lightweight-neural-architecture-search

(★ 450)

This is a collection of our zero-cost NAS and efficient vision applications.

File Explorer

Download Latest Version (.zip)

- - E3D_X3DL_FLOPs.py
  - E3D_X3DM_FLOPs.py
  - E3D_X3DS_FLOPs.py
  - README.md
- - deepmad_29M_224.py
  - deepmad_29M_288.py
  - deepmad_50M.py
  - deepmad_89M.py
  - deepmad_R18_FLOPs.py
  - deepmad_R34_FLOPs.py
  - deepmad_R50_FLOPs.py
  - MBV2_FLOPs.py
  - R50_FLOPs.py
  - README.md
- - damoyolo_k1kx_small.py
  - damoyolo_k1kx_tiny.py
  - damoyolo_kxkx_medium.py
- - R50_FLOPs.py
  - R50_FLOPs_predictor.py
  - README.md
- - Mixed_19d2G.py
  - Mixed_7d0G.py
  - README.md
- arch.png
- - __init__.py
  - file.py
  - io.py
- - __init__.py
  - config.py
  - config_ds.py
  - constant.py
  - data_utils.py
  - error.py
  - file_utils.py
  - import_utils.py
  - json_utils.py
  - logger.py
  - megatron_utils.py
  - metric.py
  - model_tag.py
  - plugins.py
  - registry.py
  - tensor_utils.py
  - timer.py
  - torch_utils.py
  - type_assert.py
  - typing.py
- __init__.py
- version.py
- nas.txt
- tests.txt
- - __init__.py
  - base.py
  - budgets.py
  - builder.py
  - README.md
- - __init__.py
  - population.py
  - README.md
- - __init__.py
  - builder.py
  - op_predictor.py
  - robust_gpu_predictor.py
- - __init__.py
  - base.py
  - builder.py
  - cnn3dnet.py
  - cnnnet.py
  - README.md
- - __init__.py
  - builder.py
  - compute_deepmad.py
  - compute_ensemble.py
  - compute_madnas.py
  - compute_random.py
  - compute_stentr.py
  - README.md
- - __init__.py
  - base.py
  - builder.py
  - README.md
  - searcher.py
  - synchonizer.py
- - __init__.py
  - base.py
  - builder.py
  - random_sample.py
  - README.md
  - space_3d_k1dwk1.py
  - space_k1dwk1.py
  - space_k1dwsek1.py
  - space_k1kx.py
  - space_k1kxk1.py
  - space_kxkx.py
  - space_quant_k1dwk1.py
  - space_utils.py
- - __init__.py
  - README.md
  - strategy.py
- - __init__.py
  - dict_action.py
  - dist_utils.py
  - file_utils.py
  - import_utils.py
  - logger.py
  - misc.py
- __init__.py
- dist_search.sh
- export.py
- local_search.sh
- search.py
.gitignore
get_started.md
installation.md
LICENSE
MANIFEST.in
NOTICE
README.md
setup.cfg
setup.py

# Installation Guide

1. Get the code

git clone https://github.com/alibaba/lightweight-neural-architecture-search

Downloads the entire project code from GitHub to your computer.

cd lightweight-neural-architecture-search

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install .

Installs the package published on PyPI directly — no need to clone the source.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.