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
auto_2d_class_selection [2020/08/26 12:56]
twagner *
auto_2d_class_selection [2020/08/27 15:11]
twagner [Changelog]
Line 8: Line 8:
 ---- ----
  
-Our binary classification  tool (**Cinderella**) is based on a deep learning network to classify class averages, micrographs or subtomograms into good and bad categories. +Our binary classification  tool (//Cinderella//) is based on a deep learning network to classify class averages, micrographs or subtomograms into good and bad categories. 
-For class averages, it supports .hdf/.mrcsfor micrographs .mrc format and for subtomograms it expect that they are saved in a .hdf file+Cinderella supports ''.hdf/.mrcs'' ** files for class averages**, ''.mrc'' **files for micrographs**, and ''.hdf'' **files for subtomograms**
-Cinderella was written to automate cryo-em data processing.  It's open source and easy to use. +//Cinderella// was written to automate cryo-em data processing.  It's open source and easy to use. 
-We provide a pretrained general model for classifying class averages.([[auto2d_tutorial|see tutorial]]). But you can easily train it with your own set of classes/micrographs/subtomograms.+We provide a pretrained general model for classifying class averages ([[auto2d_tutorial|see tutorial]]). But you can easily train it with your own set of classesmicrographs, and/or subtomograms.
  
 <note> <note>
-  * **License**: MIT +  * **License**: [[https://github.com/MPI-Dortmund/sphire_classes_autoselect/blob/master/LICENSE|MIT]] 
-  * **GitHub repository**: https://github.com/MPI-Dortmund/sphire_classes_autoselect+  * **Repository**: [[https://github.com/MPI-Dortmund/sphire_classes_autoselect|GitHub]]
 </note> </note>
  
  
 ====== 2D class selection model ====== ====== 2D class selection model ======
-Our model was trained on a set of 2D classes from ISAC. During the creation of the training datasettried to ask myself "Which class would I select If I would not know the particle?" to decide which is a good class. Here are a couple of examples for good / bad classes in Cinderella: +Our model was trained on a set of 2D classes from both [[https://sphire.mpg.de/wiki/doku.php?id=pipeline:isac:sxisac2|ISAC]] and Relion. During the creation of the training data setwe tried to answer the question, "Which class would I select If I would not know the particle?" when deciding what is a "goodclass. Here are a couple of examples for good/bad classes in //Cinderella//
  
 {{ ::cinderellea.png?450 |}} {{ ::cinderellea.png?450 |}}
  
-<note important> +
-The training dataset does **not contain any Relion classes**, so it might be that Cinderella will not work with well them. +
-</note>+
 You can easily [[auto_2d_class_selection#contribute|contribute]] your own classes!   You can easily [[auto_2d_class_selection#contribute|contribute]] your own classes!  
  
-Right now our model is trained on **20 datasets**. But we will increase the number often!+Right now our model is trained on **4773 good classes and 5390 bad classes**.
 ====== Download ====== ====== Download ======
 ====Cinderella==== ====Cinderella====
-Version: 0.6.0+Version: 0.7.0
  
-Uploaded: 10March 2020+Uploaded: 27August 2020
  
 [[https://pypi.org/project/cinderella/#files|DOWNLOAD]] [[https://pypi.org/project/cinderella/#files|DOWNLOAD]]
  
 ====Pretrained model (2D classes)==== ====Pretrained model (2D classes)====
-Uploaded: 10March 2020, Datasets22+Uploaded: 27August 2020, Dataset4773 good classes and 5390 bad classes.
  
-[[ftp://ftp.gwdg.de/pub/misc/sphire/auto2d_models/gmodel_cinderella_20200310_N22.h5|DOWNLOAD]]+[[ftp://ftp.gwdg.de/pub/misc/sphire/auto2d_models/gmodel_cinderella07_202008_N10163.h5|DOWNLOAD]]
 ====Archive==== ====Archive====
-Old versions 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 0.7 === === Version 0.7 ===
-  * Now uses a circular masks by default. This allows to use full rotation during data augmentation. Can be deactivate by setting the mask radius to -1. +  * Now uses a **circular masks by default**. This allows to use full rotation during data augmentation. Can be deactivated by setting the field ''mask_radius'' in the configuration file to -1. In case you want to use an model trained with Cinderella < 0.7 please set the radius to -1. Otherwise you case specify any radius you want. **By default** (no ''mask_radius'' provided) it will use 0.4*''input_size''
-  * Fix numerical instability that occur when you have classes filled with a constant value (Thanks to Grigory Sharov). +  * The general models now includes **300 new good Relion classes and 2000 new bad Relion classes** (//Thanks to Takanori Nakane and Grigory Sharov//). 
-  * Fix a problem with classes that contain NaN values. They are now removed from the training data. (Thanks to Grigory Sharov).+  * Fixed numerical instability that occurs when you have classes filled with a constant value (//Thanks to Grigory Sharov//). 
 +  * Fixed a problem with classes that contain NaN values. NaN values are now replaced with 0. (//Thanks to Grigory Sharov//)
 +  * Fixed an issue when filenames contain more than one point.
  
 === Version 0.6 === === Version 0.6 ===
auto_2d_class_selection.txt · Last modified: 2020/08/27 15:11 by twagner