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 [2019/03/17 20:02] twagner [Run it on the CPU] |
downloads:cryolo_1 [2019/03/26 07:10] twagner [Known issues] |
||
---|---|---|---|
Line 30: | Line 30: | ||
====crYOLO==== | ====crYOLO==== | ||
- | Version: 1.3.0 | + | Version: 1.3.1 |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
====crYOLO boxmanager==== | ====crYOLO boxmanager==== | ||
Line 90: | Line 90: | ||
* < | * < | ||
* < | * < | ||
- | * Issue 15: If the --gpu_fraction is used, crYOLO always uses GPU 0. Will be fixed in 1.3.1. | + | * <del>Issue 15: If the --gpu_fraction is used, crYOLO always uses GPU 0. Will be fixed in 1.3.1.</ |
+ | * Issue 16: --gpu_fraction only works for prediction, not for training. Will be fixed in 1.3.2. | ||
Line 126: | Line 127: | ||
Install crYOLO: | Install crYOLO: | ||
< | < | ||
- | pip install numpy | + | conda install numpy |
pip install cryolo-X.Y.Z.tar.gz | pip install cryolo-X.Y.Z.tar.gz | ||
pip install cryoloBM-X.Y.Z.tar.gz | pip install cryoloBM-X.Y.Z.tar.gz | ||
Line 139: | Line 140: | ||
Picking with crYOLO is also quite fast on the CPU. On my local machine (Intel i9) it takes roughly 1 second per micrograph and on our low-performance notebooks (Intel i3) 4 seconds. | Picking with crYOLO is also quite fast on the CPU. On my local machine (Intel i9) it takes roughly 1 second per micrograph and on our low-performance notebooks (Intel i3) 4 seconds. | ||
- | 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 refining the general model, which takes 12 minutes per epoch (~ 5 hours). | + | 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: |
**Here is how you prepare your crYOLO setup for using it on the CPU:** | **Here is how you prepare your crYOLO setup for using it on the CPU:** | ||
Line 155: | Line 156: | ||
Use the **__'' | Use the **__'' | ||
- | ====== Change log ===== | + | ====== Change log ====== |
====crYOLO==== | ====crYOLO==== | ||
+ | |||
+ | **crYOLO 1.3.1:** | ||
+ | * Fix Issue 15: -g was ignored when --gpu_fraction was used. | ||
**crYOLO 1.3.0:** | **crYOLO 1.3.0:** |