为啥换成我自己的pt文件就会报错啊

您好，大佬您的代码写的很好，我有几个问题想问您。我看Mainwindow只开了一个线程，相当于视频播放和yolo预测放在一个线程去做吗，如果用cpu预测的话不能满足实时性要求，播放会很卡（我用的cv2读的视频），那我目前的思路是两个：就是分两个线程去做，一个用于播放，一个用于预测，但是信号emit的图片我不太确定怎么写，因为2张图片要叠一起，我的展示框只有1个。还有一个思路就是yolo1秒钟预测几帧就行，这样预测和播放写一个线程就行了。是不是可以用第二种哈哈哈。

我看大佬yolo线程中的run是这么写的
batch = next(self.dataset) # next data
print(batch)
self.batch = batch

                # path, im, im0s, vid_cap, s = batch
                path, im, vid_cap, im0s = batch

请问这个batch是干嘛的呢，不是cv2读了cap 就可以model预测了吗

python>=3.8
pip install ultralytics==8.0.48
pip install pyside6==6.4.2
python main.py

The problem still occurs when I try to figure out how to run the operation，What should I do

'NoneType' object has no attribute 'shape'

Hi,
You project is very good. I trained my model with the lastest ultralytics version - ultralytics-8.2.68. Since it's higher than your recommended version, I am not able to use your application. When I tried to upgrade ultralytics to 8.2.68, the app didnt start. Can you please tell me what changes do I need to make it to work with the latest version of ultralytics. Unfortunately, I cant retrain my model with the lower version of ultralytics now.

Thank you.
Atul

Hi, i can't find the folder with the saved elements. I think it isn't saving anything.

请问在定义YoloPredictor类的时候为什么不把他直接定义为进程类，而是在后续用moveToThread转成进程类，我在自己修改代码的过程中重新定义YoloPredictor类，但一涉及到继承多个父类（如QThread），就会报错RuntimeError: super-class init() of type YoloPredictor was never called，可是代码中已经有super(MainWindow, self).init()，为什么还会报这个错误

我是Ubuntu20.04的系统，
推理视频和图片都没有问题，但是推理不了网络摄像头。
我是用的无人机做的rmtp推流 ，不知道是不是rtmp和rtsp解析不一样

Doesn't work with my custom trained weight
Can anyone help me?

Error:

Ultralytics YOLOv8.0.48 Python-3.11.2 torch-2.0.1+cpu CPU
WARNING ./models/last.pt appears to require 'models.yolo', which is not in ultralytics requirements.
AutoInstall will run now for 'models.yolo' but this feature will be removed in the future.
Recommend fixes are to train a new model using the latest 'ultralytics' package or to run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'
requirements: YOLOv8 requirement "models.yolo" not found, attempting AutoUpdate...
ERROR: Could not find a version that satisfies the requirement models.yolo (from versions: none)
ERROR: No matching distribution found for models.yolo
No module named 'models.yolo'
requirements: Command 'pip install "models.yolo" ' returned non-zero exit status 1.

What does it mean?

作者你好，使用摄像头检测最后还是刷屏式的报了这个警告信息
[ WARN:[email protected]] global cap_msmf.cpp:1759 CvCapture_MSMF::grabFrame videoio(MSMF): can't grab frame. Error: -1072873821
然后就是只能检测摄像头的第一帧，然后就显示检测结束了，就和检测图片一样，上面的total class和fps之类的也不会变，请问还需修改哪里的代码

作者您好，感谢您提供的代码，我已经在我电脑上部署完成您的项目，运行main.py出现信息：进程已结束，退出代码为 -1073741819 (0xC0000005)，请问如何解决这个问题？另外，config文件需要修改吗？

clone后发现，当python版本低于3.8(我使用的是3.7),报ImportError: cannot import name ‘OrderedDict‘ from ‘typing‘错误。

解决方法：
maxvit.py中
将
from typing import Any, Callable, List, Optional, OrderedDict，Sequence, Tuple

变为

from typing import Any, Callable, List, Optional, Sequence, Tuple
from typing_extensions import OrderedDict

可以解决该问题。

C:\Users\yujunyu.conda\envs\pytorch\python.exe D:/PycharmProject(D)/CIFAR10-GUI/YOLOv8-PySide6-GUI-main/YOLOv8-PySide6-GUI-main/main.py
Traceback (most recent call last):
File "D:\PycharmProject(D)\CIFAR10-GUI\YOLOv8-PySide6-GUI-main\YOLOv8-PySide6-GUI-main\main.py", line 697, in
Home = MainWindow()
File "D:\PycharmProject(D)\CIFAR10-GUI\YOLOv8-PySide6-GUI-main\YOLOv8-PySide6-GUI-main\main.py", line 300, in init
super(MainWindow, self).init(parent)
TypeError: object.init() takes exactly one argument (the instance to initialize)

Process finished with exit code 1

i read the Read me file
is there any solution to this problem anytime soon?

requirements: YOLOv8 requirement "ultralytics.nn.modules.conv" not found, attempting AutoUpdate...
WARNING: The repository located at pypi.tuna.tsinghua.edu.cn is not a trusted or secure host and is being ignored. If this repository is available via HTTPS we recommend you use HTTPS instead, otherwise you may silence this warning and allow it anyway with '--trusted-host pypi.tuna.tsinghua.edu.cn'.
ERROR: Could not find a version that satisfies the requirement ultralytics.nn.modules.conv (from versions: none)
ERROR: No matching distribution found for ultralytics.nn.modules.conv
No module named 'ultralytics.nn.modules.conv'; 'ultralytics.nn.modules' is not a package
requirements: Command 'pip install "ultralytics.nn.modules.conv" ' returned non-zero exit status 1.

Is the function of instance segmentation not implemented yet? The image is not showing when I load the instance segmentation model.

not enough values to unpack

got

ValueError: not enough values to unpack (expected 4, got 1)

Realtime camera doesn't work. Anyone?

具体定位是在main.py里的 def write_results(self, idx, results, batch)