how can i solute it?

[Mrsunhaipeng]

Need your help!
(gaussian_splatting) PS E:\BaiduSyncdisk\Project\SparseGS-master> python train.py --source_path data/art --model_path output/art --beta 5.0 --lambda_pearson 0.05 --lambda_local_pearson 0.15 --box_p 128 --p_corr 0.5 --lambda_diffusion 0.001 --SDS_freq 0.1 --step_ratio 0.99 --lambda_reg 0.1 --prune_sched 20000 --prune_perc 0.98 --prune_exp 7.5 --iterations 30000 --checkpoint_iterations 30000 -r 2
Optimizing output/art
Output folder: output/art [18/09 11:05:08]
Tensorboard Found! [18/09 11:05:08]
Reading camera 43/43Loading Training Cameras [18/09 11:05:08]
Loading Test Cameras [18/09 11:05:13]
Number of points at initialisation : 5550 [18/09 11:05:13]
Training progress: 0%| | 0/30000 [00:00<?, ?it/s][20000] [18/09 11:05:13]
urllib3.exceptions.SSLError: [SSL: KRB5_S_TKT_NYV] unexpected eof while reading (_ssl.c:1091)

The above exception was the direct cause of the following exception:

urllib3.exceptions.ProxyError: ('Unable to connect to proxy', SSLError(SSLError(1, '[SSL: KRB5_S_TKT_NYV] unexpected eof while reading (_ssl.c:1091)')))

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "D:\miniconda3\envs\gaussian_splatting\lib\site-packages\requests\adapters.py", line 497, in send
chunked=chunked,
File "D:\miniconda3\envs\gaussian_splatting\lib\site-packages\urllib3\connectionpool.py", line 845, in urlopen
method, url, error=new_e, _pool=self, _stacktrace=sys.exc_info()[2]
File "D:\miniconda3\envs\gaussian_splatting\lib\site-packages\urllib3\util\retry.py", line 515, in increment
raise MaxRetryError(_pool, url, reason) from reason # type: ignore[arg-type]
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/stabilityai/stable-diffusion-2-1-base (Caused by ProxyError('Unable to connect to proxy', SSLError(SSLError(1, '[SSL: KRB5_S_TKT_NYV] unexpected eof while reading (_ssl.c:1091)'))))

During handling of the above exception, another exception occurred:

[Mrsunhaipeng]

maybe because i run it on windows?

[ForMyCat]

Looks like a huggingface error. Try to disable the SDS loss. On Sep 18, 2024, at 01:09, Mrsunhaipeng ***@***.***> wrote: maybe because i run it on windows? —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[Mrsunhaipeng]

I set lambda_diffusion=0,and it brings another issues.
(gaussian_splatting) (base) shp@shp-DL:~/Project/SparseGS-master$ python3 train.py --source_path data/art --model_path output/art --beta 5.0 --lambda_pearson 0.05 --lambda_local_pearson 0.15 --box_p 128 --p_corr 0.5 --lambda_diffusion 0 --SDS_freq 0 --step_ratio 1 --lambda_reg 0 --prune_sched 2000
0 --prune_perc 0.98 --prune_exp 7.5 --iterations 30000 --checkpoint_iterations 30000 -r 2
Optimizing output/art
Output folder: output/art [19/09 21:20:16]
Tensorboard not available: not logging progress [19/09 21:20:16]
Reading camera 43/43Loading Training Cameras [19/09 21:20:16]
Loading Test Cameras [19/09 21:20:17]
Number of points at initialisation : 5550 [19/09 21:20:17]
Training progress: 0%| | 0/30000 [00:00<?, ?it/s][20000] [19/09 21:20:17]
Traceback (most recent call last):
File "train.py", line 459, in
training(dataset, op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from, args.step, args.max_cameras, args.prune_sched)
File "train.py", line 135, in training
render_pkg = render(viewpoint_cam, gaussians, pipe, bg)
File "/home/shp/Project/SparseGS-master/gaussian_renderer/init.py", line 39, in render
ret_pts=ret_pts
TypeError: new() got an unexpected keyword argument 'beta'
Training progress: 0%| | 0/30000 [00:00<?, ?it/s]

[Mrsunhaipeng]

@ForMyCat

[ForMyCat]

Hi, did you install our softmax depth rasterizer? Please try "pip install submodules/diff-gaussian-rasterization-softmax".

…

On Thu, Sep 19, 2024 at 6:26 AM Mrsunhaipeng ***@***.***> wrote: I set lambda_diffusion=0,and it brings another issues. (gaussian_splatting) (base) ***@***.***:~/Project/SparseGS-master$ python3 train.py --source_path data/art --model_path output/art --beta 5.0 --lambda_pearson 0.05 --lambda_local_pearson 0.15 --box_p 128 --p_corr 0.5 --lambda_diffusion 0 --SDS_freq 0 --step_ratio 1 --lambda_reg 0 --prune_sched 2000 0 --prune_perc 0.98 --prune_exp 7.5 --iterations 30000 --checkpoint_iterations 30000 -r 2 Optimizing output/art Output folder: output/art [19/09 21:20:16] Tensorboard not available: not logging progress [19/09 21:20:16] Reading camera 43/43Loading Training Cameras [19/09 21:20:16] Loading Test Cameras [19/09 21:20:17] Number of points at initialisation : 5550 [19/09 21:20:17] Training progress: 0%| | 0/30000 [00:00<?, ?it/s][20000] [19/09 21:20:17] Traceback (most recent call last): File "train.py", line 459, in training(dataset, op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from, args.step, args.max_cameras, args.prune_sched) File "train.py", line 135, in training render_pkg = render(viewpoint_cam, gaussians, pipe, bg) File "/home/shp/Project/SparseGS-master/gaussian_renderer/*init*.py", line 39, in render ret_pts=ret_pts TypeError: *new*() got an unexpected keyword argument 'beta' Training progress: 0%| | 0/30000 [00:00<?, ?it/s] — Reply to this email directly, view it on GitHub <#23 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ALV4NNBIJQMRPQZM2VSEMCDZXLGJNAVCNFSM6AAAAABOMXORIKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNRQHE4DKOJUGQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[Mrsunhaipeng]

@ForMyCat ,Thanks you,I have successfully installed my environment.I rendered it,and got the files (depth,gt,modes,renders...), all i saw in renders is the png...What I want to know is how do I visualize it just like 3DGS? Or export the model or anything

[ForMyCat]

Please check the SIBR Viewer section from the original 3DGS codebase. You can visualize SparseGS the same way. On Sep 21, 2024, at 03:06, Mrsunhaipeng ***@***.***> wrote: @ForMyCat ,Thanks you,I have successfully installed my environment.I rendered it,and got the files (depth,gt,modes,renders...), all i saw in renders is the png...What I want to know is how do I visualize it just like 3DGS? Or export the model or anything —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you were mentioned.Message ID: ***@***.***>

[Mrsunhaipeng]

@ForMyCat Thank you for your answer, the most important thing now for the understanding of your model is the SDS, which I've now downloaded manually
stabilityai/stable-diffusion-2-1-base file, but it still seems to report errors, can you talk to me about how you use it? What directory should I put this in to use this? Appreciate it if you can let me know

[Mrsunhaipeng]

OSError: Cannot load model stabilityai/stable-diffusion-2-1-base: model is not cached locally and an error occurred while trying to fetch metadata from the Hub. Please check out the root cause in the stacktrace above.
Training progress: 0%| | 0/30000 [02:10<?, ?it/s]