Differences

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

--- pipeline:window:cryolo [2019/07/09 21:00]
twagner [Data preparation]
+++ pipeline:window:cryolo [2019/07/09 21:12]
twagner [Data preparation]
@@ Line 37: / Line 37: @@
 to the model section in your config file to filter your images down to an absolute frequency of 0.1. The filtered images are saved in folder ''filtered''.
-<hidden Alternative: Using neural-network denoising with JANNI>
+<hidden **Alternativ: Using neural-network denoising with JANNI**>
+<html><br></html>
+Since crYOLO 1.4 you can also use neural network denoising with [[:janni|JANNI]]. The easiest way is to use the JANNI's general model but you can also train one for your data. crYOLO directly an interface to JANNI to filter your data, you just have to specify the path to you JANNI model, the batch size (default 32), overlap of the batches (default 24) and a path where the denoised images should be written. To use JANNI's denoising you have to use following entry in your config.json:
 <code>
-"filter":               [model.h5,1,2,"filtered"]
+"filter":               ["path/to/janni_model.h5",32,24,"filtered"]
 </code>
+<html><br></html>
 </hidden>
+<html><br></html>
 If you followed the installation instructions, you now have to activate the cryolo virtual environment with