pipeline:window:cryolo:picking_general

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
pipeline:window:cryolo:picking_general [2019/10/11 17:11]
twagner [2. Configuration]
pipeline:window:cryolo:picking_general [2020/05/25 10:14] (current)
twagner
Line 1: Line 1:
 +<note important>​
 +
 +**DOCUMENTATION OUTDATED**
 +
 +The documentation has moved to https://​cryolo.readthedocs.io/​en/​latest/​
 +
 +</​note>​
 +
 ===== Picking particles - Without training using a general model ===== ===== Picking particles - Without training using a general model =====
 Here you can find how to apply the general models we trained for you. If you would like to train your own general model, please see our extra wiki page: [[:​cryolo_train_general_model|How to train your own general model]]. Here you can find how to apply the general models we trained for you. If you would like to train your own general model, please see our extra wiki page: [[:​cryolo_train_general_model|How to train your own general model]].
Line 26: Line 34:
  
   * General model for negative stain images: Select filter "​NONE"​   * General model for negative stain images: Select filter "​NONE"​
 +
 +
 +<note tip>
 +**Anchor size is optional**
 +
 +In the configuration file, the field "​anchors"​ is optional during prediction. That means, you don't to define a box size during prediction, as crYOLO does a size estimation internally. This is of advantage for automated pipelines. You can simply delete the entry in configuration file.
 +This should not affect the picking quality. The estimated size is still contained in .cbox files. Coordinates in EMAN and STAR format are written with a box size of 0 in that case.
 +
 +</​note>​
  
 <​html>​ <​html>​
Line 45: Line 62:
 For the general **[[:​cryolo_nets#​network_3_phosaurusnet|Phosaurus network]]** trained for **low-pass filtered cryo images** run: For the general **[[:​cryolo_nets#​network_3_phosaurusnet|Phosaurus network]]** trained for **low-pass filtered cryo images** run:
 <​code>​ <​code>​
-cryolo_gui.py config ​config_cryolo_.json 220 --filter LOWPASS --low_pass_cutoff 0.1+cryolo_gui.py config ​config_cryolo.json 220 --filter LOWPASS --low_pass_cutoff 0.1
 </​code>​ </​code>​
  
 For the general model trained with **neural-network denoised cryo images** (with [[:​janni_tutorial#​download|JANNI'​s general model]]) run: For the general model trained with **neural-network denoised cryo images** (with [[:​janni_tutorial#​download|JANNI'​s general model]]) run:
 <​code>​ <​code>​
-cryolo_gui.py config ​config_cryolo_.json 220 --filter JANNI --janni_model /​path/​to/​janni_general_model.h5+cryolo_gui.py config ​config_cryolo.json 220 --filter JANNI --janni_model /​path/​to/​janni_general_model.h5
 </​code>​ </​code>​
  
 For the general model for **negative stain data** please run: For the general model for **negative stain data** please run:
 <​code>​ <​code>​
-cryolo_gui.py config ​config_cryolo_.json 220 --filter NONE+cryolo_gui.py config ​config_cryolo.json 220 --filter NONE
 </​code>​ </​code>​
 </​hidden>​ </​hidden>​
  • pipeline/window/cryolo/picking_general.1570806669.txt.gz
  • Last modified: 2019/10/11 17:11
  • by twagner