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
cinderella_tomograms [2019/12/13 15:42]
twagner 		cinderella_tomograms [2019/12/13 16:13] (current)
twagner [Prediction]
Line 7: Line 7:
  
 === 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 specify all settings into one config file. To do so, create an empty file using
 <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 new 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>
Line 53: Line 54:
 </code> </code>
 The fields have the following meaning: The fields have the following meaning:
-  * **input_size**: This is the image size to which each central slice is resized to. +  * **input_size**: Each central slice is resized to these dimensions. 
-  * **batch_size**: How many images are in one mini-batch. If you have memory problems, you can try to reduce this value. +  * **batch_size**: The number of images in one mini-batch. If you have memory problems you can try to reduce this value. 
-  * **good_path**: Path to folder with good central slices.. +  * **good_path**: Path of folder containing good central slices. 
-  * **bad_path**: Path to folder with bad central slices.+  * **bad_path**: Path of folder containing bad central slices.
   * **pretrained_weights**: Path to weights that are used to initialize the network. It can be empty. As Cinderella is using the same network architecture as crYOLO, we are typically using the [[downloads:cryolo_1#general_phosaurusnet_models|general network of crYOLO]] as pretrained weights.   * **pretrained_weights**: Path to weights that are used to initialize the network. It can be empty. As Cinderella is using the same network architecture as crYOLO, we are typically using the [[downloads:cryolo_1#general_phosaurusnet_models|general network of crYOLO]] as pretrained weights.
-  * **saved_weights_name**: Final model filename+  * **saved_weights_name**: Final model filename.
   * **learning_rate**: Learning rate, should not be changed.   * **learning_rate**: Learning rate, should not be changed.
   * **nb_epoch**: Maximum number of epochs to train. However, it will stop earlier (see nb_early_stop).   * **nb_epoch**: Maximum number of epochs to train. However, it will stop earlier (see nb_early_stop).
Line 69: Line 70:
 </code> </code>
  
-This will train a classification network on the GPU with ID=1. After the training finishes, you get a ''my_model.h5'' file. This can then be used to classify subtomograms into good / bad categories.+This will train a classification network on the GPU with ID=1. Once the training finishes, you get a ''my_model.h5'' file. This can then be used to classify subtomograms into good / bad categories.
  
  
Line 81: Line 82:
 </code> </code>
  
-You will find two new mrcs files with the classified subtomograms. To check the results with e2display, you have to extract the central slices again (see [[cinderella_tomograms#extract_central_slices|Extract central slices]]).+In the output folder you will find two new mrcs files with the classified subtomograms. To check the results with e2display, you have to extract the central slices again (see [[cinderella_tomograms#extract_central_slices|Extract central slices]]).
  
  
  
cinderella_tomograms.1576248137.txt.gz · Last modified: 2019/12/13 15:42 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