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 [2019/03/17 10:03] twagner [Data preparation] |
pipeline:window:cryolo [2019/03/17 19:58] twagner [Picking] |
||
---|---|---|---|
Line 15: | Line 15: | ||
You can find more technical details in our paper: | You can find more technical details in our paper: | ||
- | [[https:// | + | [[https:// |
+ | ]] | ||
< | < | ||
Line 183: | Line 184: | ||
[{{ : | [{{ : | ||
- | Right now, this filtering does not work for filaments. | + | Right now, **this filtering does not yet work for filaments**. |
Line 275: | Line 276: | ||
Picking is identical as with a model trained from scratch, so we will skip it here. Just follow the description given [[pipeline: | Picking is identical as with a model trained from scratch, so we will skip it here. Just follow the description given [[pipeline: | ||
- | + | ==== Training on CPU ==== | |
+ | [[downloads: | ||
+ | The fine tune mode is especially useful if you want to train crYOLO on the CPU. On my local machine it reduced the time from 12-15 hours to 4-5 hours. | ||
===== Picking filaments - Using a model trained for your data ===== | ===== Picking filaments - Using a model trained for your data ===== | ||
Since version 1.1.0 crYOLO supports picking filaments. | Since version 1.1.0 crYOLO supports picking filaments. | ||
Line 410: | Line 412: | ||
===== Advanced parameters ===== | ===== Advanced parameters ===== | ||
- | During **training** (// | + | During **training** (// |
* // | * // | ||
* // | * // | ||
Line 416: | Line 418: | ||
* // | * // | ||
- | During **picking** (// | + | During **picking** (// |
* //-t CONFIDENCE_THRESHOLD//: | * //-t CONFIDENCE_THRESHOLD//: | ||
* //-d DISTANCE_IN_PIXEL//: | * //-d DISTANCE_IN_PIXEL//: |