p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!3611 dataset: repair problem in vgg cifar(version) 

Merge pull request !3611 from ms_yan/vgg_repair
This commit is contained in:
mindspore-ci-bot 2020-07-29 10:18:04 +08:00 committed by Gitee
parent fa3a1f4a16 4e3fa200ee
commit f48ef43647
5 changed files with 21 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
model_zoo/official/cv/vgg16/README.md
View File

@ -38,9 +38,11 @@ epcoh: 2 step: 781, loss is 1.827582
### Evaluation
- Do eval as follows, need to specify dataset type as "cifar10" or "imagenet2012"
```
python eval.py --data_path=your_data_path --device_id=6 --checkpoint_path=./train_vgg_cifar10-70-781.ckpt > out.eval.log 2>&1 &
python eval.py --data_path=your_data_path --dataset="cifar10" --pre_trained=./train_vgg_cifar10-70-781.ckpt > out.eval.log 2>&1 &
```
- If the using dataset is
The above python command will run in the background, you can view the results through the file `out.eval.log`.
You will get the accuracy as following:
@ -93,7 +95,7 @@ parameters/options:
--device_target the evaluation backend type, default is Ascend.
--data_path the storage path of datasetd
--device_id the device which used to evaluate model.
--checkpoint_path the checkpoint file path used to evaluate model.
--pre_trained the checkpoint file path used to evaluate model.
```
### Distribute Training

31
model_zoo/official/cv/vgg16/eval.py
View File

@ -52,15 +52,15 @@ class ParameterReduce(nn.Cell):
def parse_args(cloud_args=None):
"""parse_args"""
parser = argparse.ArgumentParser('mindspore classification test')
parser.add_argument('--device_target', type=str, default='GPU', choices=['Ascend', 'GPU'],
parser.add_argument('--device_target', type=str, default='Ascend', choices=['Ascend', 'GPU'],
help='device where the code will be implemented. (Default: Ascend)')
# dataset related
parser.add_argument('--dataset', type=str, choices=["cifar10", "imagenet2012"], default="imagenet2012")
parser.add_argument('--dataset', type=str, choices=["cifar10", "imagenet2012"], default="cifar10")
parser.add_argument('--data_path', type=str, default='', help='eval data dir')
parser.add_argument('--per_batch_size', default=32, type=int, help='batch size for per npu')
# network related
parser.add_argument('--graph_ckpt', type=int, default=1, help='graph ckpt or feed ckpt')
parser.add_argument('--pretrained', default='', type=str, help='fully path of pretrained model to load. '
parser.add_argument('--pre_trained', default='', type=str, help='fully path of pretrained model to load. '
'If it is a direction, it will test all ckpt')
# logging related
@ -68,9 +68,6 @@ def parse_args(cloud_args=None):
parser.add_argument('--rank', type=int, default=0, help='local rank of distributed')
parser.add_argument('--group_size', type=int, default=1, help='world size of distributed')
# roma obs
parser.add_argument('--train_url', type=str, default="", help='train url')
args_opt = parser.parse_args()
args_opt = merge_args(args_opt, cloud_args)
@ -82,6 +79,8 @@ def parse_args(cloud_args=None):
args_opt.image_size = cfg.image_size
args_opt.num_classes = cfg.num_classes
args_opt.per_batch_size = cfg.batch_size
args_opt.momentum = cfg.momentum
args_opt.weight_decay = cfg.weight_decay
args_opt.buffer_size = cfg.buffer_size
args_opt.pad_mode = cfg.pad_mode
args_opt.padding = cfg.padding
@ -130,23 +129,23 @@ def test(cloud_args=None):
args.logger.save_args(args)
if args.dataset == "cifar10":
net = vgg16(num_classes=args.num_classes)
opt = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()), 0.01, cfg.momentum,
net = vgg16(num_classes=args.num_classes, args=args)
opt = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()), 0.01, args.momentum,
weight_decay=args.weight_decay)
loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean', is_grad=False)
model = Model(net, loss_fn=loss, optimizer=opt, metrics={'acc'})
param_dict = load_checkpoint(args.checkpoint_path)
param_dict = load_checkpoint(args.pre_trained)
load_param_into_net(net, param_dict)
net.set_train(False)
dataset = vgg_create_dataset(args.data_path, 1, False)
dataset = vgg_create_dataset(args.data_path, args.image_size, args.per_batch_size, training=False)
res = model.eval(dataset)
print("result: ", res)
else:
# network
args.logger.important_info('start create network')
if os.path.isdir(args.pretrained):
models = list(glob.glob(os.path.join(args.pretrained, '*.ckpt')))
if os.path.isdir(args.pre_trained):
models = list(glob.glob(os.path.join(args.pre_trained, '*.ckpt')))
print(models)
if args.graph_ckpt:
f = lambda x: -1 * int(os.path.splitext(os.path.split(x)[-1])[0].split('-')[-1].split('_')[0])
@ -154,14 +153,10 @@ def test(cloud_args=None):
f = lambda x: -1 * int(os.path.splitext(os.path.split(x)[-1])[0].split('_')[-1])
args.models = sorted(models, key=f)
else:
args.models = [args.pretrained,]
args.models = [args.pre_trained,]
for model in args.models:
if args.dataset == "cifar10":
dataset = vgg_create_dataset(args.data_path, args.image_size, args.per_batch_size, training=False)
else:
dataset = classification_dataset(args.data_path, args.image_size, args.per_batch_size)
dataset = classification_dataset(args.data_path, args.image_size, args.per_batch_size)
eval_dataloader = dataset.create_tuple_iterator()
network = vgg16(args.num_classes, args, phase="test")

2
model_zoo/official/cv/vgg16/scripts/run_distribute_train.sh
View File

@ -47,6 +47,6 @@ do
cd ./train_parallel$i || exit
echo "start training for rank $RANK_ID, device $DEVICE_ID"
env > env.log
python train.py --data_path=$2 --device_id=$i &> log &
python train.py --data_path=$2 --device_target="Ascend" --device_id=$i &> log &
cd ..
done

2
model_zoo/official/cv/vgg16/src/vgg.py
View File

@ -138,5 +138,5 @@ def vgg16(num_classes=1000, args=None, phase="train"):
>>> vgg16(num_classes=1000)
"""
net = Vgg(cfg['16'], num_classes=num_classes, args=args, batch_norm=True, phase=phase)
net = Vgg(cfg['16'], num_classes=num_classes, args=args, batch_norm=args.batch_norm, phase=phase)
return net

4
model_zoo/official/cv/vgg16/train.py
View File

@ -109,7 +109,7 @@ class ProgressMonitor(Callback):
def parse_args(cloud_args=None):
"""parameters"""
parser = argparse.ArgumentParser('mindspore classification training')
parser.add_argument('--device_target', type=str, default='GPU', choices=['Ascend', 'GPU'],
parser.add_argument('--device_target', type=str, default='Ascend', choices=['Ascend', 'GPU'],
help='device where the code will be implemented. (Default: Ascend)')
parser.add_argument('--device_id', type=int, default=1, help='device id of GPU or Ascend. (Default: None)')
@ -127,7 +127,7 @@ def parse_args(cloud_args=None):
# logging and checkpoint related
parser.add_argument('--log_interval', type=int, default=100, help='logging interval')
parser.add_argument('--ckpt_path', type=str, default='outputs/', help='checkpoint save location')
parser.add_argument('--ckpt_interval', type=int, default=5000, help='ckpt_interval')
parser.add_argument('--ckpt_interval', type=int, default=2, help='ckpt_interval')
parser.add_argument('--is_save_on_master', type=int, default=1, help='save ckpt on master or all rank')
# distributed related