User Tools

Site Tools


pipeline:window:cryolo:issues

Differences

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

Link to this comparison view

Next revision
Previous revision
pipeline:window:cryolo:issues [2020/02/13 13:59]
twagner created
pipeline:window:cryolo:issues [2020/03/18 07:43]
twagner
Line 5: Line 5:
   * Issue 0: Training on multiple GPUs sometimes lead to worse performance (higher loss). We currently recommend to train on single gpus.   * Issue 0: Training on multiple GPUs sometimes lead to worse performance (higher loss). We currently recommend to train on single gpus.
   * Issue 17: On the fly filtering (%%--%%otf) is slower than using it not, as the filtering is not parallelized in this case.    * Issue 17: On the fly filtering (%%--%%otf) is slower than using it not, as the filtering is not parallelized in this case. 
-  * Issue 27: Filament mode is not working with micrographs motion corrected by unblur. Will be fixed in the next release. 
  
  
Line 35: Line 34:
   * <del>Issue 25: When using GUI, prediction behaves differently than using command line. The reason is, that it uses a different multiprocessing start method. Will be fixed with 1.5.1</del>   * <del>Issue 25: When using GUI, prediction behaves differently than using command line. The reason is, that it uses a different multiprocessing start method. Will be fixed with 1.5.1</del>
   * <del>Issue 26: If you select filtering "None" crYOLO does not train properly.</del>   * <del>Issue 26: If you select filtering "None" crYOLO does not train properly.</del>
 +  * <del>Issue 27: Filament mode is not working with micrographs motion corrected by unblur. Will be fixed in the next release.</del>
 +  * <del>Issue 28: Minimum distance filter is not applied to cbox files.</del>
 </hidden> </hidden>
 </note> </note>
pipeline/window/cryolo/issues.txt ยท Last modified: 2020/03/18 07:43 by twagner