PoinTr
PoinTr copied to clipboard
yuxumin
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
Currently the network is hardcoded to support _2048_ points as an input, can I get an advice how to update it to support _4096_ points as input? Right now with...
hi,我想知道在shapenet34和shapenet55数据集上，epoch多少时效果最好，我已经训练了200个epoch，还需要训练多少个epoch
Hi, I followed Issue #11 and made several attempts at training PoinTr on custom data: first for my own dataset (using PCN structure), then for a small subset of PCN...
Hi, I am trying to reproduce the results on the PCN dataset (i.e., Table 3 in the paper). While I was following the instructions for training GRNet, I got something...
Thank you for your great work, I'd like to know why you choose your threshold for F-score: 0.01.
I use following command to train pointTr ` bash ./scripts/train.sh 0 --config ./cfgs/KITTI_models/PoinTr.yaml --exp_name example`. The training speed is slow, I tried to reduce both the size of KITTI dataset,...
您好，我是一名这方面的小白，在尝试用自己制作的kitti数据集进行训练时出现了以下问题： /root/miniconda3/envs/a/lib/python3.7/site-packages/torch/optim/lr_scheduler.py:136: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`. Failure to do this will...
Thanks for your excellent work！ You mentioned in TPAMI paper that predicting the complete shape of objects in the foreground category goes in parallel with categorizing and determining the box,...
2 errors detected in the compilation of "gridding.cu". error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.6\\bin\\nvcc.exe' failed with exit code 1 这个问题要怎么解决呀，卡住了
I am currently working with the ShapeNet-55/34 datasets and would like to confirm which version of ShapeNetCore these datasets are based on. Specifically, I need to know whether they are...
