A benchmark for NAS algorithms
Project description
Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment [arXiv]
Preparation Steps
-
Download the following two requried files:
-
database.zip
file from Google Drive or Baidu云盘(提取码:mhgs) -
data.zip
file from Google Drive
-
-
pip install evoxbench
to install the benchmark. -
Configure the benchmark via the following steps:
from evoxbench.database.init import config
config("Path to databae", "Path to data")
# For example
# If you have the following structure
# /home/Downloads/
# └─ database/
# | | __init__.py
# | | db.sqlite3
# | | ...
# |
# └─ data/
# └─ darts/
# └─ mnv3/
# └─ ...
# Then you should do:
# config("/home/Downloads/database", "/home/Downloads/data")
Database
Visit this webpage for more information: https://github.com/liuxukun2000/evoxdatabase
Acknowledgement
Codes are developed upon: NAS-Bench-101 , NAS-Bench-201, NAS-Bench-301 , NATS-Bench , Once for All , AutoFormer, Django , pymoo
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
evoxbench-1.0.2.tar.gz
(94.2 kB
view hashes)
Built Distribution
evoxbench-1.0.2-py3-none-any.whl
(175.2 kB
view hashes)
Close
Hashes for evoxbench-1.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ad885d7586b119d4f11378d4b6f50a73cb6b1d70512cbe8f8da417a0cdb0012d |
|
MD5 | bc02f4ed8b310f39f7d1b05c4ab92550 |
|
BLAKE2b-256 | efe862d2889488548e8686790a7c1902dc678e12cf3b800eba8817218d776f44 |