How to use fer - 10 common examples

To help you get started, we’ve selected a few fer examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github justinshenk / fer / tests / test_fer.py View on Github external
def setUpClass(cls):
        global detector, mtcnn_detector
        detector = FER()
        mtcnn_detector = FER(mtcnn=True)
github justinshenk / fer / tests / test_fer.py View on Github external
def setUpClass(cls):
        global detector, mtcnn_detector
        detector = FER()
        mtcnn_detector = FER(mtcnn=True)
github justinshenk / fer / tests / test_fer.py View on Github external
def test_video(self):
        detector = FER()
        video = Video("tests/woman2.mp4")

        raw_data = video.analyze(detector, display=False)
        assert isinstance(raw_data, list)

        # Convert to pandas for analysis
        df = video.to_pandas(raw_data)
        assert sum(df.neutral[:5] > 0.5) == 5, f"Expected neutral > 0.5, got {df.neutral[:5]}"
        assert isinstance(df, pd.DataFrame)
        assert "angry" in df
        df = video.get_first_face(df)
        assert isinstance(df, pd.DataFrame)
        df = video.get_emotions(df)
        assert isinstance(df, pd.DataFrame)
github justinshenk / fer / tests / test_fer.py View on Github external
def test_detect_faces_invalid_content(self):
        """
        FER detects invalid images
        :return:
        """
        justin = cv2.imread("example.py")

        with self.assertRaises(InvalidImage):
            result = detector.detect_emotions(justin)  # type: list
github justinshenk / fer / tests / test_fer.py View on Github external
def test_video(self):
        detector = FER()
        video = Video("tests/woman2.mp4")

        raw_data = video.analyze(detector, display=False)
        assert isinstance(raw_data, list)

        # Convert to pandas for analysis
        df = video.to_pandas(raw_data)
        assert sum(df.neutral[:5] > 0.5) == 5, f"Expected neutral > 0.5, got {df.neutral[:5]}"
        assert isinstance(df, pd.DataFrame)
        assert "angry" in df
        df = video.get_first_face(df)
        assert isinstance(df, pd.DataFrame)
        df = video.get_emotions(df)
        assert isinstance(df, pd.DataFrame)
github justinshenk / fer / video-example.py View on Github external
import matplotlib
if os.name == 'posix' and "DISPLAY" not in os.environ:
    matplotlib.use("Agg")

import matplotlib.pyplot as plt

from fer import FER
from fer import Video

if __name__ == "__main__":
    try:
        videofile = sys.argv[1]
    except:
        videofile = "test.mp4"
    detector = FER(mtcnn=True)
    video = Video(videofile)

    # Output list of dictionaries
    raw_data = video.analyze(detector, display=False)

    # Convert to pandas for analysis
    df = video.to_pandas(raw_data)
    df = video.get_first_face(df)
    df = video.get_emotions(df)

    # Plot emotions
    df.plot()
    plt.show()
github justinshenk / fer / example.py View on Github external
#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import cv2

from fer import FER

detector = FER(mtcnn=True) # or with mtcnn=False for Haar Cascade Classifier

image = cv2.imread("justin.jpg")
result = detector.detect_emotions(image)

# Result is an array with all the bounding boxes detected. We know that for 'justin.jpg' there is only one.
bounding_box = result[0]["box"]
emotions = result[0]["emotions"]

cv2.rectangle(
    image,
    (bounding_box[0], bounding_box[1]),
    (bounding_box[0] + bounding_box[2], bounding_box[1] + bounding_box[3]),
    (0, 155, 255),
    2,
)
github justinshenk / fer / src / fer / fer.py View on Github external
def detect_emotions(self, img: np.ndarray) -> list:
        """
        Detects bounding boxes from the specified image with ranking of emotions.
        :param img: image to process (BGR or gray)
        :return: list containing all the bounding boxes detected with their emotions.
        """
        if img is None or not hasattr(img, "shape"):
            raise InvalidImage("Image not valid.")

        emotion_labels = self._get_labels()

        face_rectangles = self.find_faces(img, bgr=True)

        gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

        emotions = []
        for face_coordinates in face_rectangles:
            face_coordinates = self.tosquare(face_coordinates)
            x1, x2, y1, y2 = self.__apply_offsets(face_coordinates)

            if y1 < 0 or x1 < 0:
                gray_img = self.pad(gray_img)
                x1 += 40
                x2 += 40
github justinshenk / fer / video-example.py View on Github external
import matplotlib
if os.name == 'posix' and "DISPLAY" not in os.environ:
    matplotlib.use("Agg")

import matplotlib.pyplot as plt

from fer import FER
from fer import Video

if __name__ == "__main__":
    try:
        videofile = sys.argv[1]
    except:
        videofile = "test.mp4"
    detector = FER(mtcnn=True)
    video = Video(videofile)

    # Output list of dictionaries
    raw_data = video.analyze(detector, display=False)

    # Convert to pandas for analysis
    df = video.to_pandas(raw_data)
    df = video.get_first_face(df)
    df = video.get_emotions(df)

    # Plot emotions
    df.plot()
    plt.show()
github justinshenk / deepemotion / app.py View on Github external
def load_video(filename):
    global current_video
    current_video = Video(
        filename, outdir='/tmp', tempfile=to_uploads('temp_outfile.mp4'))
    return current_video

fer

Facial expression recognition from images

MIT
Latest version published 9 months ago

Package Health Score

60 / 100
Full package analysis

Similar packages