Python OpenCV LoadDatasetList，最后两个参数是什么？

Question

我目前正在尝试使用OpenCV 4.2.2来训练一个数据集，我浏览了网页，但是只有两个参数的示例。OpenCV 4.2.2 loadDatasetList需要4个参数，但存在一些缺点，我已尽力克服这些缺点。起初我尝试使用一个数组，但loadDatasetList抱怨该数组不可移植，然后我继续执行下面的代码，但运气不佳。非常感谢您的帮助，谢谢您抽出时间，希望大家平安

在未使用iter（）的数组中传递之前的错误

PS E:\MTCNN> python kazemi-train.py No valid input file was given, please check the given filename. Traceback (most recent call last): File "kazemi-train.py", line 35, in status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, imageFiles, annotationFiles) TypeError: cannot unpack non-iterable bool object

当前错误为：

PS E:\MTCNN> python kazemi-train.py Traceback (most recent call last): File "kazemi-train.py", line 35, in status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, iter(imageFiles), iter(annotationFiles)) SystemError: returned NULL without setting an error

import os
import time
import cv2
import numpy as np
import argparse

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Training of kazemi facial landmark algorithm.')
    parser.add_argument('--face_cascade', type=str, help="Path to the cascade model file for the face detector",
                        default=os.path.join(os.path.dirname(os.path.realpath(__file__)),'models','haarcascade_frontalface_alt2.xml'))
    parser.add_argument('--kazemi_model', type=str, help="Path to save the kazemi trained model file",
                        default=os.path.join(os.path.dirname(os.path.realpath(__file__)),'models','face_landmark_model.dat'))
    parser.add_argument('--kazemi_config', type=str, help="Path to the config file for training",
                        default=os.path.join(os.path.dirname(os.path.realpath(__file__)),'models','config.xml'))
    parser.add_argument('--training_images', type=str, help="Path of a text file contains the list of paths to all training images",
                        default=os.path.join(os.path.dirname(os.path.realpath(__file__)),'train','images_train.txt'))
    parser.add_argument('--training_annotations', type=str, help="Path of a text file contains the list of paths to all training annotation files",
                        default=os.path.join(os.path.dirname(os.path.realpath(__file__)),'train','points_train.txt'))

    parser.add_argument('--verbose', action='store_true')
    args = parser.parse_args()

    start = time.time()
    facemark = cv2.face.createFacemarkKazemi()
    if args.verbose:
        print("Creating the facemark took {} seconds".format(time.time()-start))
    start = time.time()
    imageFiles = []
    annotationFiles = []
    for file in os.listdir("./AppendInfo"):
        if file.endswith(".jpg"):
            imageFiles.append(file)
        if file.endswith(".txt"):
            annotationFiles.append(file)
    status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, iter(imageFiles), iter(annotationFiles))
    assert(status == True)
    if args.verbose:
        print("Loading the dataset took {} seconds".format(time.time()-start))

    scale  = np.array([460.0, 460.0])
    facemark.setParams(args.face_cascade,args.kazemi_model,args.kazemi_config,scale)

    for i in range(len(images_train)):
        start = time.time()
        img = cv2.imread(images_train[i])
        if args.verbose:
            print("Loading the image took {} seconds".format(time.time()-start))

        start = time.time()
        status, facial_points = cv2.face.loadFacePoints(landmarks_train[i])
        assert(status == True)
        if args.verbose:
            print("Loading the facepoints took {} seconds".format(time.time()-start))

        start = time.time()
        facemark.addTrainingSample(img,facial_points)
        assert(status == True)
        if args.verbose:
            print("Adding the training sample took {} seconds".format(time.time()-start))

    start = time.time()
    facemark.training()
    if args.verbose:
        print("Training took {} seconds".format(time.time()-start))

如果仅使用2个参数，则会引发此错误

File "kazemi-train.py", line 37, in status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations) TypeError: loadDatasetList() missing required argument 'images' (pos 3)

如果我尝试使用3个参数，则会出现此错误

Traceback (most recent call last): File "kazemi-train.py", line 37, in status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, iter(imagePaths)) TypeError: loadDatasetList() missing required argument 'annotations' (pos 4)

关于loadDatasetList的文档

Answer 1

您提供的图形是指^ {< CD1>}的C++ API，在很多情况下，其参数通常不能映射到Python API的参数。一个原因是Python函数可以返回多个值，而C++不能。在C++ API中，提供第三和第四参数来存储函数的输出。它们分别存储从imageList中的文本文件读取后的图像路径，以及通过在annotationList中读取另一个文本文件来存储注释的路径

回到你的问题，我在Python中找不到该函数的任何参考。我相信API在OpenCV 4中已经改变了。经过多次试验，我确信cv2.face.loadDatasetList只返回一个布尔值，而不是一个元组。这就是为什么您会遇到第一个错误TypeError: cannot unpack non-iterable bool object，即使您填写了四个参数

毫无疑问，cv2.face.loadDatasetList应该生成两个文件路径列表。因此，第一部分的代码应该如下所示：

images_train = []
landmarks_train = []
status = cv2.face.loadDatasetList(args.training_images, args.training_annotations, images_train, landmarks_train)

我希望images_train和landmarks_train应该包含图像和地标注释的文件路径，但它没有按预期工作

在理解了整个程序之后，我编写了一个新函数my_loadDatasetList来替换（断开的）cv2.face.loadDatasetList

def my_loadDatasetList(text_file_images, text_file_annotations):
    status = False
    image_paths, annotation_paths = [], []
    with open(text_file_images, "r") as a_file:
        for line in a_file:
            line = line.strip()
            if line != "":
                image_paths.append(line)
    with open(text_file_annotations, "r") as a_file:
        for line in a_file:
            line = line.strip()
            if line != "":
                annotation_paths.append(line)
    status = len(image_paths) == len(annotation_paths)
    return status, image_paths, annotation_paths

您现在可以替换

status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, iter(imageFiles), iter(annotationFiles))

借

status, images_train, landmarks_train = my_loadDatasetList(args.training_images, args.training_annotations)

我已经测试了images_train和landmarks_train可以分别通过cv2.imread和cv2.face.loadFacePoints使用来自here的数据进行加载

Answer 2

从文档中，我可以看到行cv2.face.loadDatasetList只返回一个布尔值，然后从参数中删除iter。函数loadDatasetList接受一个列表作为第三个和第四个参数

因此，请在代码中进行以下更改：

发件人：

status, images_train, landmarks_train = cv2.face.loadDatasetList(args.training_images,args.training_annotations, iter(imageFiles), iter(annotationFiles))

致：

status = cv2.face.loadDatasetList(args.training_images,args.training_annotations, imageFiles, annotationFiles)