search

SxJyJay / MSMDFusion

[CVPR 2023] MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection
Apache License 2.0
181 stars 11 forks source link

about generation of virtual points samples #10

Open jiumozhi123 opened 1 year ago

jiumozhi123 commented 1 year ago

In README.md, virtual points samples is mentioned. And the virtual points samples is saved in Baidu cloud storage.

**Step 2**: Download preprocessed [virtual points samples](https://pan.baidu.com/s/1IxqcGxNCFnmSZw7Dlu3Xig?pwd=9xcb)(extraction code: 9xcb) and [sweeps](https://pan.baidu.com/s/1qUeopFHCWrr35af2MGBSnw?pwd=2eg1)(extraction code: 2eg1) data. And put them under the above folder ```samples``` and ```sweeps```, respectively, and rename them as ```FOREGROUND_MIXED_6NN_WITH_DEPTH```.

What I want to know is, how to get virtual points samples by code? Thanks!

SxJyJay commented 1 year ago

We modify the MVP to generate our virtual points. Since I am busy with another ddl, I don't have much time to clean the related code.

KaidongLi commented 9 months ago

Hi @SxJyJay great work! I'm wondering if you have the time to clean the related code, and do you plan to release it? If you don't have time, could you share an un-cleaned version? It would be really helpful. Thank you!

Libraaer commented 3 weeks ago

In README.md, virtual points samples is mentioned. And the virtual points samples is saved in Baidu cloud storage.

**Step 2**: Download preprocessed [virtual points samples](https://pan.baidu.com/s/1IxqcGxNCFnmSZw7Dlu3Xig?pwd=9xcb)(extraction code: 9xcb) and [sweeps](https://pan.baidu.com/s/1qUeopFHCWrr35af2MGBSnw?pwd=2eg1)(extraction code: 2eg1) data. And put them under the above folder ```samples``` and ```sweeps```, respectively, and rename them as ```FOREGROUND_MIXED_6NN_WITH_DEPTH```.

What I want to know is, how to get virtual points samples by code? Thanks!

Hello, have you trained this model? I'm using A800 here but still not enough to train. If you've trained, can you give me an answer to the reason for my lack of memory here, thank you

Libraaer commented 3 weeks ago

Hi @SxJyJay great work! I'm wondering if you have the time to clean the related code, and do you plan to release it? If you don't have time, could you share an un-cleaned version? It would be really helpful. Thank you!

Hello, have you trained this model? I'm using A800 here but still not enough to train. If you've trained, can you give me an answer to the reason for my lack of memory here, thank you

KaidongLi commented 3 weeks ago

Hi @SxJyJay great work! I'm wondering if you have the time to clean the related code, and do you plan to release it? If you don't have time, could you share an un-cleaned version? It would be really helpful. Thank you!

Hello, have you trained this model? I'm using A800 here but still not enough to train. If you've trained, can you give me an answer to the reason for my lack of memory here, thank you

Hey I have run the model on smaller GPUs, titan xp with 12gb of memory. I kept the batch size samples_per_gpu=2.