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 [2019/07/23 10:53] twagner [Overview] |
pipeline:window:cryolo [2019/08/29 16:28] twagner [Training] |
||
---|---|---|---|
Line 52: | Line 52: | ||
<hidden **Alternative: | <hidden **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 [[: |
To use JANNI' | To use JANNI' | ||
Line 184: | Line 184: | ||
Navigate to the folder with '' | Navigate to the folder with '' | ||
- | **1. Warm up your network** | + | **Train your network |
< | < | ||
cryolo_train.py -c config.json -w 3 -g 0 | cryolo_train.py -c config.json -w 3 -g 0 | ||
- | </ | ||
- | |||
- | **2. Train your network** | ||
- | |||
- | < | ||
- | cryolo_train.py -c config.json -w 0 -g 0 | ||
</ | </ | ||
Line 199: | Line 193: | ||
The training stops when the " | The training stops when the " | ||
+ | |||
< | < | ||
- | cryolo_train.py -c config.json -w 0 -g 0 -e 15 | + | cryolo_train.py -c config.json -w 3 -g 0 -e 15 |
</ | </ | ||
+ | |||
to the training command. | to the training command. | ||
==== Picking ==== | ==== Picking ==== | ||
Line 287: | Line 283: | ||
=== Negative stain images === | === Negative stain images === | ||
For the general model for **negative stain data** please use: | For the general model for **negative stain data** please use: | ||
+ | <hidden **config.json for negative stain images**> | ||
<code json config.json> | <code json config.json> | ||
{ | { | ||
Line 298: | Line 295: | ||
} | } | ||
</ | </ | ||
+ | </ | ||
Please set the value in the //" | Please set the value in the //" | ||
Line 422: | Line 420: | ||
In principle, there is not much difference in training crYOLO for filament picking and particle picking. For project with roughly 20 filaments per image we successfully trained on 40 images (=> 800 filaments). However, in our experience the warm-up phase and training need a little bit more time: | In principle, there is not much difference in training crYOLO for filament picking and particle picking. For project with roughly 20 filaments per image we successfully trained on 40 images (=> 800 filaments). However, in our experience the warm-up phase and training need a little bit more time: | ||
- | **1. Warm up your network** | + | **Train your network |
- | + | ||
- | < | + | |
- | cryolo_train.py -c config.json -w 10 -g 0 | + | |
- | </ | + | |
- | + | ||
- | **2. Train your network** | + | |
< | < | ||
- | cryolo_train.py -c config.json -w 0 -g 0 -e 10 | + | cryolo_train.py -c config.json -w 10 -g 0 -e 10 |
</ | </ | ||