Skip to content

Commit

Permalink
Merge pull request #111 from MPI-Dortmund/fix-install-problem
Browse files Browse the repository at this point in the history
Update cuml and pandas
  • Loading branch information
thorstenwagner authored Oct 2, 2024
2 parents 12d6323 + c2ba565 commit c96b92e
Show file tree
Hide file tree
Showing 6 changed files with 10 additions and 8 deletions.
4 changes: 2 additions & 2 deletions conda_env_tomotwin.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,12 @@ channels:
dependencies:
- pytorch[version='>=2.1']
- torchvision
- pandas[version='<2']
- pandas
- scipy
- numpy
- matplotlib
- pytables
- cuml=23.12
- cuml=24.08
- cuda-version=11.8
- protobuf[version='>3.20']
- tensorboard
Expand Down
1 change: 1 addition & 0 deletions docs/requirements.txt
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
sphinx<7
sphinx-prompt
sphinx-rtd-theme
sphinxcontrib-youtube
Expand Down
4 changes: 2 additions & 2 deletions docs/tutorials/text_modules/downscale_clustering.rst
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
.. include:: text_modules/downscale/first_paragraph.rst
.. include:: downscale/first_paragraph.rst


TomoTwin should be used to pick on tomograms without denoising or lowpass filtering. But you may use these tomograms for visualizing the picks in Napari. In this case, you should make sure the denoised/lowpass filtered tomogram has the same pixel size as the one you will pick on (downscaling it if necessary).

.. include:: text_modules/downscale/boxsize_admonition.rst
.. include:: downscale/boxsize_admonition.rst
4 changes: 2 additions & 2 deletions docs/tutorials/text_modules/downscale_reference.rst
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
.. include:: text_modules/downscale/first_paragraph.rst
.. include:: downscale/first_paragraph.rst

TomoTwin should be used to pick on tomograms without denoising or lowpass filtering. But you may use these tomograms to find the coordinates of your particle of interest for use as a reference. In this case, you should make sure the denoised/lowpass filtered tomogram has the same pixel size as the one you will pick on.

.. include:: text_modules/downscale/boxsize_admonition.rst
.. include:: downscale/boxsize_admonition.rst
3 changes: 2 additions & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,8 @@
"scikit-learn",
"scikit-image",
"pystardb>=0.4.2",
"pandas <= 2", # Because rapids does not support pandas > 1.5.3
"pandas", # Because rapids does not support pandas > 1.5.3
"numexpr>=2.8.4",
# "pytorch-metric-learning<1.7",
"numba",
"tabulate",
Expand Down
2 changes: 1 addition & 1 deletion tomotwin/embed_main.py
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ def get_window_size(model_path: str) -> int:
:return: Window size
'''

checkpoint = torch.load(model_path)
checkpoint = torch.load(model_path, weights_only=False)
if "window_size" in checkpoint["tomotwin_config"]:
return int(checkpoint["tomotwin_config"]["window_size"][0])
print("Can't find window size in model. Use window size of 37.")
Expand Down

0 comments on commit c96b92e

Please sign in to comment.