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

update

Browse Source
This commit is contained in:
Xuanyi Dong
2019-03-30 00:50:18 +08:00
parent a94a67b55d
commit 3734384b68
29 changed files with 93 additions and 1184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@@ -13,13 +13,6 @@ conda install pytorch torchvision cuda100 -c pytorch
## Algorithm
Searching CNNs
```
bash ./scripts-cnn/search.sh 1 base cifar10
bash ./scripts-cnn/DMS-V-TrainV3.sh 1
bash ./scripts-cnn/search-acc-v2.sh 3 acc2
```
Train the searched CNN on CIFAR
```
bash ./scripts-cnn/train-cifar.sh 0 GDAS_FG cifar10 cut
@@ -36,10 +29,10 @@ bash ./scripts-cnn/train-imagenet.sh 0 GDAS_V1 50 14
Train the searched RNN
```
bash ./scripts-rnn/train-PTB.sh 0 DARTS_V1
bash ./scripts-rnn/train-PTB.sh 0 DARTS_V2
bash ./scripts-rnn/train-PTB.sh 0 GDAS
bash ./scripts-rnn/train-WT2.sh 0 DARTS_V1
bash ./scripts-rnn/train-WT2.sh 0 DARTS_V2
bash ./scripts-rnn/train-WT2.sh 0 GDAS
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
```

30
TEMP/DMS-V-Train.sh
View File

@@ -1,30 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 3 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 3 parameters for the GPUs and the epochs and the cutout"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=acc2
cutout=$3
dataset=cifar10
epoch=$2
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.05 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--tau_max 10 --tau_min 4 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

57
TEMP/README.md
View File

@@ -1,57 +0,0 @@
# Neural-Architecture-Search
### Baseline
```
bash ./scripts-nas/search.sh 1 base cifar10
bash ./scripts-nas/search.sh 1 share
bash ./scripts-nas/batch-base-search.sh 1
bash ./scripts-nas/batch-base-model.sh 1
```
### Meta
```
bash ./scripts-nas/meta-search.sh 0 meta 20 5
```
### Acceleration
```
bash ./scripts-nas/search-acc-v2.sh 3 acc2
bash ./scripts-nas/DMS-V-Train.sh 0
bash ./scripts-nas/search-acc-simple.sh 3 NetworkV2
```
### Base Model Training
```
bash ./scripts-nas/train-model.sh 3 AmoebaNet
bash ./scripts-nas/train-model.sh 3 NASNet
bash ./scripts-nas/train-model.sh 3 DARTS_V1
bash ./scripts-nas/train-model-simple.sh 3 AmoebaNet
bash ./scripts-nas/train-imagenet.sh 3 DARTS_V2 50 14
bash scripts-nas/TRAIN-BASE.sh 0 PNASNet cifar10 nocut 48 11
bash scripts-nas/TRAIN-BASE.sh 0 AmoebaNet cifar10 nocut 36 20
bash scripts-nas/TRAIN-BASE.sh 0 NASNet cifar10 nocut 33 20
bash scripts-nas/TRAIN-BASE.sh 0 DMS_F1 cifar10 nocut 36 20
bash scripts-nas/TRAIN-BASE.sh 0 DMS_V1 cifar10 nocut 36 20
bash scripts-nas/TRAIN-BASE.sh 0 GDAS_CC cifar10 nocut 36 20
bash scripts-nas/train-imagenet.sh 3 DMS_F1 52 14
bash scripts-nas/train-imagenet.sh 3 DMS_V1 50 14
bash scripts-nas/TRAIN-BASE.sh 0 DMS_V1 cifar10 nocut 36 20
```
### Visualization
```
python ./exps-nas/vis-arch.py --checkpoint --save_dir
python ./exps-nas/cvpr-vis.py --save_dir ./snapshots/NAS-VIS/
```
### Test datasets
```
cd ./lib/datasets/
python test_NLP.py
```

30
TEMP/TRAIN-BASE.sh
View File

@@ -1,30 +0,0 @@
#!/usr/bin/env sh
# bash scripts-nas/TRAIN-BASE.sh 0 DMS_V1 cifar10 nocut init-channel layers
if [ "$#" -ne 6 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 6 parameters for the GPUs, the architecture, the dataset, the config, the initial channel, and the number of layers"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
dataset=$3
config=$4
C=$5
N=$6
SAVED=./snapshots/NAS/${arch}-${C}-${N}-${dataset}-${config}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/train_base.py \
--data_path $TORCH_HOME/cifar.python \
--dataset ${dataset} --arch ${arch} \
--save_path ${SAVED} \
--grad_clip 5 \
--init_channels ${C} --layers ${N} \
--model_config ./configs/nas-cifar-cos-${config}.config \
--print_freq 100 --workers 8

23
TEMP/batch-base-model.sh
View File

@@ -1,23 +0,0 @@
#!/usr/bin/env sh
set -e
if [ "$#" -ne 1 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 1 parameters for the GPUs"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
bash ./scripts-nas/train-model.sh ${gpus} AmoebaNet 0
bash ./scripts-nas/train-model.sh ${gpus} NASNet 0
bash ./scripts-nas/train-model.sh ${gpus} DARTS_V1 0
bash ./scripts-nas/train-model.sh ${gpus} DARTS_V2 0

19
TEMP/batch-base-search.sh
View File

@@ -1,19 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 1 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 1 parameters for the GPUs"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
Times="1 2 3"
for time in ${Times}; do
bash ./scripts-nas/search.sh ${gpus}
done

30
TEMP/meta-search.sh
View File

@@ -1,30 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 4 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 4 parameters for the GPUs and the network and N-way and K-shot"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
n_way=$3
k_shot=$4
cutout=16
epoch=60
SAVED=./snapshots/NAS/Meta-Search-${arch}-N${n_way}-K${k_shot}-cut${cutout}-${epoch}
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/meta_search.py \
--data_path $TORCH_HOME/tiered-imagenet \
--arch ${arch} --n_way ${n_way} --k_shot ${k_shot} \
--save_path ${SAVED} \
--learning_rate_max 0.001 --learning_rate_min 0.0001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos-cut.config \
--print_freq 200 --workers 16

29
TEMP/search-acc-simple.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=100
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E100
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos-simple.config \
--print_freq 100 --workers 8

29
TEMP/search-acc-v2-E150.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=150
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

29
TEMP/search-acc-v2-E200.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=200
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

29
TEMP/search-acc-v2-E300.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=300
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

29
TEMP/search-acc-v2-E50.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=50
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

29
TEMP/search-acc-v2.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=100
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/acc_search_v2.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq 100 --workers 8

45
TEMP/search.sh
View File

@@ -1,45 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 3 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 3 parameters for the GPUs and the network and the dataset"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=$3
epoch=50
SAVED=./snapshots/NAS/Search-${arch}-${dataset}-cut${cutout}-${epoch}
if [ "$dataset" == "cifar10" ] ;then
dataset_root=$TORCH_HOME/cifar.python
print_freq=100
elif [ "$dataset" == "cifar100" ] ;then
dataset_root=$TORCH_HOME/cifar.python
print_freq=100
elif [ "$dataset" == "tiered" ] ;then
dataset_root=$TORCH_HOME/tiered-imagenet
print_freq=500
else
echo 'invalid dataset-name :'${dataset}
exit 1
fi
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/train_search.py \
--data_path ${dataset_root} \
--arch ${arch} \
--dataset ${dataset} --batch_size 64 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--manualSeed 3858 \
--model_config ./configs/nas-cifar-cos.config \
--print_freq ${print_freq} --workers 8

9
TEMP/vis.sh
View File

@@ -1,9 +0,0 @@
#!/usr/bin/env sh
seeds="seed-8167 seed-908 seed-9242"
for seed in ${seeds}; do
python ./exps-nas/vis-arch.py --checkpoint ./snapshots/NAS/Search-cifar10-cut16-100/${seed}/checkpoint-search.pth \
--save_dir ./snapshots/NAS-VIS/Search-cut16-100/${seed}
done

313
exps-cnn/DARTS-Search.py
View File

@@ -1,313 +0,0 @@
# DARTS First Order, Refer to https://github.com/quark0/darts
import os, sys, time, glob, random, argparse
import numpy as np
from copy import deepcopy
import torch
import torch.nn.functional as F
import torchvision.datasets as dset
import torch.backends.cudnn as cudnn
import torchvision.transforms as transforms
from pathlib import Path
lib_dir = (Path(__file__).parent / '..' / 'lib').resolve()
if str(lib_dir) not in sys.path: sys.path.insert(0, str(lib_dir))
from utils import AverageMeter, time_string, convert_secs2time
from utils import print_log, obtain_accuracy
from utils import Cutout, count_parameters_in_MB
from datasets import TieredImageNet
from nas import return_alphas_str, Network, NetworkV1, NetworkF1
from train_utils import main_procedure
from scheduler import load_config
Networks = {'base': Network, 'share': NetworkV1, 'fix': NetworkF1}
parser = argparse.ArgumentParser("CNN")
parser.add_argument('--data_path', type=str, help='Path to dataset')
parser.add_argument('--dataset', type=str, choices=['cifar10', 'cifar100', 'tiered'], help='Choose between Cifar10/100 and TieredImageNet.')
parser.add_argument('--arch', type=str, choices=Networks.keys(), help='Choose networks.')
parser.add_argument('--batch_size', type=int, help='the batch size')
parser.add_argument('--learning_rate_max', type=float, help='initial learning rate')
parser.add_argument('--learning_rate_min', type=float, help='minimum learning rate')
parser.add_argument('--momentum', type=float, help='momentum')
parser.add_argument('--weight_decay', type=float, help='weight decay')
parser.add_argument('--epochs', type=int, help='num of training epochs')
# architecture leraning rate
parser.add_argument('--arch_learning_rate', type=float, default=3e-4, help='learning rate for arch encoding')
parser.add_argument('--arch_weight_decay', type=float, default=1e-3, help='weight decay for arch encoding')
#
parser.add_argument('--init_channels', type=int, help='num of init channels')
parser.add_argument('--layers', type=int, help='total number of layers')
#
parser.add_argument('--cutout', type=int, help='cutout length, negative means no cutout')
parser.add_argument('--grad_clip', type=float, help='gradient clipping')
parser.add_argument('--model_config', type=str , help='the model configuration')
# resume
parser.add_argument('--resume', type=str , help='the resume path')
parser.add_argument('--only_base',action='store_true', default=False, help='only train the searched model')
# split data
parser.add_argument('--validate', action='store_true', default=False, help='split train-data int train/val or not')
parser.add_argument('--train_portion', type=float, default=0.5, help='portion of training data')
# log
parser.add_argument('--workers', type=int, default=2, help='number of data loading workers (default: 2)')
parser.add_argument('--save_path', type=str, help='Folder to save checkpoints and log.')
parser.add_argument('--print_freq', type=int, help='print frequency (default: 200)')
parser.add_argument('--manualSeed', type=int, help='manual seed')
args = parser.parse_args()
assert torch.cuda.is_available(), 'torch.cuda is not available'
if args.manualSeed is None:
args.manualSeed = random.randint(1, 10000)
random.seed(args.manualSeed)
cudnn.benchmark = True
cudnn.enabled = True
torch.manual_seed(args.manualSeed)
torch.cuda.manual_seed_all(args.manualSeed)
def main():
# Init logger
args.save_path = os.path.join(args.save_path, 'seed-{:}'.format(args.manualSeed))
if not os.path.isdir(args.save_path):
os.makedirs(args.save_path)
log = open(os.path.join(args.save_path, 'log-seed-{:}.txt'.format(args.manualSeed)), 'w')
print_log('save path : {}'.format(args.save_path), log)
state = {k: v for k, v in args._get_kwargs()}
print_log(state, log)
print_log("Random Seed: {}".format(args.manualSeed), log)
print_log("Python version : {}".format(sys.version.replace('\n', ' ')), log)
print_log("Torch version : {}".format(torch.__version__), log)
print_log("CUDA version : {}".format(torch.version.cuda), log)
print_log("cuDNN version : {}".format(cudnn.version()), log)
print_log("Num of GPUs : {}".format(torch.cuda.device_count()), log)
args.dataset = args.dataset.lower()
# Mean + Std
if args.dataset == 'cifar10':
mean = [x / 255 for x in [125.3, 123.0, 113.9]]
std = [x / 255 for x in [63.0, 62.1, 66.7]]
elif args.dataset == 'cifar100':
mean = [x / 255 for x in [129.3, 124.1, 112.4]]
std = [x / 255 for x in [68.2, 65.4, 70.4]]
elif args.dataset == 'tiered':
mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Data Argumentation
if args.dataset == 'cifar10' or args.dataset == 'cifar100':
lists = [transforms.RandomHorizontalFlip(), transforms.RandomCrop(32, padding=4), transforms.ToTensor(),
transforms.Normalize(mean, std)]
if args.cutout > 0 : lists += [Cutout(args.cutout)]
train_transform = transforms.Compose(lists)
test_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean, std)])
elif args.dataset == 'tiered':
lists = [transforms.RandomHorizontalFlip(), transforms.RandomCrop(80, padding=4), transforms.ToTensor(), transforms.Normalize(mean, std)]
if args.cutout > 0 : lists += [Cutout(args.cutout)]
train_transform = transforms.Compose(lists)
test_transform = transforms.Compose([transforms.CenterCrop(80), transforms.ToTensor(), transforms.Normalize(mean, std)])
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Datasets
if args.dataset == 'cifar10':
train_data = dset.CIFAR10(args.data_path, train= True, transform=train_transform, download=True)
test_data = dset.CIFAR10(args.data_path, train=False, transform=test_transform , download=True)
num_classes, head = 10, 'cifar'
elif args.dataset == 'cifar100':
train_data = dset.CIFAR100(args.data_path, train= True, transform=train_transform, download=True)
test_data = dset.CIFAR100(args.data_path, train=False, transform=test_transform , download=True)
num_classes, head = 100, 'cifar'
elif args.dataset == 'tiered':
train_data = TieredImageNet(args.data_path, 'train-val', train_transform)
test_data = None
num_classes, head = train_data.n_classes, 'imagenet'
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Data Loader
if args.validate:
indices = list(range(len(train_data)))
split = int(args.train_portion * len(indices))
random.shuffle(indices)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
pin_memory=True, num_workers=args.workers)
test_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:]),
pin_memory=True, num_workers=args.workers)
else:
train_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
# network and criterion
criterion = torch.nn.CrossEntropyLoss().cuda()
basemodel = Networks[args.arch](args.init_channels, num_classes, args.layers, head=head)
model = torch.nn.DataParallel(basemodel).cuda()
print_log("Network : {:}".format(model), log)
print_log("Parameter size = {:.3f} MB".format(count_parameters_in_MB(basemodel.base_parameters())), log)
print_log("Train-transformation : {:}\nTest--transformation : {:}\nClass number : {:}".format(train_transform, test_transform, num_classes), log)
# optimizer and LR-scheduler
base_optimizer = torch.optim.SGD (basemodel.base_parameters(), args.learning_rate_max, momentum=args.momentum, weight_decay=args.weight_decay)
base_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(base_optimizer, float(args.epochs), eta_min=args.learning_rate_min)
arch_optimizer = torch.optim.Adam(basemodel.arch_parameters(), lr=args.arch_learning_rate, betas=(0.5, 0.999), weight_decay=args.arch_weight_decay)
# snapshot
checkpoint_path = os.path.join(args.save_path, 'checkpoint-search.pth')
if args.resume is not None and os.path.isfile(args.resume):
checkpoint = torch.load(args.resume)
start_epoch = checkpoint['epoch']
basemodel.load_state_dict( checkpoint['state_dict'] )
base_optimizer.load_state_dict( checkpoint['base_optimizer'] )
arch_optimizer.load_state_dict( checkpoint['arch_optimizer'] )
base_scheduler.load_state_dict( checkpoint['base_scheduler'] )
genotypes = checkpoint['genotypes']
print_log('Load resume from {:} with start-epoch = {:}'.format(args.resume, start_epoch), log)
elif os.path.isfile(checkpoint_path):
checkpoint = torch.load(checkpoint_path)
start_epoch = checkpoint['epoch']
basemodel.load_state_dict( checkpoint['state_dict'] )
base_optimizer.load_state_dict( checkpoint['base_optimizer'] )
arch_optimizer.load_state_dict( checkpoint['arch_optimizer'] )
base_scheduler.load_state_dict( checkpoint['base_scheduler'] )
genotypes = checkpoint['genotypes']
print_log('Load checkpoint from {:} with start-epoch = {:}'.format(checkpoint_path, start_epoch), log)
else:
start_epoch, genotypes = 0, {}
print_log('Train model-search from scratch.', log)
config = load_config(args.model_config)
if args.only_base:
print_log('---- Only Train the Searched Model ----', log)
main_procedure(config, args.dataset, args.data_path, args, basemodel.genotype(), 36, 20, log)
return
# Main loop
start_time, epoch_time, total_train_time = time.time(), AverageMeter(), 0
for epoch in range(start_epoch, args.epochs):
base_scheduler.step()
need_time = convert_secs2time(epoch_time.val * (args.epochs-epoch), True)
print_log('\n==>>{:s} [Epoch={:03d}/{:03d}] {:s} [LR={:6.4f} ~ {:6.4f}] [Batch={:d}]'.format(time_string(), epoch, args.epochs, need_time, min(base_scheduler.get_lr()), max(base_scheduler.get_lr()), args.batch_size), log)
genotype = basemodel.genotype()
print_log('genotype = {:}'.format(genotype), log)
print_log('{:03d}/{:03d} alphas :\n{:}'.format(epoch, args.epochs, return_alphas_str(basemodel)), log)
# training
train_acc1, train_acc5, train_obj, train_time \
= train(train_loader, test_loader, model, criterion, base_optimizer, arch_optimizer, epoch, log)
total_train_time += train_time
# validation
valid_acc1, valid_acc5, valid_obj = infer(test_loader, model, criterion, epoch, log)
print_log('Base-Search : {:03d}/{:03d} : Train-Acc={:.3f}, Test-Acc={:.3f}'.format(epoch, args.epochs, train_acc1, valid_acc1), log)
# save genotype
genotypes[epoch] = basemodel.genotype()
# save checkpoint
torch.save({'epoch' : epoch + 1,
'args' : deepcopy(args),
'state_dict': basemodel.state_dict(),
'genotypes' : genotypes,
'base_optimizer' : base_optimizer.state_dict(),
'arch_optimizer' : arch_optimizer.state_dict(),
'base_scheduler' : base_scheduler.state_dict()},
checkpoint_path)
print_log('----> Save into {:}'.format(checkpoint_path), log)
# measure elapsed time
epoch_time.update(time.time() - start_time)
start_time = time.time()
print_log('Finish with training time = {:}'.format( convert_secs2time(total_train_time, True) ), log)
# clear GPU cache
#torch.cuda.empty_cache()
#main_procedure(config, 'cifar10', os.environ['TORCH_HOME'] + '/cifar.python', args, basemodel.genotype(), 36, 20, log)
log.close()
def train(train_queue, valid_queue, model, criterion, base_optimizer, arch_optimizer, epoch, log):
data_time, batch_time = AverageMeter(), AverageMeter()
objs, top1, top5 = AverageMeter(), AverageMeter(), AverageMeter()
model.train()
valid_iter = iter(valid_queue)
end = time.time()
for step, (inputs, targets) in enumerate(train_queue):
batch, C, H, W = inputs.size()
#inputs, targets = inputs.cuda(), targets.cuda(non_blocking=True)
targets = targets.cuda(non_blocking=True)
data_time.update(time.time() - end)
# get a random minibatch from the search queue with replacement
try:
input_search, target_search = next(valid_iter)
except:
valid_iter = iter(valid_queue)
input_search, target_search = next(valid_iter)
target_search = target_search.cuda(non_blocking=True)
# update the architecture
arch_optimizer.zero_grad()
output_search = model(input_search)
arch_loss = criterion(output_search, target_search)
arch_loss.backward()
arch_optimizer.step()
# update the parameters
base_optimizer.zero_grad()
logits = model(inputs)
loss = criterion(logits, targets)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.module.base_parameters(), args.grad_clip)
base_optimizer.step()
prec1, prec5 = obtain_accuracy(logits.data, targets.data, topk=(1, 5))
objs.update(loss.item() , batch)
top1.update(prec1.item(), batch)
top5.update(prec5.item(), batch)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if step % args.print_freq == 0 or (step+1) == len(train_queue):
Sstr = ' TRAIN-SEARCH ' + time_string() + ' Epoch: [{:03d}][{:03d}/{:03d}]'.format(epoch, step, len(train_queue))
Tstr = 'Time {batch_time.val:.2f} ({batch_time.avg:.2f}) Data {data_time.val:.2f} ({data_time.avg:.2f})'.format(batch_time=batch_time, data_time=data_time)
Lstr = 'Loss {loss.val:.3f} ({loss.avg:.3f}) Prec@1 {top1.val:.2f} ({top1.avg:.2f}) Prec@5 {top5.val:.2f} ({top5.avg:.2f})'.format(loss=objs, top1=top1, top5=top5)
print_log(Sstr + ' ' + Tstr + ' ' + Lstr, log)
return top1.avg, top5.avg, objs.avg, batch_time.sum
def infer(valid_queue, model, criterion, epoch, log):
objs, top1, top5 = AverageMeter(), AverageMeter(), AverageMeter()
model.eval()
with torch.no_grad():
for step, (inputs, targets) in enumerate(valid_queue):
batch, C, H, W = inputs.size()
targets = targets.cuda(non_blocking=True)
logits = model(inputs)
loss = criterion(logits, targets)
prec1, prec5 = obtain_accuracy(logits.data, targets.data, topk=(1, 5))
objs.update(loss.item() , batch)
top1.update(prec1.item(), batch)
top5.update(prec5.item(), batch)
if step % args.print_freq == 0 or (step+1) == len(valid_queue):
Sstr = ' VALID-SEARCH ' + time_string() + ' Epoch: [{:03d}][{:03d}/{:03d}]'.format(epoch, step, len(valid_queue))
Lstr = 'Loss {loss.val:.3f} ({loss.avg:.3f}) Prec@1 {top1.val:.2f} ({top1.avg:.2f}) Prec@5 {top5.val:.2f} ({top5.avg:.2f})'.format(loss=objs, top1=top1, top5=top5)
print_log(Sstr + ' ' + Lstr, log)
return top1.avg, top5.avg, objs.avg
if __name__ == '__main__':
main()

310
exps-cnn/GDAS-Search.py
View File

@@ -1,310 +0,0 @@
import os, sys, time, glob, random, argparse
import numpy as np
from copy import deepcopy
import torch
import torch.nn.functional as F
import torchvision.datasets as dset
import torch.backends.cudnn as cudnn
import torchvision.transforms as transforms
from pathlib import Path
lib_dir = (Path(__file__).parent / '..' / 'lib').resolve()
if str(lib_dir) not in sys.path: sys.path.insert(0, str(lib_dir))
from utils import AverageMeter, time_string, convert_secs2time
from utils import print_log, obtain_accuracy
from utils import Cutout, count_parameters_in_MB
from nas import Network, NetworkACC2, NetworkV3, NetworkV4, NetworkV5, NetworkFACC1
from nas import return_alphas_str
from train_utils import main_procedure
from scheduler import load_config
Networks = {'base': Network, 'acc2': NetworkACC2, 'facc1': NetworkFACC1, 'NetworkV3': NetworkV3, 'NetworkV4': NetworkV4, 'NetworkV5': NetworkV5}
parser = argparse.ArgumentParser("cifar")
parser.add_argument('--data_path', type=str, help='Path to dataset')
parser.add_argument('--dataset', type=str, choices=['cifar10', 'cifar100'], help='Choose between Cifar10/100 and ImageNet.')
parser.add_argument('--arch', type=str, choices=Networks.keys(), help='Choose networks.')
parser.add_argument('--batch_size', type=int, help='the batch size')
parser.add_argument('--learning_rate_max', type=float, help='initial learning rate')
parser.add_argument('--learning_rate_min', type=float, help='minimum learning rate')
parser.add_argument('--tau_max', type=float, help='initial tau')
parser.add_argument('--tau_min', type=float, help='minimum tau')
parser.add_argument('--momentum', type=float, help='momentum')
parser.add_argument('--weight_decay', type=float, help='weight decay')
parser.add_argument('--epochs', type=int, help='num of training epochs')
# architecture leraning rate
parser.add_argument('--arch_learning_rate', type=float, default=3e-4, help='learning rate for arch encoding')
parser.add_argument('--arch_weight_decay', type=float, default=1e-3, help='weight decay for arch encoding')
#
parser.add_argument('--init_channels', type=int, help='num of init channels')
parser.add_argument('--layers', type=int, help='total number of layers')
#
parser.add_argument('--cutout', type=int, help='cutout length, negative means no cutout')
parser.add_argument('--grad_clip', type=float, help='gradient clipping')
parser.add_argument('--model_config', type=str , help='the model configuration')
# resume
parser.add_argument('--resume', type=str , help='the resume path')
parser.add_argument('--only_base',action='store_true', default=False, help='only train the searched model')
# split data
parser.add_argument('--validate', action='store_true', default=False, help='split train-data int train/val or not')
parser.add_argument('--train_portion', type=float, default=0.5, help='portion of training data')
# log
parser.add_argument('--workers', type=int, default=2, help='number of data loading workers (default: 2)')
parser.add_argument('--save_path', type=str, help='Folder to save checkpoints and log.')
parser.add_argument('--print_freq', type=int, help='print frequency (default: 200)')
parser.add_argument('--manualSeed', type=int, help='manual seed')
args = parser.parse_args()
assert torch.cuda.is_available(), 'torch.cuda is not available'
if args.manualSeed is None:
args.manualSeed = random.randint(1, 10000)
random.seed(args.manualSeed)
cudnn.benchmark = True
cudnn.enabled = True
torch.manual_seed(args.manualSeed)
torch.cuda.manual_seed_all(args.manualSeed)
def main():
# Init logger
args.save_path = os.path.join(args.save_path, 'seed-{:}'.format(args.manualSeed))
if not os.path.isdir(args.save_path):
os.makedirs(args.save_path)
log = open(os.path.join(args.save_path, 'log-seed-{:}.txt'.format(args.manualSeed)), 'w')
print_log('save path : {}'.format(args.save_path), log)
state = {k: v for k, v in args._get_kwargs()}
print_log(state, log)
print_log("Random Seed: {}".format(args.manualSeed), log)
print_log("Python version : {}".format(sys.version.replace('\n', ' ')), log)
print_log("Torch version : {}".format(torch.__version__), log)
print_log("CUDA version : {}".format(torch.version.cuda), log)
print_log("cuDNN version : {}".format(cudnn.version()), log)
print_log("Num of GPUs : {}".format(torch.cuda.device_count()), log)
args.dataset = args.dataset.lower()
# Mean + Std
if args.dataset == 'cifar10':
mean = [x / 255 for x in [125.3, 123.0, 113.9]]
std = [x / 255 for x in [63.0, 62.1, 66.7]]
elif args.dataset == 'cifar100':
mean = [x / 255 for x in [129.3, 124.1, 112.4]]
std = [x / 255 for x in [68.2, 65.4, 70.4]]
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Data Argumentation
if args.dataset == 'cifar10' or args.dataset == 'cifar100':
lists = [transforms.RandomHorizontalFlip(), transforms.RandomCrop(32, padding=4), transforms.ToTensor(),
transforms.Normalize(mean, std)]
if args.cutout > 0 : lists += [Cutout(args.cutout)]
train_transform = transforms.Compose(lists)
test_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean, std)])
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Datasets
if args.dataset == 'cifar10':
train_data = dset.CIFAR10(args.data_path, train= True, transform=train_transform, download=True)
test_data = dset.CIFAR10(args.data_path, train=False, transform=test_transform , download=True)
num_classes = 10
elif args.dataset == 'cifar100':
train_data = dset.CIFAR100(args.data_path, train= True, transform=train_transform, download=True)
test_data = dset.CIFAR100(args.data_path, train=False, transform=test_transform , download=True)
num_classes = 100
else:
raise TypeError("Unknow dataset : {:}".format(args.dataset))
# Data Loader
if args.validate:
indices = list(range(len(train_data)))
split = int(args.train_portion * len(indices))
random.shuffle(indices)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
pin_memory=True, num_workers=args.workers)
test_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:]),
pin_memory=True, num_workers=args.workers)
else:
train_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
# network and criterion
criterion = torch.nn.CrossEntropyLoss().cuda()
basemodel = Networks[args.arch](args.init_channels, num_classes, args.layers)
model = torch.nn.DataParallel(basemodel).cuda()
print_log("Parameter size = {:.3f} MB".format(count_parameters_in_MB(basemodel.base_parameters())), log)
print_log("Train-transformation : {:}\nTest--transformation : {:}".format(train_transform, test_transform), log)
# optimizer and LR-scheduler
base_optimizer = torch.optim.SGD (basemodel.base_parameters(), args.learning_rate_max, momentum=args.momentum, weight_decay=args.weight_decay)
#base_optimizer = torch.optim.Adam(basemodel.base_parameters(), lr=args.learning_rate_max, betas=(0.5, 0.999), weight_decay=args.weight_decay)
base_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(base_optimizer, float(args.epochs), eta_min=args.learning_rate_min)
arch_optimizer = torch.optim.Adam(basemodel.arch_parameters(), lr=args.arch_learning_rate, betas=(0.5, 0.999), weight_decay=args.arch_weight_decay)
# snapshot
checkpoint_path = os.path.join(args.save_path, 'checkpoint-search.pth')
if args.resume is not None and os.path.isfile(args.resume):
checkpoint = torch.load(args.resume)
start_epoch = checkpoint['epoch']
basemodel.load_state_dict( checkpoint['state_dict'] )
base_optimizer.load_state_dict( checkpoint['base_optimizer'] )
arch_optimizer.load_state_dict( checkpoint['arch_optimizer'] )
base_scheduler.load_state_dict( checkpoint['base_scheduler'] )
genotypes = checkpoint['genotypes']
print_log('Load resume from {:} with start-epoch = {:}'.format(args.resume, start_epoch), log)
elif os.path.isfile(checkpoint_path):
checkpoint = torch.load(checkpoint_path)
start_epoch = checkpoint['epoch']
basemodel.load_state_dict( checkpoint['state_dict'] )
base_optimizer.load_state_dict( checkpoint['base_optimizer'] )
arch_optimizer.load_state_dict( checkpoint['arch_optimizer'] )
base_scheduler.load_state_dict( checkpoint['base_scheduler'] )
genotypes = checkpoint['genotypes']
print_log('Load checkpoint from {:} with start-epoch = {:}'.format(checkpoint_path, start_epoch), log)
else:
start_epoch, genotypes = 0, {}
print_log('Train model-search from scratch.', log)
config = load_config(args.model_config)
if args.only_base:
print_log('---- Only Train the Searched Model ----', log)
main_procedure(config, args.dataset, args.data_path, args, basemodel.genotype(), 36, 20, log)
return
# Main loop
start_time, epoch_time, total_train_time = time.time(), AverageMeter(), 0
for epoch in range(start_epoch, args.epochs):
base_scheduler.step()
basemodel.set_tau( args.tau_max - epoch*1.0/args.epochs*(args.tau_max-args.tau_min) )
#if epoch + 2 == args.epochs:
# torch.cuda.empty_cache()
# basemodel.set_gumbel(False)
need_time = convert_secs2time(epoch_time.val * (args.epochs-epoch), True)
print_log('\n==>>{:s} [Epoch={:03d}/{:03d}] {:s} [LR={:6.4f} ~ {:6.4f}] [Batch={:d}], tau={:}'.format(time_string(), epoch, args.epochs, need_time, min(base_scheduler.get_lr()), max(base_scheduler.get_lr()), args.batch_size, basemodel.get_tau()), log)
genotype = basemodel.genotype()
print_log('genotype = {:}'.format(genotype), log)
print_log('{:03d}/{:03d} alphas :\n{:}'.format(epoch, args.epochs, return_alphas_str(basemodel)), log)
# training
train_acc1, train_acc5, train_obj, train_time \
= train(train_loader, test_loader, model, criterion, base_optimizer, arch_optimizer, epoch, log)
total_train_time += train_time
# validation
valid_acc1, valid_acc5, valid_obj = infer(test_loader, model, criterion, epoch, log)
print_log('{:03d}/{:03d}, Train-Accuracy = {:.2f}, Test-Accuracy = {:.2f}'.format(epoch, args.epochs, train_acc1, valid_acc1), log)
# save genotype
genotypes[epoch] = basemodel.genotype()
# save checkpoint
torch.save({'epoch' : epoch + 1,
'args' : deepcopy(args),
'state_dict': basemodel.state_dict(),
'genotypes' : genotypes,
'base_optimizer' : base_optimizer.state_dict(),
'arch_optimizer' : arch_optimizer.state_dict(),
'base_scheduler' : base_scheduler.state_dict()},
checkpoint_path)
print_log('----> Save into {:}'.format(checkpoint_path), log)
# measure elapsed time
epoch_time.update(time.time() - start_time)
start_time = time.time()
print_log('Finish with training time = {:}'.format( convert_secs2time(total_train_time, True) ), log)
# clear GPU cache
#torch.cuda.empty_cache()
#main_procedure(config, args.dataset, args.data_path, args, basemodel.genotype(), 36, 20, log)
log.close()
def train(train_queue, valid_queue, model, criterion, base_optimizer, arch_optimizer, epoch, log):
data_time, batch_time = AverageMeter(), AverageMeter()
objs, top1, top5 = AverageMeter(), AverageMeter(), AverageMeter()
model.train()
valid_iter = iter(valid_queue)
end = time.time()
for step, (inputs, targets) in enumerate(train_queue):
batch, C, H, W = inputs.size()
#inputs, targets = inputs.cuda(), targets.cuda(non_blocking=True)
targets = targets.cuda(non_blocking=True)
# get a random minibatch from the search queue with replacement
try:
input_search, target_search = next(valid_iter)
except:
valid_iter = iter(valid_queue)
input_search, target_search = next(valid_iter)
target_search = target_search.cuda(non_blocking=True)
data_time.update(time.time() - end)
# update the architecture
arch_optimizer.zero_grad()
output_search = model(input_search)
arch_loss = criterion(output_search, target_search)
arch_loss.backward()
arch_optimizer.step()
# update the parameters
base_optimizer.zero_grad()
logits = model(inputs)
loss = criterion(logits, targets)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.module.base_parameters(), args.grad_clip)
base_optimizer.step()
prec1, prec5 = obtain_accuracy(logits.data, targets.data, topk=(1, 5))
objs.update(loss.item() , batch)
top1.update(prec1.item(), batch)
top5.update(prec5.item(), batch)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if step % args.print_freq == 0 or (step+1) == len(train_queue):
Sstr = ' TRAIN-SEARCH ' + time_string() + ' Epoch: [{:03d}][{:03d}/{:03d}]'.format(epoch, step, len(train_queue))
Tstr = 'Time {batch_time.val:.2f} ({batch_time.avg:.2f}) Data {data_time.val:.2f} ({data_time.avg:.2f})'.format(batch_time=batch_time, data_time=data_time)
Lstr = 'Loss {loss.val:.3f} ({loss.avg:.3f}) Prec@1 {top1.val:.2f} ({top1.avg:.2f}) Prec@5 {top5.val:.2f} ({top5.avg:.2f})'.format(loss=objs, top1=top1, top5=top5)
print_log(Sstr + ' ' + Tstr + ' ' + Lstr, log)
return top1.avg, top5.avg, objs.avg, batch_time.sum
def infer(valid_queue, model, criterion, epoch, log):
objs, top1, top5 = AverageMeter(), AverageMeter(), AverageMeter()
model.eval()
with torch.no_grad():
for step, (inputs, targets) in enumerate(valid_queue):
batch, C, H, W = inputs.size()
targets = targets.cuda(non_blocking=True)
logits = model(inputs)
loss = criterion(logits, targets)
prec1, prec5 = obtain_accuracy(logits.data, targets.data, topk=(1, 5))
objs.update(loss.item() , batch)
top1.update(prec1.item(), batch)
top5.update(prec5.item(), batch)
if step % args.print_freq == 0 or (step+1) == len(valid_queue):
Sstr = ' VALID-SEARCH ' + time_string() + ' Epoch: [{:03d}][{:03d}/{:03d}]'.format(epoch, step, len(valid_queue))
Lstr = 'Loss {loss.val:.3f} ({loss.avg:.3f}) Prec@1 {top1.val:.2f} ({top1.avg:.2f}) Prec@5 {top5.val:.2f} ({top5.avg:.2f})'.format(loss=objs, top1=top1, top5=top5)
print_log(Sstr + ' ' + Lstr, log)
return top1.avg, top5.avg, objs.avg
if __name__ == '__main__':
main()

1
exps-cnn/train_utils.py
View File

@@ -1,7 +1,6 @@
import os, sys, time
from copy import deepcopy
import torch
import torchvision.datasets as dset
import torchvision.transforms as transforms

1
exps-cnn/train_utils_imagenet.py
View File

@@ -2,7 +2,6 @@ import os, sys, time
from copy import deepcopy
import torch
import torch.nn as nn
import torchvision.datasets as dset
import torchvision.transforms as transforms

1
output/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
*

29
scripts-cluster/job-script.sh Normal file
View File

@@ -0,0 +1,29 @@
#!/bin/bash
#
echo "CHECK-DATA-DIR START"
cifar_dir="./data/data/cifar.python"
if [ -d ${cifar_dir} ]; then
echo "Find cifar-dir: "${cifar_dir}
else
echo "Can not find cifar-dir: "${cifar_dir}
exit 1
fi
echo "CHECK-DATA-DIR DONE"
sh /home/HGCP_Program/software-install/afs_mount/bin/afs_mount.sh \
COMM_KM_Data COMM_km_2018 \
`pwd`/hadoop-data \
afs://xingtian.afs.baidu.com:9902/user/COMM_KM_Data/dongxuanyi/datasets
echo "PWD: " `pwd`
echo "files:: " `ls`
echo "CUDA_VISIBLE_DEVICES: " ${CUDA_VISIBLE_DEVICES}
# config python
PYTHON_ENV=py36_pytorch1.0_env0.1.3.tar.gz
wget -e "http_proxy=cp01-sys-hic-gpu-02.cp01:8888" http://cp01-sys-hic-gpu-02.cp01/HGCP_DEMO/$PYTHON_ENV > screen.log 2>&1
tar xzf $PYTHON_ENV
alias python="./env/bin/python"
echo "Python: " `which python`

44
scripts-cluster/submit.sh Normal file
View File

@@ -0,0 +1,44 @@
#!/bin/bash
# bash ./scripts-cluster/submit.sh ${QUEUE} ${JOB-NAME} ${GPUs}
#find -name "._*" | xargs rm -rf
ODIR=$(pwd)
FDIR=$(cd $(dirname $0); pwd)
echo "Bash-Dir : "${ODIR}
echo "File-Dir : "${FDIR}
echo "File-Name: "${0}
if [ "$#" -ne 4 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 4 parameters for the queue-name, the job-name, and the number-of-GPUs"
exit 1
fi
find -name "__pycache__" | xargs rm -rf
QUEUE=$1
NAME=$2
GPUs=$3
CMD=$4
TIME=$(date +"%Y-%h-%d-%T")
JOB_SCRIPT="${FDIR}/tmps/job-${TIME}.sh"
cat ${FDIR}/job-script.sh > ${JOB_SCRIPT}
echo ${CMD} >> ${JOB_SCRIPT}
exit 1
HGCP_CLIENT_BIN="${HOME}/.hgcp/software-install/HGCP_client/bin"
${HGCP_CLIENT_BIN}/submit \
--hdfs afs://xingtian.afs.baidu.com:9902 \
--hdfs-user COMM_KM_Data \
--hdfs-passwd COMM_km_2018 \
--hdfs-path /user/COMM_KM_Data/dongxuanyi/logs \
--file-dir ./ \
--job-name ${NAME} \
--queue-name ${QUEUE} \
--num-nodes 1 \
--num-task-pernode 1 \
--gpu-pnode ${GPUs} \
--time-limit 0 \
--job-script ${JOB_SCRIPT}

1
scripts-cluster/tmps/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
*

31
scripts-cnn/DMS-V-TrainV3.sh
View File

@@ -1,31 +0,0 @@
#!/usr/bin/env sh
# bash scripts-cnn/DMS-V-TrainV3.sh 1
if [ "$#" -ne 1 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 1 parameters for the GPUs and the epochs"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=acc2
cutout=0
dataset=cifar10
epoch=200
SAVED=./snapshots/NAS/ACC-V3-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-cnn/GDAS-Search.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.01 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--tau_max 10 --tau_min 1 \
--model_config ./configs/nas-cifar-cos-cut.config \
--print_freq 100 --workers 10

29
scripts-cnn/search-acc-v2.sh
View File

@@ -1,29 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPUs and the network"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=cifar10
epoch=200
SAVED=./snapshots/NAS/ACC-V2-Search-${arch}-${dataset}-cut${cutout}-${epoch}-E600
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-cnn/GDAS-Search.py \
--data_path $TORCH_HOME/cifar.python \
--arch ${arch} --dataset ${dataset} --batch_size 128 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos-cut.config \
--print_freq 100 --workers 10

44
scripts-cnn/search.sh
View File

@@ -1,44 +0,0 @@
#!/usr/bin/env sh
if [ "$#" -ne 3 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 3 parameters for the GPUs and the network and the dataset"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
cutout=0
dataset=$3
epoch=50
SAVED=./snapshots/NAS/Search-${arch}-${dataset}-cut${cutout}-${epoch}
if [ "$dataset" == "cifar10" ] ;then
dataset_root=$TORCH_HOME/cifar.python
print_freq=100
elif [ "$dataset" == "cifar100" ] ;then
dataset_root=$TORCH_HOME/cifar.python
print_freq=100
elif [ "$dataset" == "tiered" ] ;then
dataset_root=$TORCH_HOME/tiered-imagenet
print_freq=500
else
echo 'invalid dataset-name :'${dataset}
exit 1
fi
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-cnn/DARTS-Search.py \
--data_path ${dataset_root} \
--arch ${arch} \
--dataset ${dataset} --batch_size 64 \
--save_path ${SAVED} \
--learning_rate_max 0.025 --learning_rate_min 0.001 --momentum 0.9 --weight_decay 0.0003 \
--epochs ${epoch} --cutout ${cutout} --validate --grad_clip 5 \
--init_channels 16 --layers 8 \
--model_config ./configs/nas-cifar-cos-cut.config \
--print_freq ${print_freq} --workers 8

3
scripts-cnn/train-cifar.sh
View File

@@ -17,9 +17,10 @@ arch=$2
dataset=$3
cutout=$4
SAVED=./snapshots/NAS/${arch}-${dataset}-${cutout}-E600
#--data_path $TORCH_HOME/cifar.python \
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-cnn/train_base.py \
--data_path $TORCH_HOME/cifar.python \
--data_path ./data/data/cifar.python \
--dataset ${dataset} --arch ${arch} \
--save_path ${SAVED} \
--grad_clip 5 \

17
scripts-rnn/train-PTB.sh
View File

@@ -1,21 +1,14 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
if [ "$#" -ne 1 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPU and the architecture"
echo "Need 1 parameters for the GPU and the architecture"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
SAVED=./snapshots/NAS-RNN/Search-${arch}-PTB
arch=$1
SAVED=./output/NAS-RNN/Search-${arch}-PTB
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-rnn/train_rnn_base.py \
python ./exps-rnn/train_rnn_base.py \
--arch ${arch} \
--save_path ${SAVED} \
--config_path ./configs/NAS-PTB-BASE.config \

17
scripts-rnn/train-WT2.sh
View File

@@ -1,21 +1,14 @@
#!/usr/bin/env sh
if [ "$#" -ne 2 ] ;then
if [ "$#" -ne 1 ] ;then
echo "Input illegal number of parameters " $#
echo "Need 2 parameters for the GPU and the architecture"
echo "Need 1 parameters for the architectures"
exit 1
fi
if [ "$TORCH_HOME" = "" ]; then
echo "Must set TORCH_HOME envoriment variable for data dir saving"
exit 1
else
echo "TORCH_HOME : $TORCH_HOME"
fi
gpus=$1
arch=$2
SAVED=./snapshots/NAS-RNN/Search-${arch}-WT2
arch=$1
SAVED=./output/NAS-RNN/Search-${arch}-WT2
CUDA_VISIBLE_DEVICES=${gpus} python ./exps-nas/rnn/train_rnn_base.py \
python ./exps-rnn/train_rnn_base.py \
--arch ${arch} \
--save_path ${SAVED} \
--config_path ./configs/NAS-WT2-BASE.config \