运行yolov7时报错:
AssertionError: train: No labels in /root/autodl-tmp/yolov7/data/VOC2007NWPU/train.cache. Can not train without labels. See http
报错原因:
yolov7/utils/datasets.py文件中,大概347行函数 def img2label_paths(img_paths) 中
sa, sb = os.sep + 'JPEGImages' + os.sep, os.sep + 'labels' + os.sep 的问题
解决方法:
- 查看JPEGImages 是否为自己数据集中存放图片的文件夹
- 查看是否有labels文件(该文件中存放的是所有图片中目标框的标签)
附:生成voc格式数据集 标签文件夹的代码
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ['airplane', 'baseball_diamond', 'basketball_court', 'beach', 'bridge', 'chaparral', 'church', 'circular_farmland', 'cloud', 'commercial_area', 'dense_residential', 'desert', 'forest', 'freeway', 'golf_course', 'ground_track_field', 'harbor', 'industrial_area', 'intersection', 'island', 'lake', 'meadow', 'medium_residential', 'mobile_home_park', 'mountain', 'overpass', 'palace', 'parking_lot', 'railway', 'railway_station', 'rectangular_farmland', 'river', 'roundabout', 'runway', 'sea_ice', 'ship', 'snowberg', 'sparse_residential', 'stadium', 'storage_tank', 'tennis_court', 'terrace', 'thermal_power_station', 'wetland', 'windmill'] # 改为自己数据集中各类别标签
abs_path = os.getcwd()
print(abs_path)
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(image_id):
in_file = open('/root/yolov7/data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('/root/yolov7/data/labels/%s.txt' % (image_id), '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
#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))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for image_set in sets:
if not os.path.exists('/root/yolov7/data/labels/'):
os.makedirs('/root/yolov7/data/labels/')
image_ids = open('/root/yolov7/data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('/root/autodl-tmp/yolov7/data/VOC2007NWPU/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write(abs_path + '/yolov7/data/JPEGImages/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
注意:1. 看一下输出的abs_path 和 62行的代码组合在一起是否是存放图片的完整绝对路径
2. 其他路径也都要确保是绝对路径
(写在最后:该博客中的代码是参考的其他博客,但找不到该博客了,所以不能转载博客,还请博主见谅。或者可以私信我转载链接,我再加上,嘻嘻。)