Error while use batch_face_locations and how to get pixel of face location

[blinkbink]

• face_recognition version: 1.2.3
• Python version: 3.6.8
• Operating System: ubuntu 18.04

i'm try to use batch_face_locations, this my code :

selfieimage = face_recognition.load_image_file("path")
face_locations2 =face_recognition.batch_face_locations(selfieimage,number_of_times_to_upsample=0,batch_size=128)
       

but got this error :

_call__(): incompatible function arguments. The following argument types are supported:
    1. (self: dlib.cnn_face_detection_model_v1, imgs: list, upsample_num_times: int=0, batch_size: int=128) -> std::vector<std::vector<dlib::mmod_rect, std::allocator<dlib::mmod_rect> >, std::allocator<std::vector<dlib::mmod_rect, std::allocator<dlib::mmod_rect> > > >
    2. (self: dlib.cnn_face_detection_model_v1, img: array, upsample_num_times: int=0) -> std::vector<dlib::mmod_rect, std::allocator<dlib::mmod_rect> >

Invoked with: <dlib.cnn_face_detection_model_v1 object at 0x7f4c901706f8>, array([[[255, 255, 218],
        [255, 255, 218],
        [255, 255, 218],
        ...,
        [255, 255, 255],
        [255, 255, 255],
        [255, 255, 255]],

       [[255, 255, 218],
        [255, 255, 218],
        [255, 255, 218],
        ...,
        [255, 255, 255],
        [255, 255, 255],
        [255, 255, 255]],

       [[255, 255, 218],
        [255, 255, 218],
        [255, 255, 218],
        ...,
        [255, 255, 255],
        [255, 255, 255],
        [255, 255, 255]],

       ...,

       [[230, 148, 120],
        [230, 148, 120],
        [230, 148, 120],
        ...,
        [255, 191, 195],
        [255, 191, 195],
        [255, 191, 195]],

       [[230, 148, 120],
        [230, 148, 120],
        [230, 148, 120],
        ...,
        [255, 191, 195],
        [255, 191, 195],
        [255, 191, 195]],

       [[230, 148, 120],
        [230, 148, 120],
        [230, 148, 120],
        ...,
        [255, 191, 195],
        [255, 191, 195],
        [255, 191, 195]]], dtype=uint8), 1; kwargs: batch_size=128

Did you forget to `#include <pybind11/stl.h>`? Or <pybind11/complex.h>,
<pybind11/functional.h>, <pybind11/chrono.h>, etc. Some automatic
conversions are optional and require extra headers to be included
when compiling your pybind11 module

why this happen ?

and how to find pixel of face cause i want to compare higher pixel if more than one face is detected in photo, what i try is calculate the top, right, bottom, left but is wrong:

face_locations1 = face_recognition.face_locations(selfieimage, number_of_times_to_upsample=2, model="cnn")
compare_encode1 = face_recognition.face_encodings(selfieimage, face_locations1, num_jitters=6)

            for (top, right, bottom, left), face_encoding in zip(face_locations1, compare_encode1):
                i = 0
              print(face_encoding)
                res = [compare_encode1[i]]
                selfielowest.append(compare_encode1[i])
                i = i + 1