iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests 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
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]. 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. 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]. 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 `$TORCH_HOME` (`~/.torch/` by default). If you want to generate NAS-Bench-102 or similar NAS datasets or training models by yourself, you need these data. It is recommended to put these data into `$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 `$TORCH_HOME` (`~/.torch/` by default).
``` ```
from nas_102_api import NASBench102API from nas_102_api import NASBench102API
api = NASBench102API('$path_to_meta_nas_bench_file') 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]`: 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: `NASBench102API` is the topest level api. Please see the following usages:
``` ```
from nas_102_api import NASBench102API as API 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 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). 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) ## [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. 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). You could see the highlight of our Transformable Architecture Search (TAS) at our [project page](https://xuanyidong.com/assets/projects/NeurIPS-2019-TAS.html).