Модуль dlib.cuda не найден, но dlib.DLIB_USE_CUDA=True. это нормально?

Question

[Валентин]

Захотел немного поиграть с распознаванием лиц. Использую для этого face_recognition, dlib и python3. Но у меня появились вопросы правильно ли я всё настроил для использования CUDA-ядер. Пока не запускал ничего кроме вот этого примера с гитхаба, подгрузив туда своё фото:

import face_recognition
import cv2
import numpy as np

# Get a reference to webcam #0 (the default one)
video_capture = cv2.VideoCapture(0)

# Load a sample picture and learn how to recognize it.
obama_image = face_recognition.load_image_file("my_photo.jpg")
obama_face_encoding = face_recognition.face_encodings(obama_image)[0]

# Load a second sample picture and learn how to recognize it.
biden_image = face_recognition.load_image_file("biden.jpg")
biden_face_encoding = face_recognition.face_encodings(biden_image)[0]

# Create arrays of known face encodings and their names
known_face_encodings = [
    obama_face_encoding,
    biden_face_encoding
]
known_face_names = [
    "Barack Obama",
    "Joe Biden"
]

# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True

while True:
    # Grab a single frame of video
    ret, frame = video_capture.read()

    # Resize frame of video to 1/4 size for faster face recognition processing
    small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)

    # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
    rgb_small_frame = small_frame[:, :, ::-1]

    # Only process every other frame of video to save time
    if process_this_frame:
        # Find all the faces and face encodings in the current frame of video
        face_locations = face_recognition.face_locations(rgb_small_frame)
        face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

        face_names = []
        for face_encoding in face_encodings:
            # See if the face is a match for the known face(s)
            matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
            name = "Unknown"

            # Or instead, use the known face with the smallest distance to the new face
            face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
            best_match_index = np.argmin(face_distances)
            if matches[best_match_index]:
                name = known_face_names[best_match_index]

            face_names.append(name)

    process_this_frame = not process_this_frame


    # Display the results
    for (top, right, bottom, left), name in zip(face_locations, face_names):
        # Scale back up face locations since the frame we detected in was scaled to 1/4 size
        top *= 4
        right *= 4
        bottom *= 4
        left *= 4

        # Draw a box around the face
        cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)

        # Draw a label with a name below the face
        cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
        font = cv2.FONT_HERSHEY_DUPLEX
        cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)

    # Display the resulting image
    cv2.imshow('Video', frame)

    # Hit 'q' on the keyboard to quit!
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()

Судя по всему dlib использует CUDA, так как исполнив в консоли питона команду dlib.DLIB_USE_CUDA я получаю True и при выполнении nvidia-smi я получаю вот такой вывод:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 446.14       Driver Version: 446.14       CUDA Version: 11.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name            TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 105... WDDM  | 00000000:01:00.0  On |                  N/A |
|  0%   41C    P0    N/A / 120W |    552MiB /  4096MiB |      1%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU                  PID   Type   Process name                  GPU Memory |
|                                                                  Usage      |
|=============================================================================|
|    0                 1068      C   ...Files\Python37\python.exe    N/A      |
|    0                 1096    C+G   Insufficient Permissions        N/A      |
|    0                 2160    C+G   ...w5n1h2txyewy\SearchUI.exe    N/A      |
|    0                 3680    C+G   ...y\ShellExperienceHost.exe    N/A      |
|    0                 5936    C+G   ...es.TextInput.InputApp.exe    N/A      |
|    0                 7968    C+G   C:\Windows\explorer.exe         N/A      |
|    0                 8540    C+G   ...ty\Common7\IDE\devenv.exe    N/A      |
|    0                 8904    C+G   ...lPanel\SystemSettings.exe    N/A      |
|    0                 9568    C+G   ...ekyb3d8bbwe\YourPhone.exe    N/A      |
|    0                13280    C+G   ...ub.ThreadedWaitDialog.exe    N/A      |
+-----------------------------------------------------------------------------+

При этом моя видеокарта не нагружается выше 1-2% при выполнении кода и когда я пытаюсь импортировать dlib.cuda, то получаю ошибку. Означает ли всё это что я установил что-то не так? Или всё нормально?