search

yanx27 / Pointnet_Pointnet2_pytorch

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
MIT License
3.51k stars 874 forks source link

no files in stanford_indoor3d #230

Open chenjing3340 opened 1 year ago

chenjing3340 commented 1 year ago

Train my own S3DIS dataset, no files are generated and errors are reported after running the code ‘Python collect_indoor3d_data.py’

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!! D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_3/Annotations D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_3/Annotations\close.txt D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_3/Annotations ERROR!! D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_4/Annotations D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_4/Annotations\close.txt D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_4/Annotations ERROR!! D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_5/Annotations D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_5/Annotations\close.txt D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_5/Annotations ERROR!!

swapnik-iitkgp commented 1 year ago

Same

wuwenxuan0226 commented 1 year ago

Window system has different folder separator. Your path has both / and \ Use Linux or WSL can solve your problem.

swapnik-iitkgp commented 1 year ago

I am using it in colab

On Wed, 12 Jul, 2023, 2:23 pm Wenxuan Wu, @.***> wrote:

win10 has different folder separator. Your path has both / and . Use Linux or WSL can solve your problem.

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1632112637, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X27MUKMPLEHM6FMUH4DXPZQY3ANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

wuwenxuan0226 commented 1 year ago

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!!

If your error is same, you can see the path has both / and \ which cause the path error.

swapnik-iitkgp commented 1 year ago

Ok, I'll check it out.

On Thu, 13 Jul, 2023, 11:47 am Wenxuan Wu, @.***> wrote:

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!!

If your error is same, you can see the path has both / and , which cause the path error.

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1633616634, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X2ZUBJWKCQQBUZ4TIOTXP6HHDANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

Also when I am training the model in Linux, it is getting struck again and again.

On Thu, 13 Jul, 2023, 11:48 am Swapnik Varala, @.***> wrote:

Ok, I'll check it out.

On Thu, 13 Jul, 2023, 11:47 am Wenxuan Wu, @.***> wrote:

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!!

If your error is same, you can see the path has both / and , which cause the path error.

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1633616634, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X2ZUBJWKCQQBUZ4TIOTXP6HHDANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

Can you please tell the solution if there is any

On Thu, 13 Jul, 2023, 10:53 pm Swapnik Varala, @.***> wrote:

Also when I am training the model in Linux, it is getting struck again and again.

On Thu, 13 Jul, 2023, 11:48 am Swapnik Varala, @.***> wrote:

Ok, I'll check it out.

On Thu, 13 Jul, 2023, 11:47 am Wenxuan Wu, @.***> wrote:

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!!

If your error is same, you can see the path has both / and , which cause the path error.

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1633616634, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X2ZUBJWKCQQBUZ4TIOTXP6HHDANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

Process killed by OOM killer

On Thu, 13 Jul, 2023, 10:53 pm Swapnik Varala, @.***> wrote:

Can you please tell the solution if there is any

On Thu, 13 Jul, 2023, 10:53 pm Swapnik Varala, @.***> wrote:

Also when I am training the model in Linux, it is getting struck again and again.

On Thu, 13 Jul, 2023, 11:48 am Swapnik Varala, @.***> wrote:

Ok, I'll check it out.

On Thu, 13 Jul, 2023, 11:47 am Wenxuan Wu, @.***> wrote:

D:\CCCCCCCC\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data/s3dis/Stanford3dDataset_v1.2/Area_8/cg9_2/Annotations ERROR!!

If your error is same, you can see the path has both / and , which cause the path error.

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1633616634, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X2ZUBJWKCQQBUZ4TIOTXP6HHDANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

wuwenxuan0226 commented 1 year ago

try ubuntu and reduce batch size

swapnik-iitkgp commented 1 year ago

Ok, I will try.

On Fri, 14 Jul, 2023, 3:10 am Wenxuan Wu, @.***> wrote:

try ubuntu and reduce batch size

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1634956513, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X23WNHBZF7VWX4VUSALXQBTMBANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

It is showing that it can't handle with larger numpy arrays.

On Fri, 14 Jul, 2023, 7:47 am Swapnik Varala, @.***> wrote:

Ok, I will try.

On Fri, 14 Jul, 2023, 3:10 am Wenxuan Wu, @.***> wrote:

try ubuntu and reduce batch size

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1634956513, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X23WNHBZF7VWX4VUSALXQBTMBANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

Facing memory leak error :(

On Fri, 14 Jul, 2023, 8:04 am Swapnik Varala, @.***> wrote:

It is showing that it can't handle with larger numpy arrays.

On Fri, 14 Jul, 2023, 7:47 am Swapnik Varala, @.***> wrote:

Ok, I will try.

On Fri, 14 Jul, 2023, 3:10 am Wenxuan Wu, @.***> wrote:

try ubuntu and reduce batch size

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1634956513, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X23WNHBZF7VWX4VUSALXQBTMBANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

swapnik-iitkgp commented 1 year ago

Also can I test my model without using CUDA.

On Fri, 14 Jul, 2023, 8:41 am Swapnik Varala, @.***> wrote:

Facing memory leak error :(

On Fri, 14 Jul, 2023, 8:04 am Swapnik Varala, @.***> wrote:

It is showing that it can't handle with larger numpy arrays.

On Fri, 14 Jul, 2023, 7:47 am Swapnik Varala, @.***> wrote:

Ok, I will try.

On Fri, 14 Jul, 2023, 3:10 am Wenxuan Wu, @.***> wrote:

try ubuntu and reduce batch size

— Reply to this email directly, view it on GitHub https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/230#issuecomment-1634956513, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXX2X23WNHBZF7VWX4VUSALXQBTMBANCNFSM6AAAAAAXY6I5IA . You are receiving this because you commented.Message ID: @.***>

wuwenxuan0226 commented 1 year ago

I think you can use author's env. And I think CPU torch is too slow.