iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions 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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/NATS-Bench.md
View File

@ -31,7 +31,7 @@ To merge the chunks into the original full archive, you can use `cat file_name*
| Date | benchmark file (tss) | archive (tss) | full archive (tss) | benchmark file (sss) | archive (sss) | full archive (sss) | | Date | benchmark file (tss) | archive (tss) | full archive (tss) | benchmark file (sss) | archive (sss) | full archive (sss) |
|:-----------|:---------------------:|:-------------:|:------------------:|:-------------------------------:|:--------------------------:|:------------------:| |:-----------|:---------------------:|:-------------:|:------------------:|:-------------------------------:|:--------------------------:|:------------------:|
| 2020.08.31 | [NATS-tss-v1_0-3ffb9.pickle.pbz2](https://drive.google.com/file/d/1vzyK0UVH2D3fTpa1_dSWnp1gvGpAxRul/view?usp=sharing) | [NATS-tss-v1_0-3ffb9-simple.tar](https://drive.google.com/file/d/17_saCsj_krKjlCBLOJEpNtzPXArMCqxU/view?usp=sharing) | NATS-tss-v1_0-3ffb9-full | [NATS-sss-v1_0-50262.pickle.pbz2](https://drive.google.com/file/d/1IabIvzWeDdDAWICBzFtTCMXxYWPIOIOX/view?usp=sharing) | [NATS-sss-v1_0-50262-simple.tar](https://drive.google.com/file/d/1scOMTUwcQhAMa_IMedp9lTzwmgqHLGgA/view?usp=sharing) | [NATS-sss-v1_0-50262-full](api.reload(index=12)) | | 2020.08.31 | [NATS-tss-v1_0-3ffb9.pickle.pbz2](https://drive.google.com/file/d/1vzyK0UVH2D3fTpa1_dSWnp1gvGpAxRul/view?usp=sharing) | [NATS-tss-v1_0-3ffb9-simple.tar](https://drive.google.com/file/d/17_saCsj_krKjlCBLOJEpNtzPXArMCqxU/view?usp=sharing) | [NATS-tss-v1_0-3ffb9-full](https://drive.google.com/drive/folders/17S2Xg_rVkUul4KuJdq0WaWoUuDbo8ZKB?usp=sharing) | [NATS-sss-v1_0-50262.pickle.pbz2](https://drive.google.com/file/d/1IabIvzWeDdDAWICBzFtTCMXxYWPIOIOX/view?usp=sharing) | [NATS-sss-v1_0-50262-simple.tar](https://drive.google.com/file/d/1scOMTUwcQhAMa_IMedp9lTzwmgqHLGgA/view?usp=sharing) | [NATS-sss-v1_0-50262-full](api.reload(index=12)) |
1, create the benchmark instance: 1, create the benchmark instance:

2
docs/NeurIPS-2019-TAS.md
View File

@ -25,7 +25,7 @@ We provide some logs at [Google Drive](https://drive.google.com/open?id=1_qUY4DT
## Usage ## Usage
Use `bash ./scripts/prepare.sh` to prepare data splits for `CIFAR-10`, `CIFARR-100`, and `ILSVRC2012`. Use `bash ./scripts/prepare.sh` to prepare data splits for `CIFAR-10`, `CIFARR-100`, and `ILSVRC2012`.
If you do not have `ILSVRC2012` data, pleasee comment L12 in `./scripts/prepare.sh`. If you do not have `ILSVRC2012` data, please comment L12 in `./scripts/prepare.sh`.
args: `cifar10` indicates the dataset name, `ResNet56` indicates the basemodel name, `CIFARX` indicates the searching hyper-parameters, `0.47/0.57` indicates the expected FLOP ratio, `-1` indicates the random seed. args: `cifar10` indicates the dataset name, `ResNet56` indicates the basemodel name, `CIFARX` indicates the searching hyper-parameters, `0.47/0.57` indicates the expected FLOP ratio, `-1` indicates the random seed.

4
lib/nas_201_api/__init__.py
View File

@ -1,8 +1,8 @@
##################################################### #####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 # # Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
##################################################################### #####################################################################
# This API will be updated after 2020.09.16. # # This API will not be updated after 2020.09.16. #
# Please use our new API for NATS-Bench, which is # # Please use our new API in NATS-Bench, which is #
# more efficient and contains info of more architecture candidates. # # more efficient and contains info of more architecture candidates. #
##################################################################### #####################################################################
from .api_utils import ArchResults, ResultsCount 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. # [2020.02.25] 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. # [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 import os, copy, random, torch, numpy as np
from pathlib import Path 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 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. # 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 import os, abc, copy, random, torch, numpy as np
from pathlib import Path from pathlib import Path