为 SVHN 数据集实现 YOLOv3 object 检测器

Question

I am trying to use object detection for digit detection. I found the SVHN dataset . Speed is important in my project so I decided to apply a YOLO approach.

However, all tutorials and explanatiosn on using YOLOv3 either expect me to be using a dataset made from the Google Open Images API or by manually labeling images using a tool such as labellimg.py.

I however have a premade dataset with annotaions in the PASCAL VOC format (which can be found here https://github.com/penny4860/svhn-voc-annotation-format ). Because of this I do not create a labels.txt or classes.txt file as I do no labeling myself.

I am rather at a loss on where to get started.

Any help would be appreciated.

Answer 1

You can follow the below code to convert from PASCAL VOC to YOLO supported format.

import glob
import os
import pickle
import xml.etree.ElementTree as ET
from os import listdir, getcwd
from os.path import join

dirs = ['train', 'val']
classes = ['person', 'car']

def getImagesInDir(dir_path):
    image_list = []
    for filename in glob.glob(dir_path + '/*.jpg'):
        image_list.append(filename)

    return image_list

def convert(size, box):
    dw = 1./(size[0])
    dh = 1./(size[1])
    x = (box[0] + box[1])/2.0 - 1
    y = (box[2] + box[3])/2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(dir_path, output_path, image_path):
    basename = os.path.basename(image_path)
    basename_no_ext = os.path.splitext(basename)[0]

    in_file = open(dir_path + '/' + basename_no_ext + '.xml')
    out_file = open(output_path + basename_no_ext + '.txt', 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

cwd = getcwd()

for dir_path in dirs:
    full_dir_path = cwd + '/' + dir_path
    output_path = full_dir_path +'/yolo/'

    if not os.path.exists(output_path):
        os.makedirs(output_path)

    image_paths = getImagesInDir(full_dir_path)
    list_file = open(full_dir_path + '.txt', 'w')

    for image_path in image_paths:
        list_file.write(image_path + '\n')
        convert_annotation(full_dir_path, output_path, image_path)
    list_file.close()

    print("Finished processing: " + dir_path)