Differences

This shows you the differences between two versions of the page.

--- pipeline:window:cryolo:picking [2019/09/14 10:12]
twagner created
+++ pipeline:window:cryolo:picking [2019/09/18 12:45]
twagner
@@ Line 1: / Line 1: @@
-You can now use the model weights saved in ''model.h5'' (//if you come to this section from another point of the tutorial, this filename might be different like ''gmodel_phosnet_X_Y.h5''//) to pick all your images in the directory ''full_data''. To do this, run:
+Select the action "predict" and fill all arguments in the //"Required arguments"// tab:
-<code>
+{{ :pipeline:window:cryolo:cryolo_prediction.png?600 |}}
-cryolo_predict.py -c config.json -w model.h5 -i full_data/ -g 0 -o boxfiles/
-</code>
-You will find the picked particles in the directory ''boxfiles''.
+<note tip>
+**Adjusting confidence threshold**
-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:
+In crYOLO, all particles have an assigned confidence value. By default, all particles with a confidence value below 0.3 are discarded. If you want to pick less or more conservatively you might want to change this confidence threshold to a less (e.g. 0.2) or more (e.g. 0.4) conservative value 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>
+<html>
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
+<b>&#9658; Press the the [Start] button to run the prediction.  </b>
+</div>
+</html>
+You will find the picked particles in your specified output directory.
+<hidden **Alternative:** Run prediction from the command line>
+To pick all your images in the directory ''full_data'' with the  model weight file ''cryolo_model.h5'' (//e.g. or ''gmodel_phosnet_X_Y.h5'' when using the general model//) and and a confidence threshold of 0.3 run::
 <code>
-cryolo_predict.py -c config.json -w model.h5 -i full_data/ -g 0 -o boxfiles/ -t 0.2
+cryolo_predict.py -c config.json -w cryolo_model.h5 -i full_data/ -g 0 -o boxfiles/ -t 0.3
 </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
+You will find the picked particles in the directory ''boxfiles''.
+</hidden>

User Tools

Site Tools

Differences

Page Tools