Face_recognition: ValueError: operands could not be broadcast together with shapes (1,0) (128,) on raspberry pi

[B-0F]

• face_recognition version:
• Python version: 3.5.5
• Operating System: rapbian

Description

Adding second image for recognition on raspberry. Getting:

Traceback (most recent call last):
  File "/home/pi/Рабочий стол/facerec_on_raspberry_pi.py", line 299, in <module>
    match = face_recognition.compare_faces([Roman_face_encoding], face_encoding)
  File "/usr/local/lib/python3.5/dist-packages/face_recognition/api.py", line 212, in compare_faces
    return list(face_distance(known_face_encodings, face_encoding_to_check) <= tolerance)
  File "/usr/local/lib/python3.5/dist-packages/face_recognition/api.py", line 72, in face_distance
    return np.linalg.norm(face_encodings - face_to_compare, axis=1)
ValueError: operands could not be broadcast together with shapes (1,0) (128,)  

What I Did

All samples with face_recognition

import face_recognition
import picamera
import numpy as np

camera = picamera.PiCamera()
camera.resolution = (320, 240)
output = np.empty((240, 320, 3), dtype=np.uint8)

# Load a sample picture and learn how to recognize it.
print("Loading known face image(s)")



Aleksey_image = face_recognition.load_image_file("photo1.jpg")
Aleksey_face_encoding= face_recognition.face_encodings(Aleksey_image)[0]



Roman_image = face_recognition.load_image_file("photo2.jpg")
Roman_face_encoding = face_recognition.face_encodings(Roman_image)

if len(Roman_face_encoding) > 0:
    Roman_face_encoding = Roman_face_encoding[0]

# Initialize some variables
face_locations = []
face_encodings = []

while True:
    if code == c_code:
        print("Capturing image.")
    # Grab a single frame of video from the RPi camera as a numpy array
    camera.capture(output, format="rgb")

    # Find all the faces and face encodings in the current frame of video
    face_locations = face_recognition.face_locations(output)
    print("Found {} faces in image.".format(len(face_locations)))
    face_encodings = face_recognition.face_encodings(output, face_locations)

    # Loop over each face found in the frame to see if it's someone we know.
    for face_encoding in face_encodings:
        # See if the face is a match for the known face(s)
        match = face_recognition.compare_faces([Roman_face_encoding], face_encoding)
        name = "<Unknown Person>"    

        if match[0]:
            name = "Roman"

        match = face_recognition.compare_faces([Aleksey_face_encoding], face_encoding)

        if match[0]:
            name = "Aleksey"

        print("I see someone named {}!".format(name))

Full file atached
facerec_on_raspberry_pi.py.txt

[ageitgey]

In this:

Roman_image = face_recognition.load_image_file("photo2.jpg")
Roman_face_encoding = face_recognition.face_encodings(Roman_image)

Are you sure any faces were detected in that photo? It looks like Roman_face_encoding array is possibly empty and causing the error later.

[DataActivator]

@ageitgey I am getting this error , tried to resolve by looking some solution mentioned on web but could'nt make it work :

Traceback (most recent call last):
File "face_rec_example.py", line 37, in
results = face_recognition.compare_faces(known_faces, face_encoding, TOLERANCE)
File "/home/shubham-sakha/venv/lib/python3.6/site-packages/face_recognition/api.py", line 226, in compare_faces
return list(face_distance(known_face_encodings, face_encoding_to_check) <= tolerance)
File "/home/shubham-sakha/venv/lib/python3.6/site-packages/face_recognition/api.py", line 75, in face_distance
return np.linalg.norm(face_encodings - face_to_compare, axis=1)

**ValueError: operands could not be broadcast together with shapes (9,) (128, code is
Code is followingg:-
`import face_recognition
import os
import cv2

KNOWN_FACES_DIR = "known_faces"
UNKNOWN_FACES_DIR = "unknown_faces"
TOLERANCE = 0.6
FRAME_THICKNESS = 3
FONT_THICKNESS = 2
MODEL = "cnn" #hog for cpu, cnn works slow on cpu

print("Loading known faces")

known_faces = []
known_names = []

for name in os.listdir(KNOWN_FACES_DIR):
for filename in os.listdir(f"{KNOWN_FACES_DIR}/{name}"):
image = face_recognition.load_image_file(f"{KNOWN_FACES_DIR}/{name}/{filename}")

encoding = face_recognition.face_encodings(image)[0]

encoding = face_recognition.face_encodings(image)
known_faces.append(encoding)

print(known_faces)

known_names.append(name)
print(known_names)

print("processing unknown faces ")

for filename in os.listdir(UNKNOWN_FACES_DIR):
print(filename)
image = face_recognition.load_image_file(f"{UNKNOWN_FACES_DIR}/{filename}")
locaations = face_recognition.face_locations(image, model=MODEL)
encodings = face_recognition.face_encodings(image, locaations)
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)

for face_encoding, face_location in zip(encodings, locaations):
results = face_recognition.compare_faces(known_faces, face_encoding, TOLERANCE)
print(results)
match = None
if True in results:
match = known_names[results.index(True)]
print(f"Match Found : {match}")

    top_left = (face_location[3], face_location[0])
    bottom_right = (face_location[1], face_location[2])

    color = [0, 255, 0]

    cv2.rectangle(image, top_left, bottom_right, color, FRAME_THICKNESS)

    top_left = (face_location[3], face_location[2])
    bottom_right = (face_location[1], face_location[2]+22)
    cv2.rectangle(image, top_left, bottom_right, color, cv2.FILLED)
    cv2.putText(image, match, (face_location[2]+15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (200,200,200), FONT_THICKNESS)

cv2.imshow(filename, image)
cv2.waitKey(0)
cv2.destroyWindow(filename)`

[nikhilkharade]

This is not even your code this is from sentdex on Youtube stop lying

[DataActivator]

This is not even your code this is from sentdex on Youtube stop lying

@nikhilkharade

yes bro .It is from sentdex.After his video i tried to implement but got this error. Don't come to conclusion without knowing anything. nowhere i have mentioned this is my code.

i even posted this error on his youtube comment section. when i googled about this error i came to this page where several people are trying to resolve.

[iamsandeepprasad]

I have a quick solution for that

the problem is that you are trying to match your unknown encoded image with a list that contains encoded known image, that means you are comparing the encoded image with a list, not with an image.

One possible solution is to use a for loop that loops over all the encoded known-face image and compare it with your unknown encoded image:

So the code could be something like this:

for face_encoding, face_location in zip(encoding,locations):

print(len(known_face))
for i in range(0,len(known_face)):  #loops through each encoded known_face 
  result=face_recognition.compare_faces(known_face[i],face_encoding,tolerance=0.6)

  match=None
  if True in result:
    match=known_names[i]
    print("Match found:",match)

    top_left=(face_location[3],face_location[0])
    bottom_right=(face_location[1],face_location[2])
    color=[0,255,0]
    cv2.rectangle(image,top_left,bottom_right,color,frame_tickness)
    top_left=(face_location[3],face_location[2])
    bottom_right=(face_location[1],face_location[2]+22)
    cv2.rectangle(image,top_left,bottom_right,color,cv2.FILLED)
    cv2.putText(image, match,(face_location[3]+10,face_location[2]+15),cv2.FONT_HERSHEY_COMPLEX,0.5,(200,200,200),font_thickness)

[iamsandeepprasad]

@B-0F @DataActivator

Hope it helps!

[dipanshi08]

I was getting a similar error and I solved it with a little change in the code.
The problem was actually in the part where I add a new image to the already known faces.
Change (known_names.append in 5th line)

img = face_recognition.load_image_file(file_stream)
# Get face encodings for faces in the uploaded image
unknown_face_encodings = face_recognition.face_encodings(img)
if len(unknown_face_encodings) > 0:
    known_faces.append(unknown_face_encodings)
    known_names.append(file_name)

to

img = face_recognition.load_image_file(file_stream)
# Get face encodings for faces in the uploaded image
unknown_face_encodings = face_recognition.face_encodings(img)
if len(unknown_face_encodings) > 0:
    known_faces.append(unknown_face_encodings[0])
    known_names.append(file_name)

Hope this helps someone :)

[meanOtaku]

I have a quick solution for that

the problem is that you are trying to match your unknown encoded image with a list that contains encoded known image, that means you are comparing the encoded image with a list, not with an image.

One possible solution is to use a for loop that loops over all the encoded known-face image and compare it with your unknown encoded image:

So the code could be something like this:

for face_encoding, face_location in zip(encoding,locations):

print(len(known_face))
for i in range(0,len(known_face)):  #loops through each encoded known_face 
  result=face_recognition.compare_faces(known_face[i],face_encoding,tolerance=0.6)

  match=None
  if True in result:
    match=known_names[i]
    print("Match found:",match)

    top_left=(face_location[3],face_location[0])
    bottom_right=(face_location[1],face_location[2])
    color=[0,255,0]
    cv2.rectangle(image,top_left,bottom_right,color,frame_tickness)
    top_left=(face_location[3],face_location[2])
    bottom_right=(face_location[1],face_location[2]+22)
    cv2.rectangle(image,top_left,bottom_right,color,cv2.FILLED)
    cv2.putText(image, match,(face_location[3]+10,face_location[2]+15),cv2.FONT_HERSHEY_COMPLEX,0.5,(200,200,200),font_thickness)

THanks it helped