iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update NAS-Bench-201 status

Browse Source
This commit is contained in:
D-X-Y 2020-02-26 08:09:43 +11:00
parent e0f131caac
commit 8b6df42f1f
3 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docs/NAS-Bench-201.md
View File

@ -20,9 +20,10 @@ You can simply type `pip install nas-bench-201` to install our api. Please see s
The benchmark file of NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/open?id=1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs) or [Baidu-Wangpan (code:6u5d)](https://pan.baidu.com/s/1CiaNH6C12zuZf7q-Ilm09w). The benchmark file of NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/open?id=1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs) or [Baidu-Wangpan (code:6u5d)](https://pan.baidu.com/s/1CiaNH6C12zuZf7q-Ilm09w).
You can move it to anywhere you want and send its path to our API for initialization. You can move it to anywhere you want and send its path to our API for initialization.
- v1.0: `NAS-Bench-201-v1_0-e61699.pth`, where `e61699` is the last six digits for this file. It contains all information except for the trained weights of each trial. - [2020.02.25] v1.0: `NAS-Bench-201-v1_0-e61699.pth`, where `e61699` is the last six digits for this file. It contains all information except for the trained weights of each trial.
- v1.0: The full data of each architecture can be download from [Google Drive](https://drive.google.com/open?id=1X2i-JXaElsnVLuGgM4tP-yNwtsspXgdQ) (about 226GB). This compressed folder has 15625 files containing the the trained weights. - [2020.02.25] v1.0: The full data of each architecture can be download from [Google Drive](https://drive.google.com/open?id=1X2i-JXaElsnVLuGgM4tP-yNwtsspXgdQ) (about 226GB). This compressed folder has 15625 files containing the the trained weights.
- v1.0: Checkpoints for 3 runs of each baseline NAS algorithm are provided in [Google Drive](https://drive.google.com/open?id=1eAgLZQAViP3r6dA0_ZOOGG9zPLXhGwXi). - [2020.02.25] v1.0: Checkpoints for 3 runs of each baseline NAS algorithm are provided in [Google Drive](https://drive.google.com/open?id=1eAgLZQAViP3r6dA0_ZOOGG9zPLXhGwXi).
- [2020.03.08] v2.0: coming soon (results of two set of hyper-parameters avaliable on all three datasets)
The training and evaluation data used in NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/open?id=1L0Lzq8rWpZLPfiQGd6QR8q5xLV88emU7) or [Baidu-Wangpan (code:4fg7)](https://pan.baidu.com/s/1XAzavPKq3zcat1yBA1L2tQ). The training and evaluation data used in NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/open?id=1L0Lzq8rWpZLPfiQGd6QR8q5xLV88emU7) or [Baidu-Wangpan (code:4fg7)](https://pan.baidu.com/s/1XAzavPKq3zcat1yBA1L2tQ).
It is recommended to put these data into `$TORCH_HOME` (`~/.torch/` by default). If you want to generate NAS-Bench-201 or similar NAS datasets or training models by yourself, you need these data. It is recommended to put these data into `$TORCH_HOME` (`~/.torch/` by default). If you want to generate NAS-Bench-201 or similar NAS datasets or training models by yourself, you need these data.

2
lib/nas_201_api/__init__.py
View File

@ -4,4 +4,4 @@
from .api import NASBench201API from .api import NASBench201API
from .api import ArchResults, ResultsCount from .api import ArchResults, ResultsCount
NAS_BENCH_201_API_VERSION="v1.1" NAS_BENCH_201_API_VERSION="v1.1" # [2020.02.25]

4
lib/nas_201_api/api.py
View File

@ -3,8 +3,8 @@
############################################################################################ ############################################################################################
# NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search, ICLR 2020 # # NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search, ICLR 2020 #
############################################################################################ ############################################################################################
# NAS-Bench-201-v1_0-e61699.pth : 6219 architectures are trained once, 1621 architectures are trained twice, 7785 architectures are trained three times. `LESS` only supports CIFAR10-VALID. # [2020.02.25] NAS-Bench-201-v1_0-e61699.pth : 6219 architectures are trained once, 1621 architectures are trained twice, 7785 architectures are trained three times. `LESS` only supports CIFAR10-VALID.
# # [2020.03.08] Next version (coming soon)
# #
# #
import os, sys, copy, random, torch, numpy as np import os, sys, copy, random, torch, numpy as np