This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
auto_2d_class_selection [2019/12/16 10:38] twagner [Changelog] |
auto_2d_class_selection [2020/03/10 11:28] twagner [Changelog] |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== Cinderella: Deep learning based 2D class and micrograph selection | + | ====== Cinderella: Deep learning based binary classification tool ====== |
---- | ---- | ||
Line 8: | Line 8: | ||
---- | ---- | ||
- | + | Our binary classification | |
- | Our 2d class and micrograph selection | + | For class averages, it supports .hdf/.mrcs, for micrographs .mrc format |
- | For 2D classes, it supports .hdf/ | + | Cinderella was written to automate cryo-em data processing. |
- | Cinderella | + | We provide a pretrained general model for classifying class averages.([[auto2d_tutorial|see tutorial]]). |
< | < | ||
Line 18: | Line 18: | ||
</ | </ | ||
- | Here are a couple of examples for good / bad classes in Cinderella: | + | |
+ | ====== 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?" | ||
{{ :: | {{ :: | ||
- | ====== 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?" | ||
<note important> | <note important> | ||
The training dataset does **not contain any Relion classes**, so it might be that Cinderella will not work with well them. | The training dataset does **not contain any Relion classes**, so it might be that Cinderella will not work with well them. | ||
Line 29: | Line 29: | ||
You can easily [[auto_2d_class_selection# | You can easily [[auto_2d_class_selection# | ||
- | Right now our model is trained on **19 datasets**. But we will increase the number often! | + | Right now our model is trained on **20 datasets**. But we will increase the number often! |
====== Download ====== | ====== Download ====== | ||
====Cinderella==== | ====Cinderella==== | ||
Line 49: | Line 49: | ||
====Changelog==== | ====Changelog==== | ||
+ | |||
+ | === Version 0.6 === | ||
+ | * Fix an issue for classes in mrcs format | ||
+ | * Minor changes | ||
=== Version 0.5 === | === Version 0.5 === | ||
Line 106: | Line 110: | ||
====== Tutorial ====== | ====== Tutorial ====== | ||
- | We created | + | We created |
* [[auto2d_tutorial|How to use Cinderella for 2D class selection]] | * [[auto2d_tutorial|How to use Cinderella for 2D class selection]] |