User Tools

Site Tools


cinderella_tomograms

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
cinderella_tomograms [2019/12/13 15:17]
twagner [Training]
cinderella_tomograms [2019/12/13 15:52]
twagner
Line 4: Line 4:
  
 ==== Training ==== ==== Training ====
-To train cinderella we have to create training data. To do that, we extract the central slices from your tomogram (step 1) and select bad and good particles with eman2 e2display (step 2). In step 3 we train the actual model.+To train cinderella we have to create training data. To do that, we extract the central slices from your tomogram (step 1) and select bad and good particles using eman2 [[https://blake.bcm.edu/emanwiki/EMAN2/Programs/e2displaym|e2display]] (step 2). In step 3 we train the actual model using cinderella.
  
 === 1. Extract central slices === === 1. Extract central slices ===
 +To extract the central slices from e.g. my_subtomograms.hdf and to save it into sub_central.mrcs run:
 <code> <code>
 sp_cinderella_extract.py -i my_subtomograms.hdf -o sub_central.mrcs sp_cinderella_extract.py -i my_subtomograms.hdf -o sub_central.mrcs
Line 14: Line 15:
   - Start e2display from eman2 and select the central slice file (in our example ''sub_central.mrcs'').    - Start e2display from eman2 and select the central slice file (in our example ''sub_central.mrcs''). 
   - Press ►[Show Stack] to display the file.    - Press ►[Show Stack] to display the file. 
-  - Now click with the central mouse button (mouse wheel) on any particle. In new dialog press the button ►[Sets] and select the tab "Sets".  +  - Now click with the central mouse button (mouse wheel) on any particle. In the new dialog press the button ►[Sets] and select the tab "Sets".  
-  - There should be already a class "bad_particles". Create another class with and call it "good_particles". Highlight the set to which you want to add particle. +  - There should already be a class "bad_particles". Create a new class and name it "good_particles". Highlight the set to which you want to add particle. 
-  - If you now click on particles in the overview, they will be added to the current selected set. +  - If you now click on particles in the overview, they will be added to the currently selected set. 
-  - After you finished the selection, press ►[Save] for each selected class. You should save the classes into separate folders (e.g. ''good/'' and ''bad/''). Both folder can contain multiple files (e.g. examples from another tomogram).+  - After you finished the selection, press ►[Save] for each selected class. You should save the classes into separate folders (e.g. ''good/'' and ''bad/''). Both folders can contain multiple files (e.g. examples from another tomogram).
 {{ ::eman2_set_arrow.png?300 |}} {{ ::eman2_set_arrow.png?300 |}}
 <note question> <note question>
Line 27: Line 28:
 After your created your training data, you can start the training :-)  After your created your training data, you can start the training :-) 
  
-You need to specifiy all settings into one config file. To that, create an empty file with+You need to specifiy all settings into one config file. To do so, create an empty file with
 <code> <code>
 touch config.json touch config.json
 </code> </code>
  
-Copy the following configuration into it and adapt it for your needs. The only entries you might want to change is the input_size, good_path, bad_path and pretrained_weights.+Copy the following configuration into the file and adapt it to your needs. The only entries you might want to change are the //input_size////good_path////bad_path// and //pretrained_weights//.
  
 <code json config.json> <code json config.json>
cinderella_tomograms.txt · Last modified: 2019/12/13 16:13 by twagner