hm123450

Krnl.global and Krnl.entry_point() to llvm

1

Hi: I now have an MLIR file "add.onnx.mlir" that consists of both the affine dialect and the krnl dialect as a result of lowering. I am aware that I can...

Output generic format

3

Hi, Thank you so much to the development team for creating the MLIR compilation for ONNX. It is truly an amazing work! Now, I have a question: MLIR tools usually...

Check failed: ExistsDir(*image_path)

11

Hi: I have a video file that is about ten seconds long. After splitting it using ffmpeg, I'm trying to use convert.py, but I keep getting errors related to the...

如何获得分割出来的三维模型的bbox位置

1

hello，hello，我又来了，我想问一下我应该如何获得分割出来的三维模型的bbox位置以及大小呢，就如下图所需要的中心点的位置，以及长度 

一些关于数据集的问题：数据集链接以及自己如何创建数据

4

首先真的非常感谢你们的工作，这对我自己的一些研究实验很有帮助。 我现在是遇到一些问题，首先就是nerf_llff_data的google drive的链接点进去之后显示我没有权限获取数据。

如果其他的依赖项都已经安装好了，怎么直接安装xtuner

1

各位朋友我想问一下。就是因为内网服务器没有网的问题，我需要打包一个外网安装好的有xtuner的docker容器迁移到内网服务器上。 我外网的环境中，xtuner是通过源码安装的，但是迁移到内网服务器的时候，镜像中就没有xtuner了？ `widgetsnbextension 4.0.13 pypi_0 pypi xxhash 3.5.0 pypi_0 pypi xz 5.4.6 h5eee18b_1 yapf 0.43.0 pypi_0 pypi yarl 1.17.2 pypi_0 pypi zlib 1.2.13 h5eee18b_1 ` 我想问一下，这是怎么回事呀？以及，虽然没有xtuner但是我其他的依赖包都还在，我该怎么直接安装xtuner呢？

Some problem with OmDetTurboProcessor.post_process_grounded_object_detection()

2

I followed your official code [https://huggingface.co/docs/transformers/main/en/model_doc/omdet-turbo]() and my transform is 4.48. I got error like this : `TypeError: OmDetTurboProcessor.post_process_grounded_object_detection() got an unexpected keyword argument 'threshold'` I don't understand what happened...

Is the existing code sufficient to handle the task?

1

Hello, I noticed from the readme that you haven't uploaded the complete code yet. I would like to ask, as I already have a complete 3D scene graph as well...

On the effectiveness of the NaFlex variant for high-resolution images

1

Dear Developers, Your work on SigLIP2 is truly impressive. As a beginner, I would like to ask: can the NaFlex version of SigLIP handle images larger than 512×512, for example...