User Tools

Site Tools


pipeline:window:cryolo:picking

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
pipeline:window:cryolo:picking [2019/09/16 16:48]
twagner
pipeline:window:cryolo:picking [2019/09/17 08:19]
twagner
Line 1: Line 1:
 +Select the action prediction and fill all arguments in the //"Required arguments"// tab:
 +{{ :pipeline:window:cryolo:cryolo_prediction.png?600 |}}
 +
 +<note tip>
 +In crYOLO, all particles have a assigned confidence value. By default, all particle with confidence value below 0.3 are discarded. If you want to pick less conservatively or more conservatively you might want to change this confidence threshold to a less conservative value like 0.2 or more conservative value like 0.4 in the //"Optional arguments"// tab.
 +However, it is much easier to select the best threshold after picking using the ''CBOX'' files written by crYOLO as described in the next section.
 +</note>
 +
 +Press the the Start button to run the prediction. 
 +
 +<hidden **Run prediction from the command line**>
 You can now use the model weights file (//e.g. ''cryolo_model.h5'' in training from scratch or ''gmodel_phosnet_X_Y.h5'' when using the general model//) to pick all your images in the directory ''full_data''. To do this, run:  You can now use the model weights file (//e.g. ''cryolo_model.h5'' in training from scratch or ''gmodel_phosnet_X_Y.h5'' when using the general model//) to pick all your images in the directory ''full_data''. To do this, run: 
 <code> <code>
Line 6: Line 17:
 You will find the picked particles in the directory ''boxfiles''. You will find the picked particles in the directory ''boxfiles''.
  
-If you want to pick less conservatively or more conservatively you might want to change the selection threshold from the default of 0.3 to a less conservative value like 0.2 or more conservative value like 0.4 using the //-t// parameter: + 
-<code> +</hidden>
-cryolo_predict.py -c config.json -w cryolo_model.h5 -i full_data-g 0 -o boxfiles/ -t 0.2 +
-</code> +
-However, it is much easier to select the best threshold after picking using the ''CBOX'' files written by crYOLO as described in the next section+
pipeline/window/cryolo/picking.txt · Last modified: 2020/05/17 11:04 by twagner