Интеграция двух моделей в одну модель (классификация объектов и классификация полов и распознавание эмоций)

Question

Я имел дело с проектом по ML, в котором мы готовы создать автономное приложение.Таким образом, мы не используем API для этого проекта, мы используем две модели.Один для классификации объектов, а другой для классификации пола и распознавания эмоций.Теперь у меня проблема с объединением двух моделей в одну.Обе модели представлены в OpenCV.

Код для deep_learning_object_detecti * on

# USAGE
# python deep_learning_object_detection.py --image images/example_01.jpg \
#--prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel

# import the necessary packages
import numpy as np
import argparse
import cv2  

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
  help="path to input image")
ap.add_argument("-p", "--prototxt", required=True,
  help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
  help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
  help="minimum probability to filter weak detections")
args = vars(ap.parse_args())

# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
  "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
  "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
  "sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)

# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
net.setInput(blob)
detections = net.forward()

# loop over the detections
for i in np.arange(0, detections.shape[2]):
  # extract the confidence (i.e., probability) associated with the
  # prediction
  confidence = detections[0, 0, i, 2]

  # filter out weak detections by ensuring the `confidence` is
  # greater than the minimum confidence
  if confidence > args["confidence"]:
      # extract the index of the class label from the `detections`,
      # then compute the (x, y)-coordinates of the bounding box for
      # the object
      idx = int(detections[0, 0, i, 1])
      box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
      (startX, startY, endX, endY) = box.astype("int")

      # display the prediction
      label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
      print("[INFO] {}".format(label))
      cv2.rectangle(image, (startX, startY), (endX, endY),
          COLORS[idx], 2)
      y = startY - 15 if startY - 15 > 15 else startY + 15
      cv2.putText(image, label, (startX, y),
          cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)

# show the output image

cv2.imshow("Output", image)
cv2.waitKey(0)

Код для распознавания пола и эмоций

import sys
import argparse
import cv2
from keras.models import load_model
import numpy as np

from utils.datasets import get_labels
from utils.inference import detect_faces
from utils.inference import draw_text
from utils.inference import draw_bounding_box
from utils.inference import apply_offsets
from utils.inference import load_detection_model
from utils.inference import load_image
from utils.preprocessor import preprocess_input

# parameters for loading data and images
image_path = sys.argv[1]
detection_model_path = '../trained_models/detection_models/haarcascade_frontalface_default.xml'
emotion_model_path = '../trained_models/emotion_models/fer2013_mini_XCEPTION.102-0.66.hdf5'
gender_model_path = '../trained_models/gender_models/simple_CNN.81-0.96.hdf5'
emotion_labels = get_labels('fer2013')
gender_labels = get_labels('imdb')
font = cv2.FONT_HERSHEY_SIMPLEX

# hyper-parameters for bounding boxes shape
gender_offsets = (30, 60)
gender_offsets = (10, 10)
emotion_offsets = (20, 40)
emotion_offsets = (0, 0)

# loading models
face_detection = load_detection_model(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
gender_classifier = load_model(gender_model_path, compile=False)

# getting input model shapes for inference
emotion_target_size = emotion_classifier.input_shape[1:3]
gender_target_size = gender_classifier.input_shape[1:3]

# loading images
rgb_image = load_image(image_path, grayscale=False)
gray_image = load_image(image_path, grayscale=True)
gray_image = np.squeeze(gray_image)
gray_image = gray_image.astype('uint8')

faces = detect_faces(face_detection, gray_image)
for face_coordinates in faces:
    x1, x2, y1, y2 = apply_offsets(face_coordinates, gender_offsets)
    rgb_face = rgb_image[y1:y2, x1:x2]

    x1, x2, y1, y2 = apply_offsets(face_coordinates, emotion_offsets)
    gray_face = gray_image[y1:y2, x1:x2]

    try:
        rgb_face = cv2.resize(rgb_face, (gender_target_size))
        gray_face = cv2.resize(gray_face, (emotion_target_size))
    except:
        continue

    rgb_face = preprocess_input(rgb_face, False)
    rgb_face = np.expand_dims(rgb_face, 0)
    gender_prediction = gender_classifier.predict(rgb_face)
    gender_label_arg = np.argmax(gender_prediction)
    gender_text = gender_labels[gender_label_arg]

    gray_face = preprocess_input(gray_face, True)
    gray_face = np.expand_dims(gray_face, 0)
    gray_face = np.expand_dims(gray_face, -1)
    emotion_label_arg = np.argmax(emotion_classifier.predict(gray_face))
    emotion_text = emotion_labels[emotion_label_arg]

    if gender_text == gender_labels[0]:
        color = (0, 0, 255)
    else:
        color = (255, 0, 0)

    draw_bounding_box(face_coordinates, rgb_image, color)
    draw_text(face_coordinates, rgb_image, gender_text, color, 0, -20, 1, 2)
    draw_text(face_coordinates, rgb_image, emotion_text, color, 0, -50, 1, 2)

bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
cv2.imwrite('../images/predicted_test_image.png', bgr_image)

Как объединить эти две модели в одну модель.Заранее спасибо.