HaoxiangChen
HaoxiangChen
@anita94 How did you align point clouds? Could you please share your code if possible? Thanks a lot.
@zhangchuanyi96 Hello, I 'm trying to reproduce the results following the command in ReadMe: ''' python train_mvs_nerf_pl.py --with_depth --imgScale_test 1.0 --expname mvs-nerf --num_epochs 6 --N_samples 128 --use_viewdirs --batch_size 1 --dataset_name...
Thank you for your reply! However ,when I switch GCC to 7.5.0 and torch 1.8.1 with cuda 10.2,it comes another problem ``` [18/21] /usr/local/cuda-10.2/bin/nvcc --generate-dependencies-with-compile --dependency-output /tmp/pip-install-i3mzudkc/minkowskiengine_9a929f3efb904c95b40a0041ec1260e6/build/temp.linux-x86_64-3.6/tmp/pip-install-i3mzudkc/minkowskiengine_9a929f3efb904c95b40a0041ec1260e6/src/spmm.o.d -I/home/chx/pyenv/torchenv/lib/python3.6/site-packages/torch/include -I/home/chx/pyenv/torchenv/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/home/chx/pyenv/torchenv/lib/python3.6/site-packages/torch/include/TH...
I get the lateset version and the second problem disappeared ,but the first one still exists.
I've add some explaination of each folder used in each python file. Hope it helps.
`scene_dirs = scene_dirs[:1] ` is just for debug, you can delete it and crop_small.py will process all the scenes. And it's fine that sample_matterport.py produce some empty regions.