input_bxtxi,
                        truth_bxtxn=train_truth_bxtxd,
                        conversion_factor=cf, bidx=bidx,
                        output_dist=output_dist, col_title='Train')
  plot_lfads_timeseries(valid_bxtxd, valid_model_vals,
                        valid_ext_input_bxtxi,
                        truth_bxtxn=valid_truth_bxtxd,
                        conversion_factor=cf, bidx=bidx,
                        output_dist=output_dist,
                        subplot_cidx=1, col_title='Valid')

  # Convert from figure to an numpy array width x height x 3 (last for RGB)
  f.canvas.draw()
  data = np.fromstring(f.canvas.tostring_rgb(), dtype=np.uint8, sep='')
  data_wxhx3 = data.reshape(f.canvas.get_width_height()[::-1] + (3,))
  plt.close()

  return data_wxhx3 

def load(filename):
  with open(filename, 'r') as f:
    data = f.read()
  data = np.fromstring(data, dtype=np.uint8)
  unique, data = np.unique(data, return_inverse=True)
  return data, len(unique)