I’m beginning to explore face recognition but even my simple “hello world” is blowing up on my face.

Here’s the code:

import face_recognition
from PIL import Image
import numpy as np
import base64
from io import BytesIO

def test_face_recognition(image_path):
    # Open the image and ensure it's in RGB format
    img = Image.open(image_path).convert('RGB')

    # Convert image to numpy array
    img_np = np.array(img)

    # Check face detection
    face_locations = face_recognition.face_locations(img_np)
    print(f"Faces detected: {len(face_locations)}")

    if len(face_locations) > 0:
        face_encodings = face_recognition.face_encodings(img_np, known_face_locations=face_locations)
        print(f"Encodings found: {len(face_encodings)}")
    else:
        print("No faces detected.")

# Replace with the path to a local image file
test_face_recognition("test_image.jpg")

The test_image.jpg can be any JPEG file with a face on it.

When run, the code above explodes with the following error message:

Traceback (most recent call last):
  File "C:UsersUsersourcereposballot-boxflasktest_face_recognition.py", line 25, in <module>
    test_face_recognition("test_image.jpg")
  File "C:UsersUsersourcereposballot-boxflasktest_face_recognition.py", line 15, in test_face_recognition
    face_locations = face_recognition.face_locations(img_np)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:UsersUsersourcereposballot-boxflaskvenvLibsite-packagesface_recognitionapi.py", line 121, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, model)]
                                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:UsersUsersourcereposballot-boxflaskvenvLibsite-packagesface_recognitionapi.py", line 105, in _raw_face_locations
    return face_detector(img, number_of_times_to_upsample)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Unsupported image type, must be 8bit gray or RGB image.

According to the error message, the image is in an invalid format but, before passing the face recognition function, I do convert to the appropriated format: img = Image.open(image_path).convert('RGB')

Edited:

I changed from img_np to img to no avail. Now it explodes with the following error:

Traceback (most recent call last):
  File "C:UsersPauloSantossourcereposballot-boxflasktest_face.py", line 25, in <module>
    test_face_recognition("test_image.jpg")
  File "C:UsersPauloSantossourcereposballot-boxflasktest_face.py", line 15, in test_face_recognition
    face_locations = face_recognition.face_locations(img)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:UsersPauloSantossourcereposballot-boxflaskvenvLibsite-packagesface_recognitionapi.py", line 121, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, model)]
                                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:UsersPauloSantossourcereposballot-boxflaskvenvLibsite-packagesface_recognitionapi.py", line 105, in _raw_face_locations
    return face_detector(img, number_of_times_to_upsample)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: __call__(): incompatible function arguments. The following argument types are supported:
    1. (self: _dlib_pybind11.fhog_object_detector, image: numpy.ndarray, upsample_num_times: int = 0) -> _dlib_pybind11.rectangles

Invoked with: <_dlib_pybind11.fhog_object_detector object at 0x000001A8DB8E0370>, <PIL.Image.Image image mode=RGB size=1280x720 at 0x1A8FBD47110>, 1

Solved

The problem is the numpy version 2.0. According to this answer the problem occurs due to a breaking change on numpy. Reverting to numpy 1.26.4 solved the problem.