-
Notifications
You must be signed in to change notification settings - Fork 10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error building MSMDFusion Dockerfile #34
Comments
Actually, we have not tried to install with this docker file. You can refer to getting_started.md and here for installation. |
Well I'm having issues with that installation guide as well. Specifically with trying to downloading the same mmdet3d version 0.10.0 as you. When trying to download mmdet3d with:
I get the following error message, note is only a piece of my error message.
Can you help me with this or is it possible to use later versions i.e 1.4.0? |
I found the problem to this issue above |
You can see previous questions. There are versions of libraries that author install with. And mmdet3d is installed with command |
Yes I saw that thank you. I have come a lot further but now have issues with:
What can I do to fix this error message? |
Have you prepocessed the nuscenes dataset? |
Yes my dataset follows this data preperation: MSMDFusion-main |
If you prepocess the dataset right, I think the error maybe is caused by different versions of mmcv, mmdet or mmdet3d. I suggest mmdet3d 0.11.0 that author used. |
This is my library version: mmcv-full 1.4.0 Hope it will be helpful. |
No I have followed @SxJyJay direction above so i have mmdet3d=0.11.0, mmdetection2.10.0 and mmcv-full=1.3.0
|
I have never met this error thus I don't know what the exact reason is, but I guess there is something wrong with the dataset. Did you use the entire 10 datasets to do the |
Hi thanks for helping me. Well my nuscenes data are around 600GB but my pkl files are only 1.5GB , is that reasonable? |
Describe the bug
Hi I was wondering if someone else had issues when building the docker, I get compatibility issues.
Reproduction
Yes I modified the MSMDFusion docker file. Added the follwoing in row 11 to fix earlier errors. I also specified mmcv-full to be 1.3.0 see below.
To fix GPG key error when running apt-get update
RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
---------------------------------------------------Now the docker file looks like this-------------------------------------------------------------------
I downloaded the nuscenes dataset.
python mmdet3d/utils/collect_env.py
to collect necessary environment infomation and paste it here:(open-mmlab) henrik@henrik-XPS-15-9510:
/mmdetection/mmdetection3d/mmdet3d/utils$ python collect_env.py22.04) 11.4.0sys.platform: linux
Python: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 3050 Ti Laptop GPU
CUDA_HOME: /home/henrik/miniconda3/envs/open-mmlab
NVCC: Cuda compilation tools, release 11.5, V11.5.119
GCC: gcc (Ubuntu 11.4.0-1ubuntu1
PyTorch: 2.0.0
PyTorch compiling details: PyTorch built with:
TorchVision: 0.15.0
OpenCV: 4.9.0
MMEngine: 0.10.3
MMDetection: 3.3.0
MMDetection3D: 1.4.0+fe25f7a
spconv2.0: False
3. You may add addition that may be helpful for locating the problem, such as
- How you installed PyTorch [e.g., pip, conda, source]
- Other environment variables that may be related (such as
$PATH
,$LD_LIBRARY_PATH
,$PYTHONPATH
, etc.)Error traceback
If applicable, paste the error trackback here.
Any help would be appreciated.
The text was updated successfully, but these errors were encountered: