tomotwin-cryoet

tomotwin-cryoet copied to clipboard

environment creation command in docs doesn't work

2

`mamba env create -n tomotwin -f https://raw.githubusercontent.com/MPI-Dortmund/tomotwin-cryoet/main/conda_env_tomotwin.yml` -> ```txt error libmamba YAML spec file 'https:/raw.githubusercontent.com/MPI-Dortmund/tomotwin-cryoet/main/conda_env_tomotwin.yml' not found critical libmamba File not found. Aborting. ```

alisterburt

Issue with environment creation

1

just FYI, having some problems with env creation ```txt micromamba env create -n tomotwin -f conda_env_tomotwin.yml nvidia/noarch (check zst) Checked 0.1s pytorch/noarch (check zst) Checked 0.1s pytorch/linux-64 (check zst) Checked...

alisterburt

thorstenwagner

With the upcoming napari-tomotwin, the clustering workflow becomes more streamlined and powerful. This needs to be reflected in the documentation before I can release it. Some points that needs to...

thorstenwagner

During training, I do three independent forward passes through the network for the anchors, the positive and the negative volumes respectively (see https://github.com/MPI-Dortmund/tomotwin-cryoet/blob/2f12e793a6800dd58fe09573b75b801e26830b91/tomotwin/modules/training/torchtrainer.py#L626). It is probably more efficient to concatenate...

thorstenwagner

About Model Training and Loss Function

3

Dear Thorsten, I have been using your provided dataset and configuration scripts for training, and I've achieved an F1 score of 0.90 after 300 epochs, which is even higher than...

JachyLikeCoding

Label mask is not specificed

11

Dear Devs, I am using tomotwin as part of napari 0.4.18. I am running in clustering mode. The pixel size of my tomogram is 11.06, note that I did try...

DrJesseHansen

In issue #58 @azazellochg run into an issue that ldconfig was not in the path. This also happend on some other machines for me as well: https://discuss.pytorch.org/t/dynamo-exceptions-with-distributeddataprallel-compile/186768/3 We should add...

thorstenwagner

This can be in particular useful when using the clustering mode.

thorstenwagner

This would allow multi gpu estimation of umaps. https://docs.rapids.ai/api/cuml/stable/api/#cuml.dask.manifold.UMAP

thorstenwagner