Lines Matching refs:data

308 …aining of machine-learning models, normally uses *a priori* (already gathered) data stored on disk.
309 …the scale of the problem grows and the data that is saved to disk reduces to a small percentage of…
310 One way of working around this is to perform whatever data analysis while the simulation is activel…
311 This is known as *in situ* (in place) data analysis.
313 HONEE can facilitate *in situ* data analysis using [SmartSim](https://www.craylabs.org/docs/overvie…
314 HONEE will periodically place data into an in-memory database and a separate process can then read …
315 SmartSim is responsible for orchestrating the running of HONEE and the data-analysis processes.
318 …learning interaction with normal HPC applications, any data-analysis process can be used e.g. data…
348 The most basic functionality for *in situ* data analysis is to simply place the solution vector int…
362   - Place solution data into the smartsim database
367   - Number of timesteps between writing solution data into SmartRedis database
372   - Whether new solution data should overwrite old data on database
379 Currently the code is only setup to do *in situ* training for the SGS data-driven model.
380 Training data is split into the model inputs and outputs.
385 The training will create multiple sets of data per each filter width defined in `-sgs_train_filter_…
391 …he choice of whether to add new training data on each database write or to overwrite the old data …
407   - Whether to enable *in situ* training of data-driven SGS model. Require building with SmartRedis.
412   - Number of timesteps between writing training data into SmartRedis database
417   - Whether new training data should overwrite old data on database
422   - List of scalar values for different filter widths to calculate for training data