CVHub

Yes, first of all, thank you very much for your feedback and suggestions. Regarding the issue you mentioned about the code overriding externally set labels, it is indeed due to...

@Morgott-The-Omen-King, Hello there! I'm thrilled to let you know that the most recent update has introduced support for custom labels and track IDs. Make sure to perform a `git pull`...

@cyj95, @AntyRia, here’s the code, try running this: ```python from dataclasses import field, dataclass from typing import Optional, Union, List import torch from PIL import Image from ovis.model.modeling_ovis import Ovis...

你好 @SUWEN-WEJI, 非常感谢你提交并详细报告了关于使用 X-AnyLabeling 导出 COCO 分割标签时，同一实例被遮挡成多个部分（使用同一组编号 Group ID 标记）却被错误导出为多个不同 COCO 实例的问题。 我们确认这是一个有效的 Bug，问题在于 COCO 导出逻辑未能正确处理具有相同组 ID 的多个分割区域。根据 COCO 数据集的标准，这些代表同一物理实例的不同视觉部分，理应被合并为 COCO annotations 中的**单个**标注条目，其 `segmentation` 字段应包含所有这些部分的信息（例如，一个包含多个多边形数组的列表）。 **好消息是，这个问题现在已经在最新的代码中修复了！** 更新后的 COCO 导出逻辑现在会正确地将你在 X-AnyLabeling...

Thank you for bringing this to our attention. @XushaopengHNU You're correct that purely numeric categories should be enclosed in quotes to prevent unintended conversion or parsing issues. For example, instead...

您好 @jazzlee008, 感谢反馈！你遇到的 `ImportError: DLL load failed while importing onnx_cpp2py_export` 错误通常是由于环境配置问题导致的。 请**不要将多个项目的环境混装到一起**。`onnxruntime-gpu` 对 CUDA 等版本有严格的兼容性要求，这些要求在我们的**[安装手册](https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/zh_cn/get_started.md)**中有明确说明。  建议你： 1. 使用 `miniconda` 或 `anaconda` **重新创建一个干净、独立的虚拟环境**。 2. 严格按照**[安装手册](https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/zh_cn/get_started.md)**中的指示进行安装，特别是选择与你的 CUDA 和 Python 版本兼容的 `onnxruntime-gpu`...

Hey there! @ticshen2019, You may refer to the following link for information on importing user-defined models: https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/zh_cn/custom_model.md This documentation offers comprehensive instructions and steps that should address your queries on...

Hi @kevalp-weboccult, Thanks for the suggestion and for your willingness to contribute a PR. Filtering images based on the classes they contain is typically considered a dataset management or pre-processing...

Hey there! @NickMortimer, Thanks for the suggestion! We'll consider adding this feature to improve the point removal workflow.

Hi @NickMortimer, Thanks again for the suggestion and for following up with that specific idea about using `Ctrl/Shift + click` to remove points within a set radius! That's an interesting...