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

update NAS-Bench-102

Browse Source
This commit is contained in:
D-X-Y 2019-12-21 14:42:51 +11:00
parent 7b05594edb
commit 31c6e2bcef
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
NAS-Bench-102.md
View File

@ -16,6 +16,7 @@ Note: please use `PyTorch >= 1.2.0` and `Python >= 3.6.0`.
The benchmark file of NAS-Bench-102 can be downloaded from [Google Drive](https://drive.google.com/open?id=1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs) or [Baidu-Wangpan].
You can move it to anywhere you want and send its path to our API for initialization.
- v1.0: `NAS-Bench-102-v1_0-e61699.pth`, where `e61699` is the last six digits for this file.
The training and evaluation data used in NAS-Bench-102 can be downloaded from [Google Drive](https://drive.google.com/open?id=1L0Lzq8rWpZLPfiQGd6QR8q5xLV88emU7) or [Baidu-Wangpan].
It is recommended to put these data into `$TORCH_HOME` (`~/.torch/` by default). If you want to generate NAS-Bench-102 or similar NAS datasets or training models by yourself, you need these data.
@ -26,7 +27,7 @@ It is recommended to put these data into `$TORCH_HOME` (`~/.torch/` by default).
```
from nas_102_api import NASBench102API
api = NASBench102API('$path_to_meta_nas_bench_file')
api = NASBench102API('NAS-Bench-102-v1_0.pth')
api = NASBench102API('NAS-Bench-102-v1_0-e61699.pth')
```
2. Show the number of architectures `len(api)` and each architecture `api[i]`:
@ -107,7 +108,7 @@ print(archRes.get_metrics('cifar10-valid', 'x-valid', None, True)) # print loss
`NASBench102API` is the topest level api. Please see the following usages:
```
from nas_102_api import NASBench102API as API
api = API('NAS-Bench-102-v1_0.pth')
api = API('NAS-Bench-102-v1_0-e61699.pth')
api.show(-1) # show info of all architectures
```

2
README.md
View File

@ -32,6 +32,8 @@ flop, param = get_model_infos(net, (1,3,32,32))
We build a new benchmark for neural architecture search, please see more details in [NAS-Bench-102.md](https://github.com/D-X-Y/NAS-Projects/blob/master/NAS-Bench-102.md).
The benchmark data file (v1.0) is `NAS-Bench-102-v1_0-e61699.pth`, which can be downloaded from [Google Drive](https://drive.google.com/open?id=1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs).
## [Network Pruning via Transformable Architecture Search](https://arxiv.org/abs/1905.09717)
In this paper, we proposed a differentiable searching strategy for transformable architectures, i.e., searching for the depth and width of a deep neural network.
You could see the highlight of our Transformable Architecture Search (TAS) at our [project page](https://xuanyidong.com/assets/projects/NeurIPS-2019-TAS.html).