This is an old revision of the document!
If you are interested in using crYOLO in a commercial context please contact stefan.raunser@mpi-dortmund.mpg.de
You can find more technical details in our paper:
SPHIRE-crYOLO: A fast and well-centering automated particle picker for cryo-EM
Before downloading or using this product, make sure you understand and accept the terms of the license.
Number of datasets: 32 real, 10 simulated, 10 particle free datasets on various grids with contaminations
Uploaded: 14. March 2019
Info: Trained on cryo images, therefore negative stain will not work.
Previous versions of crYOLO, the boxmanager and the general models can be found here: Archive.
System requirements:
crYOLO was tested on Ubuntu 16.04.4 LTS and Ubuntu 18.04 with an NVIDIA Geforce 1080 / Geforce 1080Ti.
However, it should run on Windows as well.
As the GPU accelerated version of tensorflow does not support MacOS, crYOLO does not support it either.
crYOLO depends on CUDA Toolkit 9.0 and the cuDNN 7.1.2 library. It will be automatically installed during crYOLO installation.
Install crYOLO!
The following instructions assume that pip and anaconda or miniconda are available. In case you have a old cryolo environment installed, first remove the old one with:
conda env remove --name cryolo
After that, create a new virtual environment:
conda create -n cryolo -c anaconda python=3.6 pyqt=5 cudnn=7.1.2
Activate the environment:
source activate cryolo
Install crYOLO:
pip install numpy pip install cryolo-X.Y.Z.tar.gz pip install cryoloBM-X.Y.Z.tar.gz
That's it!
There is also a way to run crYOLO on CPU. This is especially usefull when you would like to apply the generalized model and don't have a NVIDIA GPU.
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 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).
Here is how you prepare your crYOLO setup for using it on the CPU:
After you followed the crYOLO installation instructions just replace tensorflow-gpu by tensorflow:
pip uninstall tensorflow-gpu pip install tensorflow==1.10.1
Now crYOLO should work on the CPU as well!
Use the step-by-step tutorial
to get started!
crYOLO 1.3.0:
crYOLO Version 1.2.3:
crYOLO Version 1.2.2:
crYOLO Version 1.2.1:
crYOLO Version 1.2.0:
crYOLO Version 1.1.4:
crYOLO Version 1.1.3:
crYOLO Version 1.1.2:
crYOLO Version 1.1.1:
crYOLO Version 1.1.0:
crYOLO Version 1.0.4:
crYOLO Version 1.0.3:
crYOLO Version 1.0.2:
crYOLO Version 1.0.1:
crYOLO Boxmanager Version 1.2:
crYOLO Boxmanager Version 1.1.1:
crYOLO Boxmanager Version 1.1.0:
crYOLO Boxmanager Version 1.0.4:
crYOLO Boxmanager Version 1.0.3:
crYOLO Boxmanager Version 1.0.2:
crYOLO Boxmanager Version 1.0.1:
Version 20190315::
Version 20190218:
Version 20181221:
Same datasets as the general YOLO network model version 20181120 but with trained with PhosaurusNet.
Version 20181120:
Added multiple simulated datasets, where each micrograph contains hundreds of particles with different defocus:
Besides these simulated datasets we added handpicked
It total 45 datasets are now included.
Version 20180823:
Increase the number of hand picked datasets to 25 by adding:
Version 20180720:
Added micrographs of 7 new handpicked datasets:
Furthermore I had to remove one internal dataset, as it turned out that it is unsuitable for training the general model.
Version 20180704:
Added three more handpicked datasets: