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 [2019/04/23 10:26] twagner [crYOLO] |
downloads:cryolo_1 [2019/07/15 18:01] twagner [Known issues] |
||
---|---|---|---|
Line 12: | Line 12: | ||
You can find more technical details in our paper: | You can find more technical details in our paper: | ||
+ | Nature Communications Biology: | ||
+ | [[https:// | ||
+ | |||
+ | Preprint: | ||
[[https:// | [[https:// | ||
Line 30: | Line 34: | ||
====crYOLO==== | ====crYOLO==== | ||
- | Version: 1.3.4 | + | Version: 1.4.0 |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
- | [[ftp:// | + | Please see [[downloads:cryolo_1# |
====crYOLO boxmanager==== | ====crYOLO boxmanager==== | ||
- | Version: 1.2.1 | + | Version: 1.2.3 |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
[{{ : | [{{ : | ||
Line 51: | Line 55: | ||
- | === For cryo images === | + | === For cryo images |
- | Number of datasets: | + | Number of datasets: |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
+ | |DOWNLOAD]] | ||
+ | |||
+ | [[pipeline: | ||
+ | |||
+ | === For cryo images (neural network denoised with JANNI) === | ||
+ | Number of datasets: 38 real, 10 simulated, 10 particle free datasets on various grids with contamination | ||
+ | |||
+ | Uploaded: 11. July 2019 | ||
+ | |||
+ | [[ftp:// | ||
|DOWNLOAD]] | |DOWNLOAD]] | ||
[[pipeline: | [[pipeline: | ||
- | Info: Trained | + | < |
+ | The performance of the general model based on JANNI denoised data compared to low-pass filtered data did not improve. The average AUC on the validation data was in both cases the same (0.85). But this might be because of the data selected for the general model. I assume that especially on very noisy micrographs JANNI will improve the results. | ||
+ | </ | ||
+ | |||
=== For negative stain images === | === For negative stain images === | ||
Line 78: | Line 96: | ||
====== Known issues ===== | ====== Known issues ===== | ||
* Issue 0: Training on multiple GPUs sometimes lead to worse performance (higher loss). We currently recommend to train on single gpus. | * Issue 0: Training on multiple GPUs sometimes lead to worse performance (higher loss). We currently recommend to train on single gpus. | ||
+ | * Issue 17: On the fly filtering (%%--%%otf) is slower than using it not, as the filtering is not parallelized in this case. | ||
+ | * Issue 22: Since crYOLO 1.4.0 it sometimes take long until it starts picking. The reason seems to be the tensorflow update. | ||
+ | <hidden Closed issues> | ||
* < | * < | ||
* < | * < | ||
Line 94: | Line 115: | ||
* < | * < | ||
* < | * < | ||
- | * Issue 17: On the fly filtering (%%--%%otf) is slower than using it not, as the filtering is not parallelized in this case. | ||
* < | * < | ||
* < | * < | ||
+ | * < | ||
+ | * < | ||
+ | * < | ||
+ | </ | ||
Line 122: | Line 146: | ||
After that, create a new virtual environment: | After that, create a new virtual environment: | ||
< | < | ||
- | conda create -n cryolo -c anaconda python=3.6 pyqt=5 cudnn=7.1.2 | + | conda create -n cryolo -c anaconda python=3.6 pyqt=5 cudnn=7.1.2 |
</ | </ | ||
Line 130: | Line 154: | ||
</ | </ | ||
- | Install crYOLO: | + | Install |
+ | < | ||
+ | conda install numpy==1.15.4 | ||
+ | </ | ||
+ | |||
+ | In case you run **crYOLO | ||
+ | < | ||
+ | pip install cryolo-X.Y.Z.tar.gz[gpu] | ||
+ | </ | ||
+ | |||
+ | But if you want to run **crYOLO on a CPU** run: | ||
+ | < | ||
+ | pip install cryolo-X.Y.Z.tar.gz[cpu] | ||
+ | </ | ||
+ | |||
+ | Finally you install the cryolo boxmanager: | ||
< | < | ||
- | conda install numpy==1.14.5 | ||
- | 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 145: | Line 182: | ||
===== Run it on the CPU ==== | ===== Run it on the CPU ==== | ||
- | There is also a way to run crYOLO on CPU. To use it, just install | + | There is also a way to run crYOLO on CPU. To use it, just follow |
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. | ||
Line 158: | Line 195: | ||
====crYOLO==== | ====crYOLO==== | ||
+ | |||
+ | **crYOLO 1.4.0:** | ||
+ | * Support Just Another Noise 2 Noise Implemnentation ([[: | ||
+ | * Add --mask_width as optional parameter for the filament mode | ||
+ | * Update tensorflow from 1.10.1 to 1.12.3 to make crYOLO compatible with JANNI | ||
+ | * Update numpy from 1.14.5 to 1.15.4 to make crYOLO compatible with JANNI | ||
+ | |||
+ | <hidden **Old crYOLO change logs**> | ||
+ | **crYOLO 1.3.6:** | ||
+ | * Changed filament search radius factor from 0.8 to 1.41 (this fixed issue 21) | ||
+ | * Add search radius factor as [[pipeline: | ||
+ | * Improved error message in case of corrupted config file | ||
+ | * Fixed issue 22: If absolute paths are used in the field “train_image” in your configuration file, filtering is skipped. | ||
+ | |||
+ | **crYOLO 1.3.5:** | ||
+ | * Fixed issue 20: During training the images are normalized separately, but during prediction is done batch wise. The lead to confusing results: some micrographs were perfectly picked, some totally unreasonable, | ||
+ | * Remove unnecessary dependencies | ||
+ | * Add %%__%%version%%__%% to %%__%%init%%__%%.py for easy access to package version. | ||
+ | |||
**crYOLO 1.3.4:** | **crYOLO 1.3.4:** | ||
* Support for SPHIRE 1.2 | * Support for SPHIRE 1.2 | ||
Line 163: | Line 219: | ||
* Installation now checks if python 3 is used. | * Installation now checks if python 3 is used. | ||
* Fix issue 19: Filtering does not work if target image directory is absolute path. | * Fix issue 19: Filtering does not work if target image directory is absolute path. | ||
- | * Fix crash when --otf was specified | + | * Fix crash when %%--%%otf was specified |
**crYOLO 1.3.3:** | **crYOLO 1.3.3:** | ||
Line 283: | Line 339: | ||
* Unify image augmentation | * Unify image augmentation | ||
+ | </ | ||
====crYOLO Boxmanager==== | ====crYOLO Boxmanager==== | ||
+ | **crYOLO Boxmanager Version 1.2.3:** | ||
+ | * Make it compatible with current new environment | ||
+ | |||
+ | <hidden **Old crYOLO Boxmanager change logs**> | ||
+ | **crYOLO Boxmanager Version 1.2.2:** | ||
+ | * Makes sure that the correct version of MatplotLib is used. | ||
+ | |||
**crYOLO Boxmanager Version 1.2.1:** | **crYOLO Boxmanager Version 1.2.1:** | ||
* Press " | * Press " | ||
Line 315: | Line 379: | ||
* Fix crash when cancel import boxfiles | * Fix crash when cancel import boxfiles | ||
* Fix crash with qt4 | * Fix crash with qt4 | ||
+ | </ | ||
+ | ==== General PhosaurusNet model ==== | ||
+ | **Version 20190516: | ||
+ | * Added four more inhouse datasets | ||
+ | * Added SNRNP (Thanks to Clement Charenton) | ||
- | ==== General PhosaurusNet model ==== | + | <hidden Old General PhosaurusNet model change logs> |
**Version 20190315: | **Version 20190315: | ||
* Added KLH | * Added KLH | ||
Line 326: | Line 395: | ||
**Version 20181221:** | **Version 20181221:** | ||
- | + | * Same datasets as the general YOLO network model version 20181120 but with trained with PhosaurusNet. | |
- | Same datasets as the general YOLO network model version 20181120 but with trained with PhosaurusNet. | + | </ |
==== General YOLO network model in patch mode ==== | ==== General YOLO network model in patch mode ==== | ||
+ | <hidden Old general YOLO network model in patch mode> | ||
**Version 20181120:** | **Version 20181120:** | ||
Line 380: | Line 448: | ||
* picornavirus (EMPIAR 10033) and | * picornavirus (EMPIAR 10033) and | ||
* an internal dataset. | * an internal dataset. | ||
+ | </ | ||