I did a python script that gets data from shared mem and convert it from bytes to floats.
The main problem is that it very slow.

This is how I init the shared memory:

  def _shared_mem_init(self):

        warnings.filterwarnings("ignore")
        path = "/tmp"

        # shared memory header
        key = ipc.ftok(path, 0x3110)
        self.shm = ipc.SharedMemory(key, 0, 0)
        self.shm.attach(0, 0)
        # shared memory X values
        key_x = ipc.ftok(path, 0x3111)
        self.shm_x = ipc.SharedMemory(key_x, 0, 0)
        self.shm_x.attach(0, 0)
        # shared memory Y values
        key_y = ipc.ftok(path, 0x3112)
        self.shm_y = ipc.SharedMemory(key_y, 0, 0)
        self.shm_y.attach(0, 0)
        # shared memory Z values
        key_z = ipc.ftok(path, 0x3113)
        self.shm_z = ipc.SharedMemory(key_z, 0, 0)
        self.shm_z.attach(0, 0)
        # shared memory R values
        key_r = ipc.ftok(path, 0x3114)
        self.shm_r = ipc.SharedMemory(key_r, 0, 0)
        self.shm_r.attach(0, 0)
        # shared memory G values
        key_g = ipc.ftok(path, 0x3115)
        self.shm_g = ipc.SharedMemory(key_g, 0, 0)
        self.shm_g.attach(0, 0)
        # shared memory B values
        key_b = ipc.ftok(path, 0x3116)
        self.shm_b = ipc.SharedMemory(key_b, 0, 0)
        self.shm_b.attach(0, 0)

        self.shm.write(byte_true, 0)
        print("shared Memory init")

it gets the xyzrgb from the shared memory.
and after I get the data I try to convert it from bytes to floats:

 def next_point_cloud(self):

        # read 4 bytes from header - Data Lines
        buf = self.shm.read(4, 5)
        data_lines = int.from_bytes(buf, "little")

        # read all data
        buff_x2 = self.shm_x.read(4 * data_lines, 0)
        buff_y2 = self.shm_y.read(4 * data_lines, 0)
        buff_z2 = self.shm_z.read(4 * data_lines, 0)
        buff_r2 = self.shm_r.read(data_lines, 0)
        buff_g2 = self.shm_g.read(data_lines, 0)
        buff_b2 = self.shm_b.read(data_lines, 0)

        # split all data
        buff_x_breakdown = [buff_x2[i:i + 4] for i in range(0, 4 * data_lines, 4)]
        buff_y_breakdown = [buff_y2[i:i + 4] for i in range(0, 4 * data_lines, 4)]
        buff_z_breakdown = [buff_z2[i:i + 4] for i in range(0, 4 * data_lines, 4)]
        buff_r_breakdown = [buff_r2[i] for i in range(0, data_lines, 1)]
        buff_g_breakdown = [buff_g2[i] for i in range(0, data_lines, 1)]
        buff_b_breakdown = [buff_b2[i] for i in range(0, data_lines, 1)]

        xyz = np.zeros((data_lines, 3))
        colors = np.zeros((data_lines, 3))

        for i in range(data_lines):
            xyz[i, 0] = struct.unpack('f', buff_x_breakdown[i])[0]
            xyz[i, 1] = struct.unpack('f', buff_y_breakdown[i])[0]
            xyz[i, 2] = struct.unpack('f', buff_z_breakdown[i])[0]

            colors[i, 0] = float(buff_r_breakdown[i]) / 255.0
            colors[i, 1] = float(buff_g_breakdown[i]) / 255.0
            colors[i, 2] = float(buff_b_breakdown[i]) / 255.0

        self.pcdA.points = o3d.utility.Vector3dVector(xyz)
        self.pcdA.colors = o3d.utility.Vector3dVector(colors)

So my question is: Is there a way in python to write a code that runs better then the for loop that I wrote?

>Solution :

You can use np.frombuffer to construct a Numpy array from a bytes object:

>>> buffer = b''.join(struct.pack('f', x) for x in [1.0, 2.0, 3.0])
>>> np.frombuffer(buffer, dtype=np.float32, count=3)
array([1., 2., 3.], dtype=float32)

So in your case this should be:

xyz = np.stack(
    [
        np.frombuffer(self.shm_x.read(4*data_lines, 0), dtype=np.float32, count=data_lines),
        np.frombuffer(self.shm_y.read(4*data_lines, 0), dtype=np.float32, count=data_lines),
        np.frombuffer(self.shm_z.read(4*data_lines, 0), dtype=np.float32, count=data_lines),
    ],
    axis=1,
)

and the same for colors:

colors = (1./255) * np.stack(
    [
        np.frombuffer(self.shm_r.read(data_lines, 0), dtype=np.byte, count=data_lines),
        np.frombuffer(self.shm_g.read(data_lines, 0), dtype=np.byte, count=data_lines),
        np.frombuffer(self.shm_b.read(data_lines, 0), dtype=np.byte, count=data_lines),
    ],
    axis=1,
)