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 [2019/09/30 16:14] twagner [Installation] |
downloads:cryolo_1 [2019/10/15 16:42] twagner [General PhosaurusNet models] |
||
---|---|---|---|
Line 55: | Line 55: | ||
=== For cryo images (low-pass filtered) === | === For cryo images (low-pass filtered) === | ||
- | Number of datasets: | + | Number of datasets: |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
|DOWNLOAD]] | |DOWNLOAD]] | ||
=== For cryo images (neural network denoised with JANNI) === | === For cryo images (neural network denoised with JANNI) === | ||
- | Number of datasets: | + | Number of datasets: |
- | Uploaded: | + | Uploaded: |
- | [[ftp:// | + | [[ftp:// |
|DOWNLOAD]] | |DOWNLOAD]] | ||
Line 145: | Line 145: | ||
* 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 17: On the fly filtering (%%--%%otf) is slower than using it not, as the filtering is not parallelized in this case. | ||
+ | * Issue 26: If you select filtering " | ||