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

fix small bugs in DARTS-V1 for NASNet-Space

Browse Source
This commit is contained in:
D-X-Y
2020-01-17 22:28:33 +11:00
parent db2760c260
commit c2ff845d1b
3 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/ICLR-2019-DARTS.md
View File

@@ -4,17 +4,22 @@ DARTS: Differentiable Architecture Search is accepted by ICLR 2019.
In this paper, Hanxiao proposed a differentiable neural architecture search method, named as DARTS.
Recently, DARTS becomes very popular due to its simplicity and performance.
**Run DARTS on the NAS-Bench-201 search space**:
## Run DARTS on the NAS-Bench-201 search space
```
CUDA_VISIBLE_DEVICES=0 bash ./scripts-search/algos/DARTS-V2.sh cifar10 1 -1
CUDA_VISIBLE_DEVICES=0 bash ./scripts-search/algos/GDAS.sh cifar10 1 -1
```
**Run the first-order DARTS on the NASNet search space**:
## Run the first-order DARTS on the NASNet/DARTS search space
This command will start to use the first-order DARTS to search architectures on the DARTS search space.
```
CUDA_VISIBLE_DEVICES=0 bash ./scripts-search/DARTS1V-search-NASNet-space.sh cifar10 -1
```
After searching, if you want to train the searched architecture found by the above scripts, you need to add the config of that architecture (will be printed in log) in [genotypes.py](https://github.com/D-X-Y/AutoDL-Projects/blob/master/lib/nas_infer_model/DXYs/genotypes.py).
In future, I will add a more eligent way to train the searched architecture from the DARTS search space.
# Citation
```