Commit 3153fc66 authored by bliven_s's avatar bliven_s Committed by gsell

Create crYOLO module

parent 28ef97e2
#!/usr/bin/env modbuild
pbuild::add_to_group 'EM'
pbuild::prep() {
echo "prepping"
mkdir -p "$SRC_DIR"
curl -fsSLo "$SRC_DIR/miniconda.sh" 'https://repo.anaconda.com/miniconda/Miniconda2-latest-Linux-x86_64.sh'
curl -fsSLo "$SRC_DIR/cryoloBM.tgz" 'ftp://ftp.gwdg.de/pub/misc/sphire/crYOLO_BM_V1_1_1/cryoloBM-1.1.1.tar.gz'
curl -fsSLo "$SRC_DIR/cryolo.tgz" 'ftp://ftp.gwdg.de/pub/misc/sphire/crYOLO_V1_2_3/cryolo-1.2.3.tar.gz'
:
}
pbuild::configure() {
:
}
pbuild::compile() {
:
}
pbuild::install() {
mkdir -p $PREFIX
# Install conda
bash "$SRC_DIR/miniconda.sh" -b -p $PREFIX/conda
# Create environment
$PREFIX/conda/bin/conda create -y --name crYOLO anaconda python=3.6 pyqt=5 cudnn=7.1.2 numpy
# Activate
source $PREFIX/conda/bin/activate crYOLO
# Install
pip install $SRC_DIR/cryolo.tgz
pip install $SRC_DIR/cryoloBM.tgz
# Deactivate
source deactivate
}
crYOLO/1.2.3 unstable cuda/9.0.176
#%Module
module-whatis "crYOLO is a fast and accurate particle picking procedure for electron microscopy"
module-url "http://sphire.mpg.de/wiki/doku.php?id=pipeline:window:cryolo"
module-license "SPHIRE-crYOLO Complimentary Science Software License (http://sphire.mpg.de/wiki/doku.php?id=cryolo_license). Non-commercial academic and research purposes only"
module-maintainer "Spencer Bliven <spencer.bliven@psi.ch>"
module-help "
CrYOLO is a fast and accurate particle picking procedure. It's based on
convolutional neural networks and utilizes the popular You Only Look Once
(YOLO) object detection system.
* crYOLO makes picking fast – On a modern GPU it will pick your particles at
up to 6 micrographs per second.
* crYOLO makes picking smart – The network learns the context of particles
(e.g. not to pick particles on carbon or within ice contamination )
* crYOLO makes training easy – You might use a general network model and skip
training completely. However, if the general model doesn't give you
satisfactory results or if you would like to improve them, you might want
to train a specialized model specific for your data set by selecting
particles (no selection of negative examples necessary) on a small number
of micrographs.
"
# Check for supported shell types
set shelltype [module-info shelltype]
switch -- $shelltype {
"sh" {
}
default {
puts stderr "Shells of type '$shelltype' are NOT supported!"
}
}
#puts stderr "Switching crYOLO mode to [module-info mode]"
#puts stdout "{ date; echo Switching crYOLO mode to [module-info mode] ; } >> /gpfs/home/bliven_s/cryolo_mod.log;\n"
switch [module-info mode] {
"load" {
#puts stderr "source $PREFIX/conda/bin/activate crYOLO"
puts stdout "source $PREFIX/conda/bin/activate crYOLO;\n"
}
"unload" -
"remove" {
#puts stderr "source deactivate"
puts stdout "source $PREFIX/conda/bin/deactivate;\n"
puts stdout {unset $(set|sed -rn 's/^(_?conda[a-z_]*).*$/\1/pI');}
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment