Files
NexQuant/rdagent/app/model_implementation/eval.py
T
Xu Yang 6b626eb56d New Framework for idea proposal and implementation on RD-Agent (#34)
* Commit init framework

* Co-authored-by: Yuante Li (FESCO Adecco Human Resources) <v-yuanteli@microsoft.com>
Co-authored-by: XianBW <XianBW@users.noreply.github.com>

* add an import

* refine the whole framework

* benchmark related framework

* fix black and isort errors

* move requirements to folder

* fix black again

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: xuyang1 <xuyang1@microsoft.com>
2024-06-28 11:45:23 +08:00

30 lines
844 B
Python

from pathlib import Path
DIRNAME = Path(__file__).absolute().resolve().parent
from rdagent.model_implementation.benchmark.eval import ModelImpValEval
from rdagent.model_implementation.one_shot import ModelTaskGen
from rdagent.model_implementation.task import ModelImpLoader, ModelTaskLoderJson
mtl = ModelTaskLoderJson("TODO: A Path to json")
task_l = mtl.load()
mtg = ModelTaskGen()
impl_l = mtg.generate(task_l)
# TODO: Align it with the benchmark framework after @wenjun's refine the evaluation part.
# Currently, we just handcraft a workflow for fast evaluation.
mil = ModelImpLoader(DIRNAME.parent.parent / "model_implementation" / "benchmark" / "gt_code")
mie = ModelImpValEval()
# Evaluation:
eval_l = []
for impl in impl_l:
gt_impl = mil.load(impl.target_task)
eval_l.append(mie.evaluate(gt_impl, impl))
print(eval_l)