1.4 KiB
Resolution estimation (ML)
Resolution estimation can be done with a recent deep learning model by D. Mendez et al. (see Acta Cryst D, 80, 26-43), adapted to Jungfraujoch. Model used in the original paper is located in the resonet/ directory, after converting to TorchScript format.
To use the feature it is necessary to install libtorch library, preferably in /opt/libtorch location.
The C++11 ABI version needs to be chosen.
For RHEL 8 systems, please download older version 2.1.0, as version 2.2.0 requires newer glibc library than available with the operating system.
Version 2.1.0 can be downloaded with the following command:
wget https://download.pytorch.org/libtorch/cu121/libtorch-cxx11-abi-shared-with-deps-2.1.0%2Bcu121.zip
Compilation
Then you can compile Jungfraujoch with the following commands:
$ mkdir build
$ cd build
$ cmake .. -DJFJOCH_USE_TORCH=ON -DCMAKE_INSTALL_PREFIX=<directory to install>
$ make
$ sudo make install
Configuration
jfjoch_broker configuration file needs "resonet_model":<path to .pt file> entry.
Known issue
Currently, Cmake scripts for libtorch and Qt are incompatible, and using both libraries is not possible in a single project.
Therefore, jfjoch_viewer compilation is not possible, when libtorch is used.
The feature is experimental, and for the time being performance is low, below 100 Hz with 4 x Nvidia L4 GPUs.