Warning, /geant4/examples/extended/parameterisations/Par04/training_calodit/README.md is written in an unsupported language. File is not indexed.
0001 ## CaloDiT-2
0002
0003 CaloDiT-2 is transformer-based diffusion model, which can be easily adapted to a new detector geometry.
0004 This Par04 repository contains the ONNX and TorchScript versions of the model and how to use them for
0005 Par04-SiW detector. *Note that the virtual cylindrical mesh is less granular than VAE.*
0006
0007 The source code for CaloDiT-2 can be found [here](https://gitlab.cern.ch/fastsim/diffusion4sim/-/tree/CaloDiT_v1?ref_type=tags).
0008 It contains the training, adaptation, and distillation scripts along with the pretrained models. You can download the
0009 pretrained models (not the .onnx/.pt files available with this repository), which acts as a checkpoint and finetune
0010 it on the new dataset.
0011
0012 You can also modify the virtual mesh size and hence the architecture if needed. But in that case, you won't be able
0013 to use the pretrained models. Pretrained models adopt a mesh as in [CaloChallenge Dataset-2](https://calochallenge.github.io/homepage/).
