Comments (3)
dendenxu
commented on July 19, 2024
Hi, @lixiangweiabc!
Looks like there are several issues to address:
- You've installed
pyopengl==3.1.0. If this is the modified version from EasyMocap's guide, it might not be compatible with easyvolcap. Maybe try updating it withpip install -U pyopengl. The latest version should be 3.1.7 - You mentioned that this is run through an X-server using a cloud server and it looks like you've already successfully created the opengl context. The options
ALPHA_TESTandPOINT_SPRITEwere not available in recent opengl version so you could just try commenting them out in the code and see if we can successfully render. This could be due to the fact that we're running through a remote X-server. I added a window hint to use the compatibility profile during window initialization, but it might have been ignored. - It's recommended to run EasyVolcap's viewer locally. Running through X-server might hit the performance pretty hard.
Moreover, could you please also test if you can run off-screen rendering by replacing -t gui with -t test?
from 4k4d.
lixiangweiabc
commented on July 19, 2024
Hi,thank you for your address.I had tried the cmd evc -t test -c configs/projects/realtime4dv/rendering/4k4d_actor5_6.yaml,configs/specs/video.yaml by replacing -t gui with -t test. I got the next error:
╭─────────────────────────────────────────────────── Traceback (most recent call last) ────────────────────────────────────────────────────╮
│ /root/miniconda3/bin/evc:5 in <module> │
│ │
│ 2 # -*- coding: utf-8 -*- │
│ 3 import re │
│ 4 import sys │
│ ❱ 5 from easyvolcap.scripts.main import main_entrypoint │
│ 6 if __name__ == '__main__': │
│ 7 │ sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) │
│ 8 │ sys.exit(main_entrypoint()) │
│ │
│ /data/shaenli/4K4D/easyvolcap/scripts/main.py:25 in <module> │
│ │
│ 22 │ from easyvolcap.runners.volumetric_video_runner import VolumetricVideoRunner │
│ 23 │ from easyvolcap.runners.volumetric_video_viewer import VolumetricVideoViewer │
│ 24 │
│ ❱ 25 from easyvolcap.utils.data_utils import DataSplit │
│ 26 from easyvolcap.utils.base_utils import dotdict │
│ 27 from easyvolcap.utils.dist_utils import synchronize, get_rank, get_distributed │
│ 28 from easyvolcap.utils.net_utils import setup_deterministic, number_of_params │
│ │
│ /data/shaenli/4K4D/easyvolcap/utils/data_utils.py:24 in <module> │
│ │
│ 21 from torch.utils.data._utils.collate import default_collate, default_convert │
│ 22 │
│ 23 from easyvolcap.utils.parallel_utils import parallel_execution │
│ ❱ 24 from easyvolcap.utils.net_utils import get_rigid_transform_nobatch as net_get_rigid_transform │
│ 25 from easyvolcap.utils.base_utils import dotdict │
│ 26 from easyvolcap.utils.console_utils import * │
│ 27 │
│ │
│ /data/shaenli/4K4D/easyvolcap/utils/net_utils.py:33 in <module> │
│ │
│ 30 │ from easyvolcap.models.networks.volumetric_video_network import VolumetricVideoNetwork │
│ 31 │ from easyvolcap.models.networks.multilevel_network import MultilevelNetwork │
│ 32 │
│ ❱ 33 cudart = torch.cuda.cudart() │
│ 34 │
│ 35 │
│ 36 def indices_to_coords(idx: torch.Tensor, H: int, W: int): │
│ │
│ /root/miniconda3/lib/python3.11/site-packages/torch/cuda/__init__.py:324 in cudart │
│ │
│ 321 │
│ 322 │
│ 323 def cudart(): │
│ ❱ 324 │ _lazy_init() │
│ 325 │ return _cudart │
│ 326 │
│ 327 │
│ │
│ /root/miniconda3/lib/python3.11/site-packages/torch/cuda/__init__.py:298 in _lazy_init │
│ │
│ 295 │ │ # are found or any other error occurs │
│ 296 │ │ if "CUDA_MODULE_LOADING" not in os.environ: │
│ 297 │ │ │ os.environ["CUDA_MODULE_LOADING"] = "LAZY" │
│ ❱ 298 │ │ torch._C._cuda_init() │
│ 299 │ │ # Some of the queued calls may reentrantly call _lazy_init(); │
│ 300 │ │ # we need to just return without initializing in that case. │
│ 301 │ │ # However, we must not let any *other* threads in! │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.
My nvidia driver version is :470.161.03, but my cuda version is:11.8. That might be incompatible. I will try a new machine with compatible nvidia driver and cuda. Could you please recommend a suitable Nvidia driver and cuda version on an ubuntu 18.04 machine.
from 4k4d.
dendenxu
commented on July 19, 2024
Indeed, looks like cuda 11.8 is not supported for the 470.161.03 driver. We usually run with 525.125.06 and CUDA 11.8.
from 4k4d.
Related Issues (20)
- Are there any plans to release missing files? HOT 2
- CUDA out of memory HOT 2
- About real-time rendering HOT 1
- Is there any plan to add the training code? HOT 2
- How to convert CamPose.inf to extri.yml? HOT 1
- An error occurred(Segmentation fault) while loading the model HOT 17
- Test view HOT 3
- Question about KPlanes result of DyNeRF dataset? HOT 4
- Questions about the mask loss in the paper HOT 3
- Minimal Dataset extract_images 解帧发绿 HOT 1
- Error during rendering HOT 12
- How to get a 3d object from a new video? HOT 5
- No mask directory in Mobile-stage dataset HOT 7
- EasyVolcap can't import xxx HOT 2
- Get in trouble with pytorch3d 's installing and tiny-cuda-nn 's compiling. HOT 2
- Can it render poses that have never appeared before? HOT 2
- Licensing HOT 4
- easyvolcap.utils.console_utils -> inner: Runtime exception: 'SuperChargedR4DV is not in the samplers registry' HOT 8
- Bad results than expected. HOT 10
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from 4k4d.