dpgen.simplify package
Submodules
dpgen.simplify.arginfo module
- dpgen.simplify.arginfo.fp_args() List[Argument] [source]
Generate arginfo for fp.
- Returns
- List[Argument]
arginfo
- dpgen.simplify.arginfo.fp_style_variant_type_args() Variant [source]
Generate variant for fp style variant type.
- Returns
- Variant
variant for fp style
- dpgen.simplify.arginfo.general_simplify_arginfo() Argument [source]
General simplify arginfo.
- Returns
- Argument
arginfo
dpgen.simplify.simplify module
Simplify dataset (minimize the dataset size).
Init: pick up init data from dataset randomly
Iter: 00: train models (same as generator) 01: calculate model deviations of the rest dataset, pick up data with proper model deviaiton 02: fp (optional, if the original dataset do not have fp data, same as generator)
- dpgen.simplify.simplify.init_pick(iter_index, jdata, mdata)[source]
pick up init data from dataset randomly
- dpgen.simplify.simplify.make_model_devi(iter_index, jdata, mdata)[source]
calculate the model deviation of the rest idx
- dpgen.simplify.simplify.post_model_devi(iter_index, jdata, mdata)[source]
calculate the model deviation
- dpgen.simplify.simplify.run_iter(param_file, machine_file)[source]
init (iter 0): init_pick
tasks (iter > 0): 00 make_train (same as generator) 01 run_train (same as generator) 02 post_train (same as generator) 03 make_model_devi 04 run_model_devi 05 post_model_devi 06 make_fp 07 run_fp (same as generator) 08 post_fp (same as generator)