Question

我正在使用以下代码对模型训练中使用的图像进行人脸识别。但是，当我对同一张图片进行预测时，我得到了非常奇怪的结果，其中它正在检测出不正确的多张面孔。结果应该只是“ 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)

理想地，模型应该已经学习了图像，并且应该在已经训练的图像上给出正确的结果。我想念什么吗？需要您的帮助来调试此问题。

Answer 1

成为训练集的一部分不能保证对任何图像进行正确的分类。

对于这种保证，模型在训练示例上的准确度应为％100，这会使损失为0。您在训练过程中损失了0吗？如果不是这样，在训练示例的模型预测中出现一些错误也许并不奇怪。

因为它还不完全适合训练集。

人脸识别模型无法正确预测训练图像

1 个答案: