def get_config():
logger.set_logger_dir(
os.path.join('train_log', 'svhn-dorefa-{}'.format(args.dorefa)))
# prepare dataset
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = MultiProcessRunnerZMQ(data_train, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return TrainConfig(
data=QueueInput(data_train),
callbacks=[
ModelSaver(),
InferenceRunner(
data_test,
[ScalarStats('cost'),
ClassificationError('wrong_tensor')])
],
model=Model(),
max_epoch=200,
)
def get_data(train_or_test):
isTrain = train_or_test == 'train'
pp_mean = dataset.SVHNDigit.get_per_pixel_mean()
if isTrain:
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
ds = RandomMixData([d1, d2])
else:
ds = dataset.SVHNDigit('test')
if isTrain:
augmentors = [
imgaug.CenterPaste((40, 40)),
imgaug.Brightness(10),
imgaug.Contrast((0.8, 1.2)),
imgaug.
GaussianDeform( # this is slow. without it, can only reach 1.9% error
[(0.2, 0.2), (0.2, 0.8), (0.8, 0.8), (0.8, 0.2)], (40, 40),
0.2, 3),
imgaug.RandomCrop((32, 32)),
imgaug.MapImage(lambda x: x - pp_mean),
]
else:
augmentors = [imgaug.MapImage(lambda x: x - pp_mean)]
ds = AugmentImageComponent(ds, augmentors)
ds = BatchData(ds, 128, remainder=not isTrain)
if isTrain:
ds = PrefetchData(ds, 5, 5)
return ds
def get_config():
logger.auto_set_dir()
# prepare dataset
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
# imgaug.GaussianDeform( # this is slow but helpful. only use it when you have lots of cpus
# [(0.2, 0.2), (0.2, 0.8), (0.8,0.8), (0.8,0.2)],
# (40,40), 0.2, 3),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = PrefetchDataZMQ(data_train, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return TrainConfig(
dataflow=data_train,
callbacks=[
ModelSaver(),
InferenceRunner(data_test,
[ScalarStats('cost'), ClassificationError()])
],
model=Model(),
max_epoch=200,
)
def get_config():
#logger.auto_set_dir()
logger.set_logger_dir('./train_log/svhn_dorefa_adam01_zp_025_'+str(args.dorefa)+'_exp1')
# prepare dataset
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
# imgaug.GaussianDeform( # this is slow but helpful. only use it when you have lots of cpus
# [(0.2, 0.2), (0.2, 0.8), (0.8,0.8), (0.8,0.2)],
# (40,40), 0.2, 3),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = PrefetchDataZMQ(data_train, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return TrainConfig(
data=QueueInput(data_train),
callbacks=[
ModelSaver(max_to_keep=2),
InferenceRunner(data_test,
[ScalarStats('cost'), ClassificationError('wrong_tensor')])
],
model=Model(),
max_epoch=200,
)
def get_data():
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
dataset_train = RandomMixData([d1, d2])
dataset_test = dataset.SVHNDigit('test', shuffle=False)
dataset_train = BatchData(dataset_train, 256)
dataset_test = BatchData(dataset_test, 128, remainder=True)
return dataset_train, dataset_test
def get_data():
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_test = dataset.SVHNDigit('test', shuffle=False)
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = PrefetchData(data_train, 5, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return data_train, data_test
def get_data():
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_train = DisturbLabel(data_train, args.prob)
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = MultiProcessRunner(data_train, 5, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return data_train, data_test
def get_data():
d1 = dataset.SVHNDigit('train')
d2 = dataset.SVHNDigit('extra')
data_train = RandomMixData([d1, d2])
data_test = dataset.SVHNDigit('test', shuffle=False)
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
imgaug.GaussianDeform( # this is slow. only use it when you have lots of cpus
[(0.2, 0.2), (0.2, 0.8), (0.8, 0.8), (0.8, 0.2)],
(40, 40), 0.2, 3),
]
data_train = AugmentImageComponent(data_train, augmentors)
data_train = BatchData(data_train, 128)
data_train = PrefetchData(data_train, 5, 5)
augmentors = [imgaug.Resize((40, 40))]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
return data_train, data_test
'--load',
help='load a checkpoint, or a npz (given as the pretrained model)')
parser.add_argument('--data', help='ILSVRC dataset dir')
parser.add_argument(
'--dorefa',
required=True,
help='number of bits for W,A,G, separated by comma. W="t" means TTQ')
parser.add_argument(
'--run',
help='run on a list of images with the pretrained model',
nargs='*')
parser.add_argument('--eval', action='store_true')
args = parser.parse_args()
if args.eval:
BATCH_SIZE = 128
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
eval_classification(Model(), get_model_loader(args.load), data_test)
sys.exit()
BITW, BITA, BITG = map(int, args.dorefa.split(','))
config = get_config()
launch_train_with_config(config, SimpleTrainer())
