YOLOX报错FileNotFoundError: [Errno 2] No such file or directory: ‘xxx.xml‘个人解决方案
在训练YOLOX的时候，每训练10次，进行模型评估的时候，会报错停止，完整报错信息如下：
2022-07-05 16:19:49 | ERROR | yolox.core.launch:98 - An error has been caught in function 'launch', process 'MainProcess' (17800), thread 'MainThread' (
26892):
Traceback (most recent call last):
File "E:\Study\DeepLearn\DPlearn\YOLO\YOLOX\tools\train.py", line 134, in
launch(
└
> File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\core\launch.py", line 98, in launch
main_func(*args)
│ └ (╒═══════════════════╤═══════════════════════════════════════════════════════════════════════════════════════════════════════...
└
File "E:\Study\DeepLearn\DPlearn\YOLO\YOLOX\tools\train.py", line 118, in main
trainer.train()
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\core\trainer.py", line 76, in train
self.train_in_epoch()
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\core\trainer.py", line 86, in train_in_epoch
self.after_epoch()
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\core\trainer.py", line 222, in after_epoch
self.evaluate_and_save_model()
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\core\trainer.py", line 328, in evaluate_and_save_model
(ap50_95, ap50, summary), predictions = self.exp.eval(
│ │ └
│ └ ╒═══════════════════╤═══════════════════════════════════════════════════════════════════════════════════
═════════════════════...
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\exp\yolox_base.py", line 322, in eval
return evaluator.evaluate(model, is_distributed, half, return_outputs=return_outputs)
│ │ │ │ │ └ True
│ │ │ │ └ False
│ │ │ └ False
│ │ └ YOLOX(
│ │ (backbone): YOLOPAFPN(
│ │ (backbone): CSPDarknet(
│ │ (stem): Focus(
│ │ (conv): BaseConv(
│ │ (conv): ...
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\evaluators\voc_evaluator.py", line 114, in evaluate
eval_results = self.evaluate_prediction(data_list, statistics)
│ │ │ └ tensor([0.7917, 0.3148, 1.0000], device='cuda:0')
│ │ └ {0: (tensor([[ 5.5528e+01, -4.4439e+01, 1.1621e+03, 1.1649e+03],
│ │ [ 4.6180e+02, -1.1025e+01, 1.1711e+03, 1.1398e+0...
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\evaluators\voc_evaluator.py", line 186, in evaluate_prediction
mAP50, mAP70 = self.dataloader.dataset.evaluate_detections(all_boxes, tempdir)
│ │ │ │ │ └ 'C:\\Users\\76493\\AppData\\Local\\Temp\\tmp3n4ozfu8'
│ │ │ │ └ [[array([[ 5.55276413e+01, -4.44387054e+01, 1.16205750e+03,
│ │ │ │ 1.16488818e+03, 8.09440315e-01],
│ │ │ │ [ 4.61802429e+...
│ │ │ └
│ │ └
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\data\datasets\voc.py", line 271, in evaluate_detections
mAP = self._do_python_eval(output_dir, iou)
│ │ │ └ 0.5
│ │ └ 'C:\\Users\\76493\\AppData\\Local\\Temp\\tmp3n4ozfu8'
│ └
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\data\datasets\voc.py", line 335, in _do_python_eval
rec, prec, ap = voc_eval(
└
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\evaluators\voc_eval.py", line 92, in voc_eval
recs[imagename] = parse_rec(annopath.format(imagename))
│ │ │ │ │ └ '112_3'
│ │ │ │ └
│ │ │ └ '{:s}.xml'
│ │ └
│ └ '112_3'
└ {}
File "C:\ProgramData\Anaconda3\lib\site-packages\yolox-0.3.0-py3.9.egg\yolox\evaluators\voc_eval.py", line 16, in parse_rec
tree = ET.parse(filename)
│ │ └ '112_3.xml'
│ └
└
File "C:\ProgramData\Anaconda3\lib\xml\etree\ElementTree.py", line 1229, in parse
tree.parse(source, parser)
│ │ │ └ None
│ │ └ '112_3.xml'
│ └
└
File "C:\ProgramData\Anaconda3\lib\xml\etree\ElementTree.py", line 569, in parse
source = open(source, "rb")
└ '112_3.xml'
FileNotFoundError: [Errno 2] No such file or directory: '112_3.xml' 参考了大佬文章中的解决方案windows10搭建YOLOx环境 训练+测试+评估
更改/yolox/evaluators/voc_eval.py文件中代码，在def parse_rec(filename)前面加上一句话。
import numpy as np
#这里写入你数据集的Annotations文件夹的绝对路径
root=r'E:DeepLearn/dataset/yolox/VOCdevkit/VOC2007/Annotations/'
def parse_rec(filename):
"""Parse a PASCAL VOC xml file"""
tree = ET.parse(filename)
objects = []
for obj in tree.findall("object"):在终端里执行python setup.py install 更新yolox
PS:如果想每训练一轮就评估一下模型，更改/yolox/exp/yolox_base.py文件中
self.eval_interval = 1，将10改为1，就是每训练一轮评估一下，更改之后记得执行一下python setup.py install更新一下。
上面操作执行完了之后，运行之后，发现还是报一样的错，评估的时候还是找不到xml文件。
又去翻github，最后在github的issue中找到了答案
如果是windows环境的话，需要把/yolox/data/datasets/voc.py文件中的
annopath = os.path.join(rootpath, "Annotations", "{:s}.xml")替换为
annopath = os.path.join(rootpath, "Annotations", "{}.xml")更新一下后再执行，没有报错了