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

update README

Browse Source
This commit is contained in:
D-X-Y
2019-09-28 19:58:19 +10:00
parent 05ab2729c6
commit c2ba1bae57
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -17,7 +17,6 @@ Some methods use knowledge distillation (KD), which require pre-trained models.
## [Network Pruning via Transformable Architecture Search](https://arxiv.org/abs/1905.09717)
<img src="https://d-x-y.github.com/resources/paper-icon/NIPS-2019-TAS.png" width="700">
Use `bash ./scripts/prepare.sh` to prepare data splits for `CIFAR-10`, `CIFARR-100`, and `ILSVRC2012`.
@@ -43,6 +42,7 @@ args: `cifar10` indicates the dataset name, `ResNet56` indicates the basemodel n
## One-Shot Neural Architecture Search via Self-Evaluated Template Network
<img src="https://d-x-y.github.com/resources/paper-icon/ICCV-2019-SETN.png" width="550">
Train the searched SETN-searched CNN on CIFAR-10, CIFAR-100, and ImageNet.
```
CUDA_VISIBLE_DEVICES=0 bash ./scripts/nas-infer-train.sh cifar10 SETN 96 -1
@@ -55,6 +55,8 @@ Searching codes come soon!
## [Searching for A Robust Neural Architecture in Four GPU Hours](http://openaccess.thecvf.com/content_CVPR_2019/papers/Dong_Searching_for_a_Robust_Neural_Architecture_in_Four_GPU_Hours_CVPR_2019_paper.pdf)
<img src="https://d-x-y.github.com/resources/paper-icon/CVPR-2019-GDAS.png" width="450">
The old version is located at [`others/GDAS`](https://github.com/D-X-Y/NAS-Projects/tree/master/others/GDAS) and a paddlepaddle implementation is locate at [`others/paddlepaddle`](https://github.com/D-X-Y/NAS-Projects/tree/master/others/paddlepaddle).
Train the searched GDAS-searched CNN on CIFAR-10, CIFAR-100, and ImageNet.