zh #8026
Replies: 140 comments 292 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.
-
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.
-
请问一下,量化best.onnx错误Ultralytics YOLOv8.2.90 🚀 Python-3.9.19 torch-2.4.0+cu121 CPU (Intel Core(TM) i5-10600KF 4.10GHz) PyTorch: starting from 'yolov8n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (6.2 MB) ONNX: starting export with onnx 1.16.0 opset 19... Export complete (1.7s) PyTorch: starting from 'yolov8n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (6.2 MB) ONNX: starting export with onnx 1.16.0 opset 19... Export complete (1.7s) PyTorch: starting from '/home/h/PycharmProjects/YOLOV8/ultralytics/runs/detect/train2/weights/best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 24, 8400) (6.0 MB) ONNX: starting export with onnx 1.16.0 opset 19... Export complete (1.7s) |
Beta Was this translation helpful? Give feedback.
-
如何通过推理得到的边界框坐标信息将目标对象从图片中裁剪出来呢? |
Beta Was this translation helpful? Give feedback.
-
现在遇到的问题是有一半标签被预测成背景,召回率0.5左右,map为0.67,现在有什么方法提高召回率,是否可以通过降低背景的权重,这个该怎么实现呢 |
Beta Was this translation helpful? Give feedback.
-
非常感谢您的回复,pos_weight = torch.FloatTensor([2.0, 2.0, 2.0, 2.0, 2.0, 2.0]) |
Beta Was this translation helpful? Give feedback.
-
我注意到在你们的trainer.py中有如下代码: |
Beta Was this translation helpful? Give feedback.
-
Please consult. When I trained my model under windows |
Beta Was this translation helpful? Give feedback.
-
我把yolov5和另一个车位检测网络做了拼接,实现多任务检测,同时检测车位和障碍物,但不知道训练的时候该用什么预训练权重? |
Beta Was this translation helpful? Give feedback.
-
您好,为什么写predict脚本。设置imgsz=640,推理的时候显示图片尺寸是640x480,预处理部分是能修改,那部分代码是在哪 |
Beta Was this translation helpful? Give feedback.
-
不知道
Van♂
***@***.***
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2024年10月17日(星期四) 下午4:19
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [ultralytics/ultralytics] zh (Discussion #8026)
您好,为什么写predict脚本。设置imgsz=640,推理的时候显示图片尺寸是640x480,记得预处理部分是能修改,那部分代码是在哪
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
推理结果不想显示被检测对象的概率如何操作呢 |
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.
-
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.
-
请问如何用独立显卡运行 |
Beta Was this translation helpful? Give feedback.
-
您的来信我已收到,谢谢。 王志向
|
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