yinjunbo / is-fusion Goto Github PK

Issue Description:
Hi there, thank you for your exceptional code implementation. However, I've encountered an issue regarding the absence of the multi_scale_deformable_attn_function module within the middle encoders. This module should ideally include MultiScaleDeformableAttnFunction_fp32 and ms_deform_attn_core_pytorch, which are crucial for running and reproducing the performance reported in the article. This missing module significantly hampers the ability to achieve the expected results and needs to be addressed for effective utilization of the codebase.

May I ask how you visualize the point cloud and the detection result as shown in the framework?

Thank you!

Thank you for your excellent work. May I ask, when will the code be released?

快点发代码吧，同等分辨率条件下能超过focalFormer吗？我的BEVFixV3就指望您地代码了

Thank you very much for sharing your excellent work! I 'd like to record some implementation details.

1. Some files may be missing in mmdet3D/models.
   I've tried to supplement them with the files from the autoalignv2 project.

2. In mmdet3D/models./init.py, I had to delete line 20 (from .vtransforms import *) to make sure it can successfully run.

However, I still have some questions:

1. In the project, I can't find the Point-to-Grid Transformer module you've mentioned in your paper.
2. How can you get the checkpoint of the baseline Transfusion which can achieve 65.1mAP? Did you train it from scratch? The checkpoint (IS-Fusion_epoch_10.pth) you provided seems like final weights rather than a pre-trained model.

I'm sorry for taking up your time, and I hope to receive your reply.

Thank you for your work! What are the versions of libraries :mmseg, mmdet, mmcv in your code?

你好 @yinjunbo ！
请问我在配置环境时，完成pip install -v -e .这一步后，接下来是不是要用你当前github项目中的所有文件覆盖git clone中mmdetection3d中的文件？

can you provide code of TTA and model ensemble, thanks

你这个对比LSS提升了多少，我用的LSS比较low，你这个采用地站多少显存，24g的能跑吗

最后的的图像融合，点云和图像的梯度都打开的吗，采样 one -circle方式吗，训练6轮CBGS还是采样的10轮无CBGS，我就4卡的机器，能给点提示好吗。