User Tools

Site Tools

auto_2d_class_selection

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Next revision Both sides next revision
auto_2d_class_selection [2019/07/29 14:48]
twagner [Changelog] 		auto_2d_class_selection [2019/12/10 09:47]
twagner [Changelog]
Line 1: Line 1:
-====== Cinderella: Automatic 2D class selection ======+====== Cinderella: Deep learning based 2D class and micrograph selection ======
  
 ---- ----
Line 9: Line 9:
  
  
-Our automatic 2d class selection tool (**Cinderella**) is based on a deep learning network to seperate 2D classes from .hdf / .mrcs files into good and bad classes. It uses the same deep neural network as crYOLO and was pretrained on a set good / bad classes. Cinderella was written to automate cryo-em data processing. It's open source and easy to use ([[auto2d_tutorial|see tutorial]]). You can easily train it with your own set of classes.+Our 2d class and micrograph selection tool (**Cinderella**) is based on a deep learning network to separate 2D classes or micrographs into good and bad.  
 +For 2D classes, it supports .hdf/.mrcs and for micrographs .mrc format.  
 +Cinderella provides a pretrained general model for classifying 2D classes and was written to automate cryo-em data processing. It's open source and easy to use ([[auto2d_tutorial|see tutorial]]). You can easily train it with your own set of classes/micrographs. 
 <note> <note>
   * **License**: MIT   * **License**: MIT
   * **GitHub repository**: https://github.com/MPI-Dortmund/sphire_classes_autoselect   * **GitHub repository**: https://github.com/MPI-Dortmund/sphire_classes_autoselect
 </note> </note>
 +
 Here are a couple of examples for good / bad classes in Cinderella:  Here are a couple of examples for good / bad classes in Cinderella: 
  
 {{ ::cinderellea.png?450 |}} {{ ::cinderellea.png?450 |}}
  
-====== The Model ======+====== 2D class selection model ======
 Our model was trained on a set of 2D classes from ISAC. During the creation of the training dataset, I tried to ask myself "Which class would I select If I would not know the particle?" to decide which is a good class. Our model was trained on a set of 2D classes from ISAC. During the creation of the training dataset, I tried to ask myself "Which class would I select If I would not know the particle?" to decide which is a good class.
 <note important> <note important>
Line 28: Line 32:
 ====== Download ====== ====== Download ======
 ====Cinderella==== ====Cinderella====
-Version: 0.3.1+Version: 0.4.0
  
-Uploaded: 29. July 2019+Uploaded: 10. December 2019
  
 [[https://pypi.org/project/cinderella/#files|DOWNLOAD]] [[https://pypi.org/project/cinderella/#files|DOWNLOAD]]
  
 ====Pretrained model==== ====Pretrained model====
-Uploaded: 11. July 2019, Datasets: 19+Uploaded: 10. December 2019, Datasets: 20
  
-[[ftp://ftp.gwdg.de/pub/misc/sphire/auto2d_models/model_cinderella_20190708.h5|DOWNLOAD]]+[[ftp://ftp.gwdg.de/pub/misc/sphire/auto2d_models/gmodel_cinderella_201912_N20.h5|DOWNLOAD]]
  
 [[auto2d_tutorial#classify|Valid configuration file]] [[auto2d_tutorial#classify|Valid configuration file]]
  
 ====Archive==== ====Archive====
-Old version of cinderella and the pretrained model can be found in the [[cinderella_archive|archive]]+Old versions of cinderella and the pretrained model can be found in the [[cinderella_archive|archive]]
  
 ====Changelog==== ====Changelog====
 +=== Version 0.4 ===
 +  * Balances unbalanced training datasets.
 +  * It is now possible to train Cinderella to select micrographs
 +  * Updated the general model for 2D class selection.
  
 === Version 0.3.1 === === Version 0.3.1 ===
Line 74: Line 82:
 After that, create a new virtual environment: After that, create a new virtual environment:
 <code> <code>
-conda create -n cinderella -c anaconda python=3.6 pyqt=5 cudnn=7.1.2+conda create -n cinderella -c anaconda python=3.6 pyqt=5 cudnn=7.1.2 numpy==1.14.5
 </code> </code>
  
Line 80: Line 88:
 <code> <code>
 source activate cinderella source activate cinderella
-</code> 
- 
-Install fast numpy: 
-<code> 
-conda install numpy==1.15.4 
 </code> </code>
  
Line 98: Line 101:
  
 ====== Tutorial ====== ====== Tutorial ======
-[[auto2d_tutorial|We created a tutorial how to use Cinderella!]]+We created two tutorials: 
 + 
 +  * [[auto2d_tutorial|How to use Cinderella for 2D class selection]] 
 +  * [[cinderella_micrographs|How to use Cinderella for micrograph selection]] 
 + 
auto_2d_class_selection.txt · Last modified: 2020/08/27 15:11 by twagner

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: GNU Free Documentation License 1.3
GNU Free Documentation License 1.3 Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki