def load_data(traindir, valdir, args):
# Data loading code
print("Loading data")
resize_size, crop_size = (342,
299) if args.model == 'inception_v3' else (256,
224)
print("Loading training data")
st = time.time()
cache_path = _get_cache_path(traindir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print("Loading dataset_train from {}".format(cache_path))
dataset, _ = torch.load(cache_path)
else:
auto_augment_policy = getattr(args, "auto_augment", None)
random_erase_prob = getattr(args, "random_erase", 0.0)
dataset = torchvision.datasets.ImageFolder(
traindir,
presets.ClassificationPresetTrain(
crop_size=crop_size,
auto_augment_policy=auto_augment_policy,
random_erase_prob=random_erase_prob))
if args.cache_dataset:
print("Saving dataset_train to {}".format(cache_path))
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset, traindir), cache_path)
print("Took", time.time() - st)
print("Loading validation data")
cache_path = _get_cache_path(valdir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print("Loading dataset_test from {}".format(cache_path))
dataset_test, _ = torch.load(cache_path)
else:
dataset_test = torchvision.datasets.ImageFolder(
valdir,
presets.ClassificationPresetEval(crop_size=crop_size,
resize_size=resize_size))
if args.cache_dataset:
print("Saving dataset_test to {}".format(cache_path))
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset_test, valdir), cache_path)
print("Creating data loaders")
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(
dataset)
test_sampler = torch.utils.data.distributed.DistributedSampler(
dataset_test)
else:
train_sampler = torch.utils.data.RandomSampler(dataset)
test_sampler = torch.utils.data.SequentialSampler(dataset_test)
return dataset, dataset_test, train_sampler, test_sampler
def load_data(traindir, valdir, args):
# Data loading code
print("Loading data")
resize_size, crop_size = (342,
299) if args.model == 'inception_v3' else (256,
224)
print("Loading training data")
st = time.time()
auto_augment_policy = getattr(args, "auto_augment", None)
random_erase_prob = getattr(args, "random_erase", 0.0)
dataset = paddlevision.datasets.ImageFolder(
traindir,
presets.ClassificationPresetTrain(
crop_size=crop_size,
auto_augment_policy=auto_augment_policy,
random_erase_prob=random_erase_prob))
print("Took", time.time() - st)
print("Loading validation data")
dataset_test = paddlevision.datasets.ImageFolder(
valdir,
presets.ClassificationPresetEval(crop_size=crop_size,
resize_size=resize_size))
print("Creating data loaders")
train_sampler = paddle.io.DistributedBatchSampler(
dataset=dataset,
batch_size=args.batch_size,
shuffle=True,
drop_last=False)
# train_sampler = paddle.io.RandomSampler(dataset)
test_sampler = paddle.io.SequenceSampler(dataset_test)
return dataset, dataset_test, train_sampler, test_sampler
def load_data(traindir, valdir, args):
# Data loading code
print("Loading data")
resize_size, crop_size = 256, 224
interpolation = InterpolationMode.BILINEAR
if args.model == 'inception_v3':
resize_size, crop_size = 342, 299
elif args.model.startswith('efficientnet_'):
sizes = {
'b0': (256, 224),
'b1': (256, 240),
'b2': (288, 288),
'b3': (320, 300),
'b4': (384, 380),
'b5': (456, 456),
'b6': (528, 528),
'b7': (600, 600),
}
e_type = args.model.replace('efficientnet_', '')
resize_size, crop_size = sizes[e_type]
interpolation = InterpolationMode.BICUBIC
print("Loading training data")
st = time.time()
cache_path = _get_cache_path(traindir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print("Loading dataset_train from {}".format(cache_path))
dataset, _ = torch.load(cache_path)
else:
auto_augment_policy = getattr(args, "auto_augment", None)
random_erase_prob = getattr(args, "random_erase", 0.0)
dataset = torchvision.datasets.ImageFolder(
traindir,
presets.ClassificationPresetTrain(
crop_size=crop_size,
auto_augment_policy=auto_augment_policy,
random_erase_prob=random_erase_prob))
if args.cache_dataset:
print("Saving dataset_train to {}".format(cache_path))
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset, traindir), cache_path)
print("Took", time.time() - st)
print("Loading validation data")
cache_path = _get_cache_path(valdir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print("Loading dataset_test from {}".format(cache_path))
dataset_test, _ = torch.load(cache_path)
else:
dataset_test = torchvision.datasets.ImageFolder(
valdir,
presets.ClassificationPresetEval(crop_size=crop_size,
resize_size=resize_size,
interpolation=interpolation))
if args.cache_dataset:
print("Saving dataset_test to {}".format(cache_path))
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset_test, valdir), cache_path)
print("Creating data loaders")
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(
dataset)
test_sampler = torch.utils.data.distributed.DistributedSampler(
dataset_test)
else:
train_sampler = torch.utils.data.RandomSampler(dataset)
test_sampler = torch.utils.data.SequentialSampler(dataset_test)
return dataset, dataset_test, train_sampler, test_sampler
def load_data(traindir, valdir, args):
# Data loading code
print("Loading data")
val_resize_size, val_crop_size, train_crop_size = args.val_resize_size, args.val_crop_size, args.train_crop_size
interpolation = InterpolationMode(args.interpolation)
print("Loading training data")
st = time.time()
cache_path = _get_cache_path(traindir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print(f"Loading dataset_train from {cache_path}")
dataset, _ = torch.load(cache_path)
else:
auto_augment_policy = getattr(args, "auto_augment", None)
random_erase_prob = getattr(args, "random_erase", 0.0)
dataset = torchvision.datasets.ImageFolder(
traindir,
presets.ClassificationPresetTrain(
crop_size=train_crop_size,
interpolation=interpolation,
auto_augment_policy=auto_augment_policy,
random_erase_prob=random_erase_prob,
),
)
if args.cache_dataset:
print(f"Saving dataset_train to {cache_path}")
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset, traindir), cache_path)
print("Took", time.time() - st)
print("Loading validation data")
cache_path = _get_cache_path(valdir)
if args.cache_dataset and os.path.exists(cache_path):
# Attention, as the transforms are also cached!
print(f"Loading dataset_test from {cache_path}")
dataset_test, _ = torch.load(cache_path)
else:
if not args.prototype:
preprocessing = presets.ClassificationPresetEval(
crop_size=val_crop_size,
resize_size=val_resize_size,
interpolation=interpolation)
else:
if args.weights:
weights = prototype.models.get_weight(args.weights)
preprocessing = weights.transforms()
else:
preprocessing = prototype.transforms.ImageClassificationEval(
crop_size=val_crop_size,
resize_size=val_resize_size,
interpolation=interpolation)
dataset_test = torchvision.datasets.ImageFolder(
valdir,
preprocessing,
)
if args.cache_dataset:
print(f"Saving dataset_test to {cache_path}")
utils.mkdir(os.path.dirname(cache_path))
utils.save_on_master((dataset_test, valdir), cache_path)
print("Creating data loaders")
if args.distributed:
if hasattr(args, "ra_sampler") and args.ra_sampler:
train_sampler = RASampler(dataset,
shuffle=True,
repetitions=args.ra_reps)
else:
train_sampler = torch.utils.data.distributed.DistributedSampler(
dataset)
test_sampler = torch.utils.data.distributed.DistributedSampler(
dataset_test, shuffle=False)
else:
train_sampler = torch.utils.data.RandomSampler(dataset)
test_sampler = torch.utils.data.SequentialSampler(dataset_test)
return dataset, dataset_test, train_sampler, test_sampler