3
votes

I'm getting the following error in my code.

import mtcnn
# print version
print(mtcnn.__version__)

# demonstrate face detection on 5 Celebrity Faces Dataset
from os import listdir
from PIL import Image
from numpy import asarray
from matplotlib import pyplot
from mtcnn.mtcnn import MTCNN
print("MTCNN: {}".format(mtcnn.__version__))
import tensorflow as tf
from tensorflow import keras

# extract a single face from a given photograph
def extract_face(filename, required_size=(160, 160)):
    # load image from file
    image = Image.open(filename)
    # convert to RGB, if needed
    image = image.convert('RGB')
    # convert to array
    pixels = asarray(image)
    # create the detector, using default weights
    detector = MTCNN()
    # detect faces in the image
    results = detector.detect_faces(pixels)
    # extract the bounding box from the first face
    x1, y1, width, height = results[0]['box']
    # bug fix
    x1, y1 = abs(x1), abs(y1)
    x2, y2 = x1 + width, y1 + height
    # extract the face
    face = pixels[y1:y2, x1:x2]
    # resize pixels to the model size
    image = Image.fromarray(face)
    image = image.resize(required_size)
    face_array = asarray(image)
    return face_array

# specify folder to plot
#folder = '5-celebrity-faces-dataset/train/ben_afflek/'
folder = '5-celebrity-faces-dataset/train/ben_afflek'
i = 1
# enumerate files
for filename in listdir(folder):
    # path
    path = folder + '/' + filename
    # get face
    face = extract_face(path)
    print(i, face.shape)
    # plot
    pyplot.subplot(2, 7, i)
    pyplot.axis('off')
    pyplot.imshow(face)
    i += 1
pyplot.show()

Error:

anaconda3\envs\py3\lib\site-packages\keras\backend\tensorflow_backend.py", line 68, in get_uid graph = tf.get_default_graph()

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

I tried several different imports, but nothing works. It seems that this error is usual, but I'm not finding anything that solves my problem.

1

1 Answers

1
votes

In the answer here import keras from tensorflow, like you did, solves the problem.

But the problem in your case is that the MTCNN works on pure Keras instead of TensorFlow, so the fact that you load in your "main.py" keras from tensorflow does not have any effect. You either need to downgrade the tensorflow version or you modify every import in MTCNN which is not guaranteed to work unfortunately.