iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update docs

Browse Source
This commit is contained in:
D-X-Y
2020-09-17 11:00:08 +00:00
parent 386184fef8
commit 470d9a5de2
5 changed files with 5 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
lib/nas_201_api/__init__.py
View File

@@ -1,8 +1,8 @@
#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
#####################################################################
# This API will be updated after 2020.09.16. #
# Please use our new API for NATS-Bench, which is #
# This API will not be updated after 2020.09.16. #
# Please use our new API in NATS-Bench, which is #
# more efficient and contains info of more architecture candidates. #
#####################################################################
from .api_utils import ArchResults, ResultsCount

2
lib/nas_201_api/api_201.py
View File

@@ -7,7 +7,7 @@
# [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.
# [2020.03.16] NAS-Bench-201-v1_1-096897.pth : 2225 architectures are trained once, 5439 archiitectures are trained twice, 7961 architectures are trained three times on all training sets. For the hyper-parameters with the total epochs of 12, each model is trained on CIFAR-10, CIFAR-100, ImageNet16-120 once, and is trained on CIFAR-10-VALID twice.
#
# I'm still actively enhancing this benchmark. Please feel free to contact me if you have any question w.r.t. NAS-Bench-201.
# I'm still actively enhancing our benchmark, while for the future benchmark file, please follow news from NATS-Bench (an extended version of NAS-Bench-201).
#
import os, copy, random, torch, numpy as np
from pathlib import Path

2
lib/nas_201_api/api_utils.py
View File

@@ -7,8 +7,6 @@
# We also define the class ArchResults, which contains all information of a single architecture trained by one kind of hyper-parameters on three datasets.
# We also define the class ResultsCount, which contains all information of a single trial for a single architecture.
############################################################################################
# History:
# [2020.06.30] The first version.
#
import os, abc, copy, random, torch, numpy as np
from pathlib import Path