Spaces:
Sleeping
Sleeping
File size: 4,790 Bytes
5971329 a48be09 5971329 47a77c5 5971329 3be2ce3 5971329 3be2ce3 5971329 3be2ce3 ef83c22 5971329 d51323f 3be2ce3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
import gradio as gr
import keras
from keras.preprocessing.image import img_to_array
import imutils
import cv2
from keras.models import load_model
import numpy as np
# parameters for loading data and images
detection_model_path = 'haarcascade_files/haarcascade_frontalface_default.xml'
emotion_model_path = 'model2/model2_entire_model.h5'
# hyper-parameters for bounding boxes shape
# loading models
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = ['neutral','happiness','surprise','sadness','anger','disgust','fear','contempt','unknown']
# def predict(frame):
# frame = imutils.resize(frame, width=300)
# gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
# faces = face_detection.detectMultiScale(gray, scaleFactor=1.1,
# minNeighbors=5, minSize=(30, 30),
# flags=cv2.CASCADE_SCALE_IMAGE)
# frameClone = frame.copy()
# if len(faces) > 0:
# faces = sorted(faces, reverse=True,
# key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
# (fX, fY, fW, fH) = faces
# # Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
# # the ROI for classification via the CNN
# roi = gray[fY:fY + fH, fX:fX + fW]
# roi = cv2.resize(roi, (48, 48))
# roi = roi.astype("float") / 255.0
# roi = img_to_array(roi)
# roi = np.expand_dims(roi, axis=0)
# preds = emotion_classifier.predict(roi)[0]
# label = EMOTIONS[preds.argmax()]
# else:
# return frameClone, "Can't find your face"
# probs = {}
# cv2.putText(frameClone, label, (fX, fY - 10),
# cv2.FONT_HERSHEY_DUPLEX, 1, (238, 164, 64), 1)
# cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
# (238, 164, 64), 2)
# for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
# probs[emotion] = float(prob)
# return frameClone, probs
# inp = gr.components.Image(sources="webcam", label="Your face")
# out = [
# gr.components.Image(label="Predicted Emotion"),
# gr.components.Label(num_top_classes=2, label="Top 2 Probabilities")
# ]
# title = "Facial Emotion Recognition"
# description = "How well can this model predict your emotions? Take a picture with your webcam, and it will guess if" \
# " you are: happy, sad, angry, disgusted, scared, surprised, or neutral."
# thumbnail = "https://raw.githubusercontent.com/gradio-app/hub-emotion-recognition/master/thumbnail.png"
# # gr.Interface(predict, inp, out, capture_session=True, title=title, thumbnail=thumbnail,
# # description=description).launch(inbrowser=True)
# gr.Interface(fn=predict, inputs=inp, outputs=out, title=title, thumbnail=thumbnail).launch()
######################################################################################################################################################
def predict(frame):
frame = imutils.resize(frame, width=300)
gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
faces = face_detection.detectMultiScale(gray, scaleFactor=1.1,
minNeighbors=5, minSize=(30, 30),
flags=cv2.CASCADE_SCALE_IMAGE)
frameClone = frame.copy()
if len(faces) > 0:
faces = sorted(faces, reverse=True,
key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
(fX, fY, fW, fH) = faces
# Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
# the ROI for classification via the CNN
roi = gray[fY:fY + fH, fX:fX + fW]
roi = cv2.resize(roi, (48, 48))
roi = roi.astype("float") / 255.0
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
preds = emotion_classifier.predict(roi)[0]
label = EMOTIONS[preds.argmax()]
else:
return frameClone, "Can't find your face"
probs = {}
cv2.putText(frameClone, label, (fX, fY - 10),
cv2.FONT_HERSHEY_DUPLEX, 1, (238, 164, 64), 1)
cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
(238, 164, 64), 2)
for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
probs[emotion] = float(prob)
return frameClone, probs
inp = gr.components.Video(sources="webcam", label="Your face")
out = [
gr.components.Video(label="Predicted Emotion"),
gr.components.Label(num_top_classes=2, label="Top 2 Probabilities")
]
gr.Interface(fn=predict, inputs=inp, outputs=out, title=title, thumbnail=thumbnail).launch()
|