Closed percypeng5221 closed 9 months ago
does your desktop have a display?
If not, you could also try without gui, by --use_gui 0
My desktop has a display. I may stick to using that cause I wanna test this algorithm in a big framework
can you provide more info (OS, GPU version, CUDA version)?
This is my output from nvidia-smi:
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.129.03 Driver Version: 535.129.03 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 4090 ... Off | 00000000:01:00.0 Off | N/A |
| N/A 57C P8 23W / 80W | 17MiB / 16376MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 1229 G /usr/lib/xorg/Xorg 4MiB |
| 0 N/A N/A 1982 G /usr/lib/xorg/Xorg 4MiB |
+---------------------------------------------------------------------------------------+
My system is Ubuntu 20.04.6 LTS focal. And this is my docker info:
Client: Docker Engine - Community
Version: 24.0.7
Context: default
Debug Mode: false
Plugins:
buildx: Docker Buildx (Docker Inc.)
Version: v0.11.2
Path: /usr/libexec/docker/cli-plugins/docker-buildx
compose: Docker Compose (Docker Inc.)
Version: v2.21.0
Path: /usr/libexec/docker/cli-plugins/docker-compose
Server:
Containers: 1
Running: 0
Paused: 0
Stopped: 1
Images: 1
Server Version: 24.0.7
Storage Driver: overlay2
Backing Filesystem: extfs
Supports d_type: true
Using metacopy: false
Native Overlay Diff: true
userxattr: false
Logging Driver: json-file
Cgroup Driver: cgroupfs
Cgroup Version: 1
Plugins:
Volume: local
Network: bridge host ipvlan macvlan null overlay
Log: awslogs fluentd gcplogs gelf journald json-file local logentries splunk syslog
Swarm: inactive
Runtimes: io.containerd.runc.v2 runc
Default Runtime: runc
Init Binary: docker-init
containerd version: 61f9fd88f79f081d64d6fa3bb1a0dc71ec870523
runc version: v1.1.9-0-gccaecfc
init version: de40ad0
Security Options:
apparmor
seccomp
Profile: builtin
Kernel Version: 5.15.0-88-generic
Operating System: Ubuntu 20.04.6 LTS
OSType: linux
Architecture: x86_64
CPUs: 32
Total Memory: 31.08GiB
Name: percyp
ID: 5d5306fc-c351-4573-9cb3-143edeb69e03
Docker Root Dir: /var/lib/docker
Debug Mode: false
Experimental: false
Insecure Registries:
127.0.0.0/8
Live Restore Enabled: false
I've never seen this issue before. If you dont use GUI, are you able to run? I know you need GUI, just curious.
log.txt Well, it seems that without GUI, the code can run. I've attached the output. But it seems like I don't have this package:
Process Process-2:
Traceback (most recent call last):
File "/opt/conda/envs/py38/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/opt/conda/envs/py38/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/percyp/BundleSDF/bundlesdf.py", line 219, in run_nerf
nerf = NerfRunner(cfg_nerf,rgbs,depths=depths,masks=masks,normal_maps=normal_maps,occ_masks=occ_masks,poses=poses,K=K,build_octree_pcd=pcd_normalized)
File "/home/percyp/BundleSDF/nerf_runner.py", line 156, in __init__
self.create_nerf()
File "/home/percyp/BundleSDF/nerf_runner.py", line 208, in create_nerf
embed_fn, input_ch = get_embedder(self.cfg['multires'], self.cfg, i=self.cfg['i_embed'], octree_m=self.octree_m)
File "/home/percyp/BundleSDF/nerf_helpers.py", line 207, in get_embedder
from mycuda.torch_ngp_grid_encoder.grid import GridEncoder
File "/home/percyp/BundleSDF/mycuda/torch_ngp_grid_encoder/grid.py", line 23, in <module>
import gridencoder
ModuleNotFoundError: No module named 'gridencoder'
I am also having the same issue when running without the GUI, how to get rid of that ?? @percypeng5221 @wenbowen123 were you able to solve the issue ?
[2023-11-25 09:44:51.998] [warning] [FeatureManager.cpp:1589] start multi pair ransac GPU, pairs#=1
[2023-11-25 09:44:51.999] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 0090 0089 #inliers=755, #prev 764
[bundlesdf.py] frame 0090 pose update before
[[ 0.992 0.113 -0.054 -0.039]
[-0.087 0.933 0.348 -0.251]
[ 0.089 -0.34 0.936 -0.421]
[ 0. 0. 0. 1. ]]
[2023-11-25 09:44:52.001] [warning] [FeatureManager.cpp:1095] procrustesByCorrespondence err per point between 0090 and 0089: 4.11612e-05
[bundlesdf.py] frame 0090 pose update after
[[ 0.99 0.124 -0.064 -0.035]
[-0.092 0.927 0.365 -0.258]
[ 0.105 -0.355 0.929 -0.418]
[ 0. 0. 0. 1. ]]
[2023-11-25 09:44:52.001] [warning] [Bundler.cpp:67] forgetting frame 0083
[2023-11-25 09:44:52.001] [warning] [FeatureManager.cpp:469] forgetting frame 0083
[bundlesdf.py] exceed window size, forget frame 0083
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:435] total keyframes=4, want to select 10
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:793] frame 0090 and 0000 visible=0.942166
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:802] add frame (0090, 0000) into pairs
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:793] frame 0090 and 0078 visible=0.941756
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:802] add frame (0090, 0078) into pairs
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:793] frame 0090 and 0082 visible=0.945857
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:802] add frame (0090, 0082) into pairs
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:793] frame 0090 and 0086 visible=0.945037
[2023-11-25 09:44:52.002] [warning] [Bundler.cpp:802] add frame (0090, 0086) into pairs
[bundlesdf.py] frame_pairs: 4
[loftr_wrapper.py] image0: torch.Size([4, 1, 400, 400])
[loftr_wrapper.py] net forward
[loftr_wrapper.py] mconf, 0.2003738433122635 0.998960018157959
[loftr_wrapper.py] pair_ids (2955,)
[loftr_wrapper.py] corres: (2955, 5)
[2023-11-25 09:44:52.222] [warning] [FeatureManager.cpp:1589] start multi pair ransac GPU, pairs#=4
[2023-11-25 09:44:52.232] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 0090 0000 #inliers=295, #prev 345
[2023-11-25 09:44:52.232] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 0090 0078 #inliers=442, #prev 487
[2023-11-25 09:44:52.232] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 0090 0082 #inliers=592, #prev 634
[2023-11-25 09:44:52.232] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 0090 0086 #inliers=709, #prev 739
#optimizeGPU frames=5, #keyframes=4, #_frames=10
0000 0078 0082 0086 0090
[2023-11-25 09:44:52.245] [warning] [Bundler.cpp:920] OptimizerGPU begin, global_corres#=5844
global_corres=5844
maxNumResiduals / maxNumberOfImages = 53844 / 5 = 10768
m_maxNumberOfImages*m_maxCorrPerImage = 5 x 2797 = 13985
m_solver->solve Time difference = 18.845[ms]
[2023-11-25 09:44:52.269] [warning] [Bundler.cpp:924] OptimizerGPU finish
[2023-11-25 09:44:52.269] [warning] [Bundler.cpp:320] Added frame 0090 as keyframe, current #keyframe: 5
[bundlesdf.py] processNewFrame done 0090
[bundlesdf.py] 0090 prepare data for nerf
[bundlesdf.py] out_dir: /home/arghya/BundleSDF/ho3d_v3_generated_mesh/MPM10//0090/nerf
[tool.py] compute_scene_bounds_worker start
[tool.py] compute_scene_bounds_worker done
[tool.py] merge pcd
[tool.py] compute_translation_scales done
translation_cvcam=[ 0.00559992 0.00377557 -0.0042612 ], sc_factor=16.757416592922073
[bundlesdf.py] First nerf run, create Runner, latest nerf frame 0090
[nerf_runner.py] Octree voxel dilate_radius:1
Process Process-2:
Traceback (most recent call last):
File "/opt/conda/envs/py38/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/opt/conda/envs/py38/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/arghya/BundleSDF/bundlesdf.py", line 219, in run_nerf
nerf = NerfRunner(cfg_nerf,rgbs,depths=depths,masks=masks,normal_maps=normal_maps,occ_masks=occ_masks,poses=poses,K=K,build_octree_pcd=pcd_normalized)
File "/home/arghya/BundleSDF/nerf_runner.py", line 156, in __init__
self.create_nerf()
File "/home/arghya/BundleSDF/nerf_runner.py", line 208, in create_nerf
embed_fn, input_ch = get_embedder(self.cfg['multires'], self.cfg, i=self.cfg['i_embed'], octree_m=self.octree_m)
File "/home/arghya/BundleSDF/nerf_helpers.py", line 207, in get_embedder
from mycuda.torch_ngp_grid_encoder.grid import GridEncoder
File "/home/arghya/BundleSDF/mycuda/torch_ngp_grid_encoder/grid.py", line 23, in <module>
import gridencoder
ModuleNotFoundError: No module named 'gridencoder'
I may choose another algorithm to do this task. It’s a little too much for my need based on my recent experience. I’m willing to help you guys solve this issue if you need me but later I might move on. @wenbowen123 @ArghyaChatterjee
BTW, I am also having issues with the GUI on, is there any solution to that one as well @wenbowen123 ??
(py38) root@arghya-Pulse-GL66-12UEK:/home/arghya/BundleSDF# python3 run_ho3d.py --use_gui 1
video_dirs:
['/home/arghya/BundleSDF/HO3D_v3/evaluation/MPM10']
[2023-11-25 10:28:24.403] [warning] [Bundler.cpp:49] Connected to nerf_port 9999
[2023-11-25 10:28:24.403] [warning] [FeatureManager.cpp:2084] Connected to port 5555
default_cfg {'backbone_type': 'ResNetFPN', 'resolution': (8, 2), 'fine_window_size': 5, 'fine_concat_coarse_feat': True, 'resnetfpn': {'initial_dim': 128, 'block_dims': [128, 196, 256]}, 'coarse': {'d_model': 256, 'd_ffn': 256, 'nhead': 8, 'layer_names': ['self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross'], 'attention': 'linear', 'temp_bug_fix': False}, 'match_coarse': {'thr': 0.2, 'border_rm': 2, 'match_type': 'dual_softmax', 'dsmax_temperature': 0.1, 'skh_iters': 3, 'skh_init_bin_score': 1.0, 'skh_prefilter': True, 'train_coarse_percent': 0.4, 'train_pad_num_gt_min': 200}, 'fine': {'d_model': 128, 'd_ffn': 128, 'nhead': 8, 'layer_names': ['self', 'cross'], 'attention': 'linear'}}
GUI started
libGL error: MESA-LOADER: failed to retrieve device information
Glfw Error 65543: GLX: Failed to create context: GLXBadFBConfig
python3: /home/runner/work/DearPyGui/DearPyGui/thirdparty/glfw/src/window.c:533: glfwSetWindowPos: Assertion `window != NULL' failed.
I am having the same issue "ModuleNotFoundError: No module named 'gridencoder'" as soon as there is a nerf run.
Any news?
Did you run bash build.sh
as mentioned in readme?
Yeah, I did
I am having the same issue "ModuleNotFoundError: No module named 'gridencoder'" as soon as there is a nerf run.
Any news?
Did you run
bash build.sh
as mentioned in readme?
this was the problem for me :/
I am having the same issue "ModuleNotFoundError: No module named 'gridencoder'" as soon as there is a nerf run. Any news?
Did you run
bash build.sh
as mentioned in readme?this was the problem for me :/
#################### just re-execute 'build.sh' indocker ################ I have encountered this issue sometimes, and its very strange that the 'build.sh' successed and the bundlesdf run coreactly. But if i exit the docker and rerun, it will happens. My solution is build again.
this is more about the docker usage, but if you dont kill the docker container you dont need rebuild. Otherwise you would need.
I also met the same problem when using GUI, but it works without using GUI. I have already running build.sh. Any suggestions? @wenbowen123
@cwchenwang what is the error using GUI?
I was running the run_custom.py file on the milk dataset. But the output is like this: