人脸识别 model 对训练图像给出不正确的预测

Question

I am using below code to do face recognition on the image which was used in the model training as well. But when I run prediction on the same image, I get very weird result wherein it is detecting multiple faces which are incorrect. Result should have been only 'Aarav'

import numpy as np
import argparse
import imutils
import pickle
import cv2
import os

ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
    help="path to input image")
ap.add_argument("-d", "--detector", required=True,
    help="path to OpenCV's deep learning face detector")
ap.add_argument("-m", "--embedding-model", required=True,
    help="path to OpenCV's deep learning face embedding model")
ap.add_argument("-r", "--recognizer", required=True,
    help="path to model trained to recognize faces")
ap.add_argument("-l", "--le", required=True,
    help="path to label encoder")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
    help="minimum probability to filter weak detections")
args = vars(ap.parse_args())

# load our serialized face detector from disk
print("[INFO] loading face detector...")
protoPath = os.path.sep.join([args["detector"], "deploy.prototxt"])
modelPath = os.path.sep.join([args["detector"],"res10_300x300_ssd_iter_140000.caffemodel"])
detector = cv2.dnn.readNetFromCaffe(protoPath, modelPath)

# load our serialized face embedding model from disk
print("[INFO] loading face recognizer...")
embedder = cv2.dnn.readNetFromTorch(args["embedding_model"])

# load the actual face recognition model along with the label encoder
recognizer = pickle.loads(open(args["recognizer"], "rb").read())
le = pickle.loads(open(args["le"], "rb").read())

# load the image, resize it to have a width of 600 pixels (while
# maintaining the aspect ratio), and then grab the image dimensions
image = cv2.imread(args["image"])
image = imutils.resize(image, width=600)
(h, w) = image.shape[:2]

# construct a blob from the image
imageBlob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 1.0, (300, 300),(104.0, 177.0, 123.0), swapRB=False, crop=False)
# apply OpenCV's deep learning-based face detector to localize
# faces in the input image
detector.setInput(imageBlob)
detections = detector.forward()
#print("detections",detections)
# loop over the detections
for i in range(0, detections.shape[2]):
    # extract the confidence (i.e., probability) associated with the
    # prediction
    confidence = detections[0, 0, i, 2]
    # filter out weak detections
    if confidence > args["confidence"]:
        # compute the (x, y)-coordinates of the bounding box for the
        # face
        box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
        (startX, startY, endX, endY) = box.astype("int")
        print("box",box)
        # extract the face ROI
        face = image[startY:endY, startX:endX]
        (fH, fW) = face.shape[:2]
        # ensure the face width and height are sufficiently large
        if fW < 20 or fH < 20:
            continue
        # construct a blob for the face ROI, then pass the blob
        # through our face embedding model to obtain the 128-d
        # quantification of the face
        faceBlob = cv2.dnn.blobFromImage(face, 1.0 / 255, (96, 96),(0, 0, 0), swapRB=True, crop=False)
        embedder.setInput(faceBlob)
        vec = embedder.forward()
        # perform classification to recognize the face
        preds = recognizer.predict_proba(vec)[0]
        j = np.argmax(preds)
        proba = preds[j]
        name = le.classes_[j]
        # draw the bounding box of the face along with the associated
        # probability
        text = "{}: {:.2f}%".format(name, proba * 100)
        y = startY - 10 if startY - 10 > 10 else startY + 10
        cv2.rectangle(image, (startX, startY), (endX, endY),
            (0, 0, 255), 2)
        cv2.putText(image, text, (startX, y),
            cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)

Ideally the model should have learnt the image and should have given proper result on the image which is already trained. Am I missing something? Would need your help to debug this issue.

Answer 1

Being a part of the training set does not guarantee the correct classification for any image.

For that kind of guarantee, model should be performing with %100 accuracy on training examples, which would make the loss 0. Do you get 0 loss during your training? If not, maybe it is not surprising to have some errors in the models predictions on training examples.

Because it did not entirely fit on the training set yet.