MLPF results on the simulated CLIC dataset
收藏资源简介:
Trained models and evaluation results for the upcoming paper "Scalable neural network models and terascale datasets for particle-flow reconstruction". The archive contains the following subfolders: clusters_best_tuned_gnn_clic_v130 MLPF GNN model after hypertuning the inputs are reconstructed tracks and Pandora clusters the outputs are reconstructed PF candidates trained on tt and qq v1.3.0 (1M events each) hits MLPF GNN model inputs are reconstructed tracks and calorimeter hits outputs are reconstructed PF candidates trained on tt, qq and gun samples (K0L, gamma, pi+-, pi0, neutron, ele, mu) v1.2.0 training was restarted several times from previous checkpoints hypertuning GNN and transformer model before and after hypertuning timing scaling study of baseline PF with number of gun particles on CPU scaling study of GNN model with number of input elements on GPU gpu_scaling the scaling study of model training on multiple accelerator cards The training dataset is available at Pata, Joosep, Wulff, Eric, Duarte, Javier, Mokhtar, Farouk, Zhang, Mengke, Girone, Maria, & Southwick, David. (2023). Simulated datasets for detector and particle flow reconstruction: CLIC detector (1.1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8260741
本资源包含即将发表的论文《面向粒子流重建的可扩展神经网络模型与太字节级数据集》(Scalable neural network models and terascale datasets for particle-flow reconstruction)的训练模型与评估结果。 本归档文件包含以下子文件夹: clusters_best_tuned_gnn_clic_v130 该文件夹包含经过超参数调优后的MLPF图神经网络(Graph Neural Network,GNN)模型: - 输入为重建径迹与潘多拉(Pandora)簇团 - 输出为重建粒子流候选(Particle Flow,PF) - 训练数据集为tt与qq样本v1.3.0版本,每个样本集包含100万次事件 hits 该文件夹包含MLPF图神经网络模型: - 输入为重建径迹与量能器击中信号 - 输出为重建粒子流候选 - 训练数据集为tt、qq以及单粒子束样本(包含K0L、γ光子、π±、π0、中子、电子ele、缪子mu)v1.2.0版本 - 训练过程曾多次基于此前的检查点重启 hypertuning 该文件夹包含超参数调优前后的图神经网络与Transformer模型 timing 该文件夹包含两项扩展性研究内容: - 基于CPU的基准粒子流模型随单粒子束样本数量变化的扩展性测试 - 基于GPU的图神经网络模型随输入元素数量变化的扩展性测试 gpu_scaling 该文件夹包含多加速卡并行训练模型的扩展性研究结果 训练数据集可通过以下资源获取: Pata, Joosep、Wulff, Eric、Duarte, Javier、Mokhtar, Farouk、Zhang, Mengke、Girone, Maria 与 Southwick, David. (2023). 面向探测器与粒子流重建的模拟数据集:CLIC探测器(1.1) [数据集]. Zenodo. https://doi.org/10.5281/zenodo.8260741



