yolo训练时遇到GBK编码问题

yolo训练时遇到GBK编码问题

启动训练具体信息如下:

comet upload E:\python\yolov9-main.cometml-runs\e0c17dd22058467f98cf447d5cc45bf5.zip

COMET INFO: Using 'D:\pycharmProject\yolov5-master-6.2\.cometml-runs' path as offline directory. Pass 'offline_directory' parameter into constructor or set the 'COMET_OFFLINE_DIRECTORY' environment variable to manually choose where to store offline experiment archives.

COMET WARNING: Native output logging mode is not available, falling back to basic output logging

Traceback (most recent call last):

File "D:\pycharmProject\yolov5-master-6.2old\train.py", line 630, in

main(opt)

File "D:\pycharmProject\yolov5-master-6.2old\train.py", line 526, in main

train(opt.hyp, opt, device, callbacks)

File "D:\pycharmProject\yolov5-master-6.2old\train.py", line 94, in train

loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance

File "D:\pycharmProject\yolov5-master-6.2old\utils\loggers_init _.py", line 132, in init

self.comet_logger = CometLogger(self.opt, self.hyp)

File "D:\pycharmProject\yolov5-master-6.2old\utils\loggers\comet_init _.py", line 97, in init

self.data_dict = self.check_dataset(self.opt.data)

File "D:\pycharmProject\yolov5-master-6.2old\utils\loggers\comet_init _.py", line 232, in check_dataset

data_config = yaml.safe_load(f)

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml_init _.py", line 125, in safe_load

return load(stream, SafeLoader)

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml_init _.py", line 79, in load

loader = Loader(stream)

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml\loader.py", line 34, in init

Reader.init (self, stream)

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml\reader.py", line 85, in init

self.determine_encoding()

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml\reader.py", line 124, in determine_encoding

self.update_raw()

File "D:\ProgramData\Anaconda3\lib\site-packages\yaml\reader.py", line 179, in update_raw

data = self.stream.read(size)

UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 233: illegal multibyte sequence

<_io.TextIOWrapper name='data\coco128.yaml' mode='r' encoding='cp936'> ---------------------

COMET INFO: Couldn't find a Git repository in 'D:\pycharmProject\yolov5-master-6.2old' nor in any parent directory. Set COMET_GIT_DIRECTORY if your Git Repository is elsewhere.

COMET WARNING: Unknown error exporting current conda environment

COMET INFO: ---------------------------------------------------------------------------------------

COMET INFO: Comet.ml OfflineExperiment Summary

COMET INFO: ---------------------------------------------------------------------------------------

COMET INFO: Data:

COMET INFO: display_summary_level : 1

COMET INFO: url : [OfflineExperiment will get URL after upload]

COMET INFO: Others:

COMET INFO: offline_experiment : True

COMET INFO: Uploads:

COMET INFO: conda-info : 1

COMET INFO: conda-specification : 1

COMET INFO: environment details : 1

COMET INFO: installed packages : 1

COMET INFO:

COMET WARNING: Experiment Name is generated at upload time for Offline Experiments unless set explicitly with Experiment.set_name

COMET WARNING: To get all data logged automatically, import comet_ml before the following modules: tensorboard, torch.

COMET INFO: Still saving offline stats to messages file before program termination (may take up to 120 seconds)

COMET INFO: Starting saving the offline archive

COMET INFO: To upload this offline experiment, run:

comet upload D:\pycharmProject\yolov5-master-6.2.cometml-runs\bf6f678f442649758c6ec09340cd9b34.zip

解决方法

bash 复制代码
pip uninstall comet-ml

删运行命令卸载掉这个包后可以正常运行


参考文章https://blog.csdn.net/shuangshuangboole/article/details/131420080

https://github.com/ultralytics/yolov5/issues/10301

相关推荐
Luis Li 的猫猫2 小时前
深度学习中的知识蒸馏
人工智能·经验分享·深度学习·学习·算法
带娃的IT创业者3 小时前
机器学习实战(6):支持向量机(SVM)——强大的非线性分类器
算法·机器学习·支持向量机
wyg_0311137 小时前
用deepseek学大模型04-模型可视化与数据可视化
人工智能·机器学习·信息可视化
盼小辉丶8 小时前
TensorFlow深度学习实战(8)——卷积神经网络
深度学习·cnn·tensorflow
我是一个对称矩阵9 小时前
YOLOv5-Seg 深度解析:与 YOLOv5 检测模型的区别
人工智能·yolo·目标跟踪
Donvink9 小时前
【复现DeepSeek-R1之Open R1实战】系列5:SFT源码逐行深度解析
人工智能·深度学习·语言模型·transformer
好评笔记9 小时前
深度学习笔记——循环神经网络之LSTM
笔记·rnn·深度学习
eso198311 小时前
浅谈DNN(深度神经网络)算法原理
深度学习·算法·dnn
白-胖-子11 小时前
DeepSeek系统架构的逐层分类拆解分析,从底层基础设施到用户端分发全链路
人工智能·机器学习·分类·数据挖掘·系统架构·agi·deepseek
taoqick12 小时前
nn.EmbeddingBag把offsets之间的进行归约,offsets从0开始
pytorch·python·深度学习