User Tools

Site Tools


pipeline:window:cryolo

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
pipeline:window:cryolo [2020/06/05 09:03]
twagner [Overview]
pipeline:window:cryolo [2021/02/19 10:00]
twagner
Line 1: Line 1:
-{{ :downloads:cryolo_logo.jpg?600 |}}+{{  :downloads:cryolo_logo.jpg?600  }}
  
 ===== Overview ===== ===== Overview =====
  
-<note important>+<note warning>
  
 **NEW DOCUMENTATION** **NEW DOCUMENTATION**
  
-The documentation has moved to https://cryolo.readthedocs.io+The documentation has moved to [[https://cryolo.readthedocs.io|https://cryolo.readthedocs.io]]
  
 </note> </note>
  
-CrYOLO is a fast and accurate particle picking procedure. It's based on convolutional neural networks and utilizes the popular [[https://arxiv.org/abs/1612.08242|You Only Look Once]] (YOLO) object detection system.  +CrYOLO is a fast and accurate particle picking procedure. It's based on convolutional neural networks and utilizes the popular [[https://arxiv.org/abs/1612.08242|You Only Look Once]] (YOLO) object detection system. 
-  * crYOLO makes picking **fast** -- On a modern GPU it will pick your particles at up to 6 micrographs per second. + 
-  * crYOLO makes picking **smart** -- The network learns the context of particles (e.g. not to pick particles on carbon or within ice contamination ) +  * crYOLO makes picking **fast**  – On a modern GPU it will pick your particles at up to 6 micrographs per second. 
-  * crYOLO makes training **easy** -- You might use a general network model and skip training completely. However, if the general model doesn't give you satisfactory results or if you would like to improve them, you might want to train a specialized model specific for your data set by selecting __particles__ (no selection of negative examples necessary) on a small number of micrographs. +  * crYOLO makes picking **smart**  – The network learns the context of particles (e.g. not to pick particles on carbon or within ice contamination ) 
-  * crYOLO makes training **tolerant** -- Don't worry if you miss quite a lot particles during creation of your training set. [[:cryolo_picking_unlabeled|crYOLO will still do the job.]]+  * crYOLO makes training **easy**  – You might use a general network model and skip training completely. However, if the general model doesn't give you satisfactory results or if you would like to improve them, you might want to train a specialized model specific for your data set by selecting __particles__  (no selection of negative examples necessary) on a small number of micrographs. 
 +  * crYOLO makes training **tolerant**  – Don't worry if you miss quite a lot particles during creation of your training set. [[:cryolo_picking_unlabeled|crYOLO will still do the job.]]
  
 In this tutorial we explain our recommended configurations for single particle and filament projects. You can find more information how to use crYOLO, about supported networks and about the config file in the following articles: In this tutorial we explain our recommended configurations for single particle and filament projects. You can find more information how to use crYOLO, about supported networks and about the config file in the following articles:
 +
   * [[https://www.youtube.com/embed/JTgldM4wAAk|crYOLO talk at SBGrid]]   * [[https://www.youtube.com/embed/JTgldM4wAAk|crYOLO talk at SBGrid]]
   * [[:cryolo_nets|crYOLO networks]]   * [[:cryolo_nets|crYOLO networks]]
   * [[:cryolo_config|crYOLO configuration file]]   * [[:cryolo_config|crYOLO configuration file]]
- 
- 
  
 <note> <note>
Line 34: Line 34:
 We are also proud that crYOLO was recommended by F1000: We are also proud that crYOLO was recommended by F1000:
  
-//"CrYOLO works amazingly well in identifying the true particles and distinguishing them from other high-contrast features. Thus, crYOLO provides a fast, automated tool, which gives similar reliable results as careful manual selection and outperforms template based selection procedures."// +//"CrYOLO works amazingly well in identifying the true particles and distinguishing them from other high-contrast features. Thus, crYOLO provides a fast, automated tool, which gives similar reliable results as careful manual selection and outperforms template based selection procedures."//  <html></html> <html> <a href="https://f1000.com/prime/733517098?bd=1" target="_blank"><img src="https://s3.amazonaws.com/cdn.f1000.com/images/badges/badgef1000.gif" alt="Access the recommendation on F1000Prime" id="bg" /> Bettina Böttcher, Biochemistry, University Würzburg</a> </html> </note>
-<html></html> +
-<html> +
-<a href="https://f1000.com/prime/733517098?bd=1" target="_blank"><img src="https://s3.amazonaws.com/cdn.f1000.com/images/badges/badgef1000.gif" alt="Access the recommendation on F1000Prime" id="bg" />&nbsp;Bettina Böttcher, Biochemistry, University Würzburg</a> +
-</html> +
-</note>+
  
 ===== Installation ===== ===== Installation =====
  
-You can find the download and installation instructions here: [[howto:download_latest_cryolo|Download and Installation]]+You can find the download and installation instructions here: [[:howto:download_latest_cryolo|Download and Installation]]
  
 {{page>pipeline:window:cryolo:issues}} {{page>pipeline:window:cryolo:issues}}
 +
 ===== Release notes ===== ===== Release notes =====
 +
 {{page>pipeline:window:cryolo:changelog}} {{page>pipeline:window:cryolo:changelog}}
 +
 ===== Tutorials ===== ===== Tutorials =====
  
 Depending what you want to do, you can follow one of these self-contained Tutorials: Depending what you want to do, you can follow one of these self-contained Tutorials:
  
-  - [[pipeline:window:cryolo:picking_general|I would like to pick particles without training using a general model]] +  - [[:pipeline:window:cryolo:picking_general|I would like to pick particles without training using a general model]] 
-  - [[pipeline:window:cryolo:picking_scratch|I would like to train a model from scratch for picking my particles]] +  - [[:pipeline:window:cryolo:picking_scratch|I would like to train a model from scratch for picking my particles]] 
-  - [[pipeline:window:cryolo:picking_filaments|I would like to train a model from scratch for picking filaments]] +  - [[:pipeline:window:cryolo:picking_filaments|I would like to train a model from scratch for picking filaments]] 
-  - [[pipeline:window:cryolo:picking_general_refine|I would like to refine a general model for my particle]] +  - [[:pipeline:window:cryolo:picking_general_refine|I would like to refine a general model for my particle]]
- +
-The **first, second and third tutorial** are the most common use cases and well tested. The **fourth tutorial** is still experimental but might give you better results in less time and less training data.  +
- +
- +
- +
- +
  
 +The **first, second and third tutorial**  are the most common use cases and well tested. The **fourth tutorial**  is still experimental but might give you better results in less time and less training data.
  
 ===== Help ===== ===== Help =====
Line 70: Line 62:
  
 Find help at our [[https://listserv.gwdg.de/mailman/listinfo/sphire|mailing list]]! Find help at our [[https://listserv.gwdg.de/mailman/listinfo/sphire|mailing list]]!
 +
 +
pipeline/window/cryolo.txt · Last modified: 2021/02/19 10:00 by twagner