Comments (3)
Thanks for your question. We will update it to Readme doc.
Enable model services
Make sure you have installed NVIDIA Driver and NVIDIA Container Toolkit. But you do not need to install the CUDA Toolkit, as it already contained in the model image.
Set "default-runtime" as "nvidia" in /etc/docker/daemon.json and restart docker to enable NVIDIA Container Toolkit
{
"runtimes": {
"nvidia": {
"path": "nvidia-container-runtime",
"runtimeArgs": []
}
},
"default-runtime": "nvidia"
}
Need to explicitly specify model profile to enable model services.
docker compose --profile model up
from xtreme1.
Thanks for your question. We will update it to Readme doc.
Enable model services Make sure you have installed NVIDIA Driver and NVIDIA Container Toolkit. But you do not need to install the CUDA Toolkit, as it already contained in the model image.
Set "default-runtime" as "nvidia" in /etc/docker/daemon.json and restart docker to enable NVIDIA Container Toolkit
{ "runtimes": { "nvidia": { "path": "nvidia-container-runtime", "runtimeArgs": [] } }, "default-runtime": "nvidia" }Need to explicitly specify model profile to enable model services.
docker compose --profile model up
thanks for your help, I change the config and restart docker, but it doesn't work. and I check another docker image to check my docker enviroment, it success
(base) ➜ xtreme1 git:(main) docker run --rm -it --gpus all tensorrt-ubuntu18.04-cuda11.4 bash
To run a command as administrator (user "root"), use "sudo <command>".
See "man sudo_root" for details.
trtuser@f9bb9f074adb:/workspace$ python
Python 3.6.9 (default, Mar 15 2022, 13:55:28)
[GCC 8.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> torch.cuda.is_available()
True
>>> torch.Tensor().cuda()
tensor([], device='cuda:0')
but I check in the xtreme container it doesnt work,
(base) ➜ xtreme1 git:(main) docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
739269c3bdc4 basicai/xtreme1-point-cloud-object-detection "python app.py ../cb…" 20 hours ago Up 7 minutes 0.0.0.0:8293->5000/tcp, :::8293->5000/tcp
base) ➜ xtreme1 git:(main) docker exec -it 739269c3bdc4 /bin/bash
root@739269c3bdc4:/app/pcdet_open# python
Python 3.6.9 (default, Mar 15 2022, 13:55:28)
[GCC 8.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> torch.cuda.is_available()
False
>>> torch.Tensor().cuda()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python3.6/dist-packages/torch/cuda/__init__.py", line 214, in _lazy_init
torch._C._cuda_init()
RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
>>>
any suggestion about this?
from xtreme1.
fixed by #68
from xtreme1.
Related Issues (20)
- the default values for camera calibration HOT 2
- How to render a point cloud in a single image view HOT 4
- how to convert this calibration file? HOT 5
- Load Resource Error HOT 3
- Seeking Detailed Information on the Model Architecture and Weight File Used in Basic AI for AI-assisted Boxing (Cuboid) function HOT 3
- backend Dockerfile build error
- Version 0.9.1 installation HOT 4
- Do you have server side rendering as a feature ? HOT 1
- Pointcloud annotation question HOT 1
- how to configure for fisheye cameras HOT 3
- How to install for web? HOT 1
- How to auto-fit instances to next frame HOT 3
- How to copy and paste object to a different location in the same frame HOT 1
- Conversion of Camera Calibration Data HOT 1
- How to perform semantic segmentation tasks? HOT 2
- build front HOT 5
- To get 2D BBox in addition to 2D cuboids HOT 1
- is it possible to define more cameras HOT 1
- Excuse me, how to label lane line segmentation?
- The annoation tool is not showing up, indicating a "not logged in" message
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 xtreme1.