Likes - Activity - seneca_wolf - DeepTalk - Deep Learning Community

Low Disk Space on filesystem.root

I’m receiving the following warning on my TensorBook: “Low Disk Space on filesystem.root - The volume filesystem.root has only 77.3 Mb disk space remaining” The TensorBook (April 2022) is running Ubuntu 20.04.4 and Lambda Stack.

Pytorch and conda on Lambda Workstation RTX 3090

I do not see cuda-toolkit installed above. Remember Anaconda changes your search paths and ignores the system installed software. So either you would need to install the cuda-toolkit you want or set the PYTHONPATH to see the system installed software.

Pytorch has a handy tool to help with the …

There are other options also:

Pytorch has a nice example also, and you can specify the level of CUDA and pytorch. From: Start Locally | PyTorch For CUDA 11.3, linux, conda, python:

conda install pytorch torchvision torchaudio cudatool...

Lambda Stack and Nvidia Data Science Workbench

I would recommend setting up a separate root so you can back to a healthy image. I ended up cleaning up a lot after installing to get it back to normal. And I will likely just reinstall. (But note I have 3 boot devices and shared space). I will set up a clean Ubuntu root and test install Nvidia...

NVIDIA Data Science Workbench is writes all over the system replacing packages. The way it is written it is not directly compatible with any normal install, and can break usage not just for the user installing but for other users on system, also it does not isolate to a virtual environment, so it m…

Running apt-get autoremove

apt-get autoremove is almost always safe to run, especially on a single-user system where you know what software is installed. But, there are scenarios where running apt-get autoremove could cause problems, for example: if software you’ve installed, or someone else sharing the system installed, dep…

Checking installed packages

Just ask if you run into any issues. You can check with:

apt list --installed | grep lambda

CUDA compatibility issues

I encountered this error also. I found the reason is torch.version.cuda is 10.2. this is too old for 3090, I updated my torch to torch==1.8.1+cu111, and the error solved. You could create some env and by conda activate your_env_name, switch to a specific environment and pip there. maybe you co…

Anaconda and Lambda Stack Compatibility

Lambda stack and miniconda exist harmoniously. Miniconda gives one the ability to create virtual envs and utilize environment.yml files, but it doesn’t install all the base packages. So one can create an env, if one only has instructions for conda, then install packages using pip or conda. If you…

It’s not officially supported yet, it eventually will be. That said, I’ve heard rumors of people getting both to work side-by-side but haven’t tried myself.

TensorBook Issues

Dear all, I have just received my TensorBook, and I have experienced some issues:

I thank you in advance for your helpful advice.

Installation Experience

Hi! I was so relieved to find the one-liner install for Ubuntu Bionic desktop (6 core with RTX2070). Install without issues (a miracle in itself), so relieved to avoid the difficulties normally encountered when setting up a DL machine. In terminal I did it with one of my venv’s activated.

Found out myself, let this be as others might find it useful. Created a new user after installing the Lambda stack. Then all modules etc work. Great! I then installed Anaconda - and tensorflow etc were no longer available. Lesson: CAN’T INSTALL ANACONDA OVER LAMBDA STACK!
No great issue, but thi…