Closed rdrighetto closed 10 months ago
I believe I've found the source of the issue. We create a torch DataLoader from the PatchDataset, but that dataset returns numpy arrays and not torch tensors. Working on a quick fix now.
This actually doesn't appear to be an issue with later versions of pytorch (1.13.1) and numpy (1.24.3). Also, when I try to install those in a new environment, conda tells me that your numpy version is too low for your pytorch version.
Could you update numpy (and pytorch if that doesn't work) and try it again?
OK, the issue was that I was using python=3.6
(as per the installation instructions). When switching to python=3.8
I managed to get the newer versions of pytorch
and numpy
among other things. Also the GPU versions of pytorch
libraries, which somehow were not installed before. In summary, this is what did the trick:
mamba remove torchaudio
mamba install python==3.8
mamba install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
mamba install topaz -c tbepler -c pytorch
Thank you!
Hi, I'm trying to run
topaz denoise3d
for the first time and getting the following error:And here is the MRC file header:
I'm on CentOS 7.9.2 trying to run it on NVIDIA A40 GPUs. Please find below my conda environment:
Any ideas how to fix this?
Thank you!