mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 07:57:44 +00:00
Xu Yang
1d9b4cd2ec
* use CoSTEER as component name * rename factorimplementation to avoid confusion * rename modelimplementation * align benchmark and evolving evaluators * add scenario to evaluator init function * rename all factorimplementationknowledge in CoSTEER * remove all scenario related information in component * remove useless code --------- Co-authored-by: xuyang1 <xuyang1@microsoft.com>
Preparation
Install Pytorch
CPU CUDA will be enough for verify the implementation
Please install pytorch based on your system. Here is an example on my system
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
pip3 install torch_geometric
Tasks
Task Extraction
From paper to task.
# python rdagent/app/model_implementation/task_extraction.py
# It may based on rdagent/document_reader/document_reader.py
python rdagent/components/task_implementation/model_implementation/task_extraction.py ./PaperImpBench/raw_paper/
Complete workflow
From paper to implementation
# Similar to
# rdagent/app/factor_extraction_and_implementation/factor_extract_and_implement.py
Paper benchmark
# TODO: it does not work well now.
python rdagent/app/model_implementation/eval.py
TODO:
- Create reasonable benchmark
- with uniform input
- manually create task
- Create reasonable evaluation metrics