Qixing Jiang

About image resize with intrinsics in config.

2

Thank you for your contribution to the community through your work! But I have some doubts about the code in config: HFT/configs/pyva/pyva_swin_kd_simple_fpn_force_nuscenes.py https://github.com/JiayuZou2020/HFT/blob/c4d06714e302e9f659635d0254e0dcf63089c257/HFT/configs/pyva/pyva_swin_kd_simple_fpn_force_nuscenes.py#L49-L50 These configurations resize the images of nuScenes...

hi，作者您好。 首先很感谢您在本领域做出的贡献，尤其是提供了DeepPCB这个数据集。 我是一名哈工大的研究生，想在您的工作基础上进行改进，未来也会引用您的论文。 请问代码能否公开？如果不方便的话，我想问问如何修改现有的目标检测算法，使其能够处理输入为成对图片（目前主流的目标检测算法输入都是单张图片，无法用到PCB模板图），输出为检测结果？希望您能给我一点启发，万分感谢~如果方便的话，或许能加您联系方式进一步交流？

What is {:06} means

1

Thank you for your outstanding contribution to community! I noticed that in main.py, line 621: "filename": "{epoch:06}-{step:09}", and line 553: "filename": "{epoch:06}", I wonder if it's missing "format", or what...

A harmless mistake

As I know, currently there is no model category for Qwen2_5VLChat, only Qwen2VLChat. In _config.py_, the Qwen2.5VL series models also use Qwen2VLChat, but there are structural differences between the two...