wch
/
brep2sdf
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
108 Commits
3 Branches
0 Tags
18 MiB
Tree: 58e000dad3
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '58e000dad3'
${ noResults }
Commit Graph

108 Commits (58e000dad336b594780728d35d409c48edf8054b)
 

Author SHA1 Message Date
mckay 58e000dad3 可以torch jit script
8 months ago
mckay f98c9ac227 可以训练，但是和torch jit还有一些兼容问题
8 months ago
mckay fa17441396 优化了八叉树并行，确保一个叶节点不超过两个面
8 months ago
mckay b89989bbc1 device相关优化，但是显存峰值问题还在
8 months ago
mckay 56efa123ec 暂时可用的ISG
8 months ago
mckay f0af2208a9 octree单独作为一个模块，且解决显存不足问题
8 months ago
mckay 595f24effa 显存不够，待优化
8 months ago
mckay 0d0f6ecfca ruff 清理包导入
8 months ago
mckay 2bb0864190 加入邻接图作为八叉树subdivide依据
8 months ago
mckay 8173bae5d5 loss删除无用代码
8 months ago
mckay e20686242f 优化八叉树encoder，使用long直接索引 特征向量
8 months ago
mckay 18b0ed99c8 拆分数据预处理
8 months ago
mckay 8466bd199c 更改ltorch 版本 2.6.0
8 months ago
mckay 6a1e871e7b 优化训练脚本
8 months ago
mckay 123e21a9af 增加c++ ISOsurfacing
8 months ago
mckay a3a2a2c7a1 增加非零表面采样点，优化batch train
8 months ago
mckay 98372f1717 优化八叉树性能
8 months ago
mckay 48755817c0 Revert "oct 修改中间版本"
8 months ago
mckay 5bd4a8d866 oct 修改中间版本
8 months ago
mckay 21f8369e20 兼容torch.jit.script，load和save方便。但是牺牲了随机访问，性能降了很多
8 months ago
mckay 2ac55ea3df 基本可以跑通，除了八叉树部分保存还有问题
8 months ago
mckay 26e3984f76 加强gen name list功能
8 months ago
mckay d5ac19e093 调c进行isosurfing
8 months ago
mckay cc88dfb798 支持normal
8 months ago
mckay 1e4c360403 可以加载和保存
9 months ago
mckay 32d4e45196 修改预处理
9 months ago
mckay a7541c9da3 优化写法，兼容 torch
9 months ago
mckay b33203a7e6 fix: logger
9 months ago
mckay 8fe07b2b3a gitignore 还有config 修改
9 months ago
mckay 845ad864b5 引入 NH-Rep 从 mesh 采样二面角的处理程序
9 months ago
mckay 2e8dc3b0fe 可以直接从 step 开始处理的版本
9 months ago
mckay 7f2049c4bd 加保存checkpoint
9 months ago
mckay 584354bbf7 能在八叉树上面训练，但是速度很慢
9 months ago
mckay cabc98090e BREAKPOINT: first attremp based on brepgen encoder and deepsef decoder
9 months ago
mckay 0b4df54447 feat: filter the data if their face_num or edge_num > max_face or max_edge.
1 year ago
mckay 4dddcdcd56 feat: diagnose script
1 year ago
mckay 7c97b82fdf feat: optimaize loss, by torch.norm and mead
1 year ago
mckay 66fa9fcc58 fix: zero_grad mv afterwards
1 year ago
mckay 86fb4c31e4 config: 修改
1 year ago
mckay e34d99a955 fix: loss 增加batch归一化
1 year ago
mckay 6c76b66fb4 config: change batch and epoch
1 year ago
mckay 0fa6a3ac3c fix: neg sdf too small, -> shape error
1 year ago
mckay 6d5c24c842 feat: script read npz
1 year ago
mckay de231aeb04 refactor: config
1 year ago
mckay bcc8ea8cf3 style: del log
1 year ago
mckay 03fa4012a4 feat: 统计brep数据
1 year ago
mckay f81ca6040e feat: SDF值分布log
1 year ago
mckay d9ecfbf4c7 style: 注释了不必要log
1 year ago
mckay 959dafc4b1 refctor: print_tensor_stats 移入log
1 year ago
mckay 41eb043d3f fix: 梯度改在train里面加
1 year ago