This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
pipeline:window:cryolo:configuration [2019/09/17 15:30] twagner |
pipeline:window:cryolo:configuration [2020/01/10 14:47] twagner |
||
---|---|---|---|
Line 5: | Line 5: | ||
{{ : | {{ : | ||
- | At this point you could already press the Start button to generate the config file but you might want to take these options into account: | + | At this point you could already press the [Start] button to generate the config file but you might want to take these options into account: |
- | * During training, crYOLO also needs validation data((Micrographs that are selected as validation data are not used to train crYOLO. These micrographs are used to calculate how well the model performs and whether it still improves.)). Typically, 20% of the training data are randomly chosen as validation data. If you want to use specific images as validation data, you can move the images and the corresponding box files to separate folders. | + | * During training, crYOLO also needs validation data((Micrographs that are selected as validation data are not used to train crYOLO. These micrographs are used to calculate how well the model performs and whether it still improves.)). Typically, 20% of the training data are randomly chosen as validation data. If you want to use specific images as validation data, you can move the images and the corresponding box files to separate folders. |
- | * By default, your micrographs are low pass filtered to an absolute frequency of 0.1 and saved to disk. You can change the cutoff threshold and the directory for filtered micrographs in the //"Model/Denoising options"// | + | * By default, your micrographs are low pass filtered to an absolute frequency of 0.1 and saved to disk. You can change the cutoff threshold and the directory for filtered micrographs in the //" |
+ | * When training from scratch, crYOLO is initialized with weights learned on the ImageNet training data (transfer learning((From Wikipedia: Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.))). It might be helpful if you set the pretrained_weights options in the //" | ||
<note tip> | <note tip> | ||
**Alternative: | **Alternative: | ||
- | Since crYOLO 1.4 you can also use neural network denoising with [[: | + | Since crYOLO 1.4 you can also use neural network denoising with [[: |
{{ : | {{ : | ||
I recommend to use denoising with JANNI only together with a GPU as it is rather slow (~ 1-2 seconds per micrograph on the GPU and 10 seconds per micrograph on the CPU) | I recommend to use denoising with JANNI only together with a GPU as it is rather slow (~ 1-2 seconds per micrograph on the GPU and 10 seconds per micrograph on the CPU) | ||
Line 19: | Line 20: | ||
</ | </ | ||
<note tip> | <note tip> | ||
- | You can also modify all options and parameters directly in the config.json file. Please note the wiki entry about the [[: | + | **Editing the configuration file** |
+ | |||
+ | You can also modify all options and parameters directly in the config.json file. It can be opened by any text editor. Please note the wiki entry about the [[: | ||
</ | </ |