2601705041

through this:https://kaolin.readthedocs.io/en/v0.10.0/notes/installation.html

same problem error: ('The size of tensor a (133) must match the size of tensor b (132) at non-singleton dimension 2',)

平台工具集全换成vs2019的会对项目有影响吗？

**i edit** @pip install --no-deps --install-opts="--boost-location=$$BOOST_INCLUDE_DIRS" --verbose --no-cache-dir **to** @pip install --no-deps --verbose --no-cache-dir . here is the problem (scan) j222@222:~/TotalSelfScan-main/mesh-master$ BOOST_INCLUDE_DIRS=/path/to/boost/include make all ----- [ mesh_package ] Installing with...

still no ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2024年4月15日(星期一) 中午1:46 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [MPI-IS/mesh] no such option: --install-option make: *** [Makefile:7：all] 错误 2 (Issue #99) Still an issue...

what's wrong with it? i just run the code in docker follow the Installation

and here is something might wrong with hydra-core print(hydra.utils.to_absolute_path('..')) ------> /home/j222/vid2avatar-main/code/.. i think it should be /home/j222/vid2avatar-main

well now i get a new environment (cuda 11.1) use this: pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html python train.py Traceback (most recent call last): File "train.py", line 1, in...

> > hi, how did you get textured mesh? > > infer.py add the codes: 708: final_colors=gen_mesh_color(verts_pr, model.netG, device, in_tensor) 716: final.visual.vertex_colors = final_colors My generated mesh is bad ,so...

相同的问题。 我在校园和室内房间两个场景都进行了训练，其中这张图片是室内房间训练的结果，可以看到在loss变小（about1.6）后会突然出现NaN 的行为，在校园大场景中同样会出现这个问题，只不过是在about9时就会出现。 同时关于配置问题，都遵循项目的处理与训练命令，用process_data.py 成功转换格式。对于房间数据集，scr-overlap-score --data data/aachen/train --max_depth 50，将max_depth 改为了5，其他遵循标准命令。