zh #8026
Replies: 109 comments 230 replies
-
请问一下 ,我制备的负样本怎么使用yolov8 的代码进行训练,目前还未找到解决办法。 |
Beta Was this translation helpful? Give feedback.
-
请问,YOLO在Document Layout Analysis上有没有好的表现,谢谢! |
Beta Was this translation helpful? Give feedback.
-
您好,请问会考虑支持yolov9吗? |
Beta Was this translation helpful? Give feedback.
-
你好,想用yolov8进行多类别的关键点检测,我需要怎么修改代码呢 |
Beta Was this translation helpful? Give feedback.
-
你好,我在运行yolo predict model=yolov8n.pt source='ultralytics/assets/bus.jpg'时出现了 |
Beta Was this translation helpful? Give feedback.
-
你好,我是一名初学者,如果我想得到经过我自己改良的预训练模型,请问我应该去哪里修改yolov8的对应的函数部分(就是修改诸如损失函数之类的),然后在得到不同于yolov8n.pt的不同的预训练模型,我是在github上将ultralytics-main文件夹整个下载下来了,但我找不到相应的部分😭 |
Beta Was this translation helpful? Give feedback.
-
这是来自QQ邮箱的假期自动回复邮件。你好,我最近正在休假中,无法亲自回复你的邮件。我将在假期结束后,尽快给你回复。
|
Beta Was this translation helpful? Give feedback.
-
您好,请问yolov8怎么做增量训练。就比如我需要基于yolov8n.pt上训练识别一个个性化的水管。然后训练出来的模型不仅仅要能识别水管还要能识别本身yoloV8n.pt就有的人、猫、杯子等。就是本身yolov8n.pt上的都不被抹除,应该怎么操作 |
Beta Was this translation helpful? Give feedback.
-
你好 我想使用他进行SAR舰船图像识别 请问该怎么弄啊 之前尝试了很多别的 都不太行 |
Beta Was this translation helpful? Give feedback.
-
您好 我想使用該程式進行畫面上多車體捕捉 該如何進行呢 |
Beta Was this translation helpful? Give feedback.
-
请问一下,我在pycharm里用git克隆了yolov8源码,还需要用pip install Ultralytics吗。如果不用的话,yolov8所需要的其他依赖怎么安装呢?在源码中我没找到requirement.txt文件。 |
Beta Was this translation helpful? Give feedback.
-
这是来自QQ邮箱的假期自动回复邮件。您好,我最近正在休假中,无法亲自回复您的邮件。我将在假期结束后,尽快给您回复。
|
Beta Was this translation helpful? Give feedback.
-
请问这错误如何解决? 路径没有错 数据结构: 代码: model = YOLO('yolov8m-cls.pt') datadir = r'C:\Users\name\Desktop\model\datasets' results = model.train(data=datadir, epochs=300, imgsz=64, batch=16, device=0, optimizer='Adam') 错误:TypeError Traceback (most recent call last) File c:\Users\name\AppData\Local\Programs\Python\Python311\Lib\site-packages\ultralytics\engine\model.py:655, in Model.train(self, trainer, **kwargs) File c:\Users\name\AppData\Local\Programs\Python\Python311\Lib\site-packages\ultralytics\engine\trainer.py:213, in BaseTrainer.train(self) File c:\Users\name\AppData\Local\Programs\Python\Python311\Lib\site-packages\ultralytics\engine\trainer.py:327, in BaseTrainer._do_train(self, world_size) File :323, in expanduser(path) TypeError: expected str, bytes or os.PathLike object, not NoneType |
Beta Was this translation helpful? Give feedback.
-
您好!在YOLOv8-obb的训练过程中,我没有找到yolov8-obb.yaml文件,请问官方是否有相关的yaml文件呢?或是说直接使用yolov8s.yaml即可呢?另外,在训练过程中,box_loss 在1左右, cls_loss在3.8左右,这是否正常,因为我之前在使用yolov5时,这两者的数据通常是比较小的,希望您能解答我的疑问! |
Beta Was this translation helpful? Give feedback.
-
您好,我在一次yolov8改进后的训练结果中,没有生成置信度曲线以及PR曲线。如何使用训练后的pth文件,产生置信度曲线等文件 |
Beta Was this translation helpful? Give feedback.
-
你好,我現在有個項目要判斷人是否有正確使用遮掩版來遮住左眼做視力檢查(須完全遮住左眼),若是這種應用,需要用detect還是pose檢測? |
Beta Was this translation helpful? Give feedback.
-
你好,在yolov8的训练中,我的数据集不划分验证集,也就是val,我应该怎么操作呢 |
Beta Was this translation helpful? Give feedback.
-
请问我在哪里可以下载yolov8的网络架构图呢? |
Beta Was this translation helpful? Give feedback.
-
请问我该怎么添加模块呢,然后又怎么调用? |
Beta Was this translation helpful? Give feedback.
-
我已经使用yolov10训练出来了一个模型,我现在想知道预测时该如何获取box和conf的信息,请问有详细指导么 |
Beta Was this translation helpful? Give feedback.
-
你好! 我想要用docker将本地的yolov8项目创建一个镜像,我应该如何编写dockerfile的内容呢 |
Beta Was this translation helpful? Give feedback.
-
你好,因为在预测阶段也就是predict时,RAM内存不够,所以我采用stream=True参数,但是我同时想要保存每一张图片的txt结果,应该如何实现 |
Beta Was this translation helpful? Give feedback.
-
你好,我们使用yolov8 使用自制数据集训练后,预测后的图片和视频目标框 与自己标注的框大小不同,请问有什么解决方法。 |
Beta Was this translation helpful? Give feedback.
-
ltralytics YOLOv8.2.48 🚀 Python-3.8.19 torch-2.3.1+cpu torch.cuda.is_available(): False |
Beta Was this translation helpful? Give feedback.
-
我尝试找到可以修改模型结构的脚本文件,按照你们在别人评论下的回复: |
Beta Was this translation helpful? Give feedback.
-
请问如果我需要使用自己训练出来的模型进行训练和测试该如何操作,因为我发现好像训练过程中的ckpt并没有保存,而最后的模型pt好像不能直接作为模型进行训练和测试,我希望能用我训练出来的模型单独进行测试,谢谢! |
Beta Was this translation helpful? Give feedback.
-
你好!yolov8对于小目标的检测有一些改进方法吗?同时,这些小目标是以旋转框的形式标注的,我注意到yolov8-p2.yaml以及yolov8-obb.pt,这两者可以进行混用吗,也就是说用p2的yaml,用obb的权重进行训练。 |
Beta Was this translation helpful? Give feedback.
-
zh
探索Ultralytics YOLOv8 的完整指南,这是一个高速、高精度的对象检测和图像分割模型。安装、预测、培训教程等。
https://docs.ultralytics.com/zh
Beta Was this translation helpful? Give feedback.
All reactions