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 | ||
downloads:cryolo_1 [2019/09/13 11:17] twagner [crYOLO] |
downloads:cryolo_1 [2019/09/17 13:58] twagner [Start picking!] |
||
---|---|---|---|
Line 187: | Line 187: | ||
Training crYOLO is much more computational expensive. Training a model with 14 micrographs from scratch on my local machine take 34 minutes per epoch on the CPU. Given that you often need 25 epochs until convergence it is a task to do overnight (~ 12 hours). However, you might want to try [[pipeline: | Training crYOLO is much more computational expensive. Training a model with 14 micrographs from scratch on my local machine take 34 minutes per epoch on the CPU. Given that you often need 25 epochs until convergence it is a task to do overnight (~ 12 hours). However, you might want to try [[pipeline: | ||
- | ====== | + | ====== |
- | Use the **__'' | + | Use our **__'' |
====== Change log ====== | ====== Change log ====== | ||
Line 197: | Line 197: | ||
**crYOLO 1.5.0:** | **crYOLO 1.5.0:** | ||
* Added a GUI for crYOLO (start with cryoloo.py) | * Added a GUI for crYOLO (start with cryoloo.py) | ||
- | * New fast low-pass filtering pipeline: Speed up on-the-fly filtering by 175%, speed up training by 75% speed up picking by 50% | + | * Optimized |
* Add rotation as data augmentation | * Add rotation as data augmentation | ||
* Number of layers for fine tuning are now changeable (-lft) | * Number of layers for fine tuning are now changeable (-lft) |