Aviv Shamsian

Did you solve the problem? if not can you give more details? setup and what you tired so far?

can you share you validation/train loss graphs throughout training?

That is really strange since the last commit relates to this notebook was 15 months ago. I think the origin of this problem is google colab and not the repo....

Hi @haolanut, How are you? Currently, we do not have plans to release the generalization experiment. The first paragraph in Sec. 5.3 describes in detail how to train the hypernetwork...

as far as I can tell `high_reso_imgs` should be np array instead of list.

If you still won't able to solve this problem please drop here your email and I will reach out so you can send me your notebook.

I face the same issue it is a major problem when you run a script which takes several days to run using a server. Sometimes I didn't have a choice...

I did not see that they released config files based on OpenPCDet (can you please share the link?). If that is the case than you can close this issue and...

Hi @sshaoshuai, thank you for your quick response. Does this model use RGB+point clouds as its input? by looking at [the paper](https://arxiv.org/pdf/2012.15712.pdf) it seems it only uses point clouds as...

And what about the pipeline? what do I need to change in my config file in order to train this model in multimodal setup?