Go to file
Xuanyi Dong 3734384b68 update
2019-03-30 00:50:18 +08:00
configs update codes 2019-02-01 04:03:35 +11:00
data init 2019-02-01 02:40:20 +11:00
exps-cnn update 2019-03-30 00:50:18 +08:00
exps-rnn update 2019-03-28 23:21:03 +08:00
lib update codes 2019-02-02 22:27:36 +11:00
output update 2019-03-30 00:50:18 +08:00
scripts-cluster update 2019-03-30 00:50:18 +08:00
scripts-cnn update 2019-03-30 00:50:18 +08:00
scripts-rnn update 2019-03-30 00:50:18 +08:00
.gitignore init 2019-02-01 01:27:38 +11:00
LICENSE init 2019-02-01 01:27:38 +11:00
README.md update 2019-03-30 00:50:18 +08:00

GDAS

By Xuanyi Dong and Yi Yang

University of Technology Sydney

Requirements

  • PyTorch 1.0
  • Python 3.6
  • opencv
conda install pytorch torchvision cuda100 -c pytorch

Algorithm

Train the searched CNN on CIFAR

bash ./scripts-cnn/train-cifar.sh 0 GDAS_FG cifar10  cut
bash ./scripts-cnn/train-cifar.sh 0 GDAS_F1 cifar10  cut
bash ./scripts-cnn/train-cifar.sh 0 GDAS_V1 cifar100 cut

Train the searched CNN on ImageNet

bash ./scripts-cnn/train-imagenet.sh 0 GDAS_F1 52 14
bash ./scripts-cnn/train-imagenet.sh 0 GDAS_V1 50 14

Train the searched RNN

CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-PTB.sh DARTS_V1
CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-PTB.sh DARTS_V2
CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-PTB.sh GDAS
CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-WT2.sh DARTS_V1
CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-WT2.sh DARTS_V2
CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-WT2.sh GDAS