Caloscore official repository

Repo for diffusion based calorimeter generation.

Started as an offshoot of CaloScore.

Following the approach of Denoising Diffusion Probabilistic Models and High-Resolution Image Synthesis with Latent Diffusion Models.

Pytorch v1.9 was used to implement all models.

Data

Results are presented using the Fast Calorimeter Data Challenge dataset and are available for download on zenodo:

• Dataset 1
• Dataset 2
• Dataset 3

Run the training scripts with

cd scripts
python train.py  --config CONFIG --model MODEL

• MODEL options are: subVPSDE/VESDE/VPSDE (Original CaloScore)

• For training an autoencoder or training a diffusion model, use train_ae.py or train_diffu.py

• CONFIG options are [config_dataset1.json/config_dataset2.json/config_dataset3.json]

Sampling from the learned score function

python plot.py  --nevts N  --sample  --config CONFIG --model MODEL

Creating the plots shown in the paper

python plot.py  --config CONFIG --model MODEL