def create_dataset(repeat_num=1, batch_size=32, rank_id=0, rank_size=1):
resize_height = 224
resize_width = 224
rescale = 1.0 / 255.0
shift = 0.0
# get rank_id and rank_size
rank_id = get_rank()
rank_size = get_group_size()
data_set = ds.Cifar10Dataset(data_path,
num_shards=rank_size,
shard_id=rank_id)
# define map operations
random_crop_op = vision.RandomCrop((32, 32), (4, 4, 4, 4))
random_horizontal_op = vision.RandomHorizontalFlip()
resize_op = vision.Resize((resize_height, resize_width))
rescale_op = vision.Rescale(rescale, shift)
normalize_op = vision.Normalize((0.4465, 0.4822, 0.4914),
(0.2010, 0.1994, 0.2023))
changeswap_op = vision.HWC2CHW()
type_cast_op = C.TypeCast(mstype.int32)
c_trans = [random_crop_op, random_horizontal_op]
c_trans += [resize_op, rescale_op, normalize_op, changeswap_op]
# apply map operations on images
data_set = data_set.map(input_columns="label", operations=type_cast_op)
data_set = data_set.map(input_columns="image", operations=c_trans)
# apply shuffle operations
data_set = data_set.shuffle(buffer_size=10)
# apply batch operations
data_set = data_set.batch(batch_size=batch_size, drop_remainder=True)
# apply repeat operations
data_set = data_set.repeat(repeat_num)
return data_set
def test_deterministic_run_fail():
"""
Test RandomCrop with seed, expected to fail
"""
logger.info("test_deterministic_run_fail")
# when we set the seed all operations within our dataset should be deterministic
ds.config.set_seed(0)
ds.config.set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# Assuming we get the same seed on calling constructor, if this op is re-used then result won't be
# the same in between the two datasets. For example, RandomCrop constructor takes seed (0)
# outputs a deterministic series of numbers, e,g "a" = [1, 2, 3, 4, 5, 6] <- pretend these are random
random_crop_op = vision.RandomCrop([512, 512], [200, 200, 200, 200])
decode_op = vision.Decode()
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"], operations=random_crop_op)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=decode_op)
# If seed is set up on constructor
data2 = data2.map(input_columns=["image"], operations=random_crop_op)
try:
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
np.testing.assert_equal(item1["image"], item2["image"])
except BaseException as e:
# two datasets split the number out of the sequence a
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Array" in str(e)
def test_random_crop_comp(plot=False):
"""
Test RandomCrop and compare between python and c image augmentation
"""
logger.info("Test RandomCrop with c_transform and py_transform comparison")
cropped_size = 512
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
random_crop_op = c_vision.RandomCrop(cropped_size)
decode_op = c_vision.Decode()
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"], operations=random_crop_op)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [
py_vision.Decode(),
py_vision.RandomCrop(cropped_size),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data2 = data2.map(input_columns=["image"], operations=transform())
image_c_cropped = []
image_py_cropped = []
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
c_image = item1["image"]
py_image = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_c_cropped.append(c_image)
image_py_cropped.append(py_image)
if plot:
visualize_list(image_c_cropped, image_py_cropped, visualize_mode=2)
def test_random_crop_02_c():
"""
Test RandomCrop op with c_transforms: size is a list/tuple with length 2, expected to pass
"""
logger.info("test_random_crop_02_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: If size is a sequence of length 2, it should be (height, width).
random_crop_op = c_vision.RandomCrop([512, 375])
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_02_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_01_c():
"""
Test RandomCrop op with c_transforms: size is a single integer, expected to pass
"""
logger.info("test_random_crop_01_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: If size is an int, a square crop of size (size, size) is returned.
random_crop_op = c_vision.RandomCrop(512)
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_01_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_03_c():
"""
Test RandomCrop op with c_transforms: input image size == crop size, expected to pass
"""
logger.info("test_random_crop_03_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: The size of the image is 4032*2268
random_crop_op = c_vision.RandomCrop([2268, 4032])
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_03_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_08_c():
"""
Test RandomCrop op with c_transforms: padding_mode is Border.EDGE,
expected to pass
"""
logger.info("test_random_crop_08_c")
ds.config.set_seed(0)
ds.config.set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# Note: The padding_mode is Border.EDGE.
random_crop_op = c_vision.RandomCrop(512, [200, 200, 200, 200],
padding_mode=mode.Border.EDGE)
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_08_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
def test_cpp_uniform_augment_exception_pyops(num_ops=2):
"""
Test UniformAugment invalid op in operations
"""
logger.info("Test CPP UniformAugment invalid OP exception")
transforms_ua = [
C.RandomCrop(size=[224, 224], padding=[32, 32, 32, 32]),
C.RandomHorizontalFlip(),
C.RandomVerticalFlip(),
C.RandomColorAdjust(),
C.RandomRotation(degrees=45),
F.Invert()
]
with pytest.raises(TypeError) as e:
C.UniformAugment(transforms=transforms_ua, num_ops=num_ops)
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Argument tensor_ops[5] with value" \
" <mindspore.dataset.transforms.vision.py_transforms.Invert" in str(e.value)
assert "is not of type (<class 'mindspore._c_dataengine.TensorOp'>,)" in str(
e.value)
def test_bounding_box_augment_with_crop_op(plot_vis=False):
"""
Test BoundingBoxAugment op (passing crop op as transform)
Prints images side by side with and without Aug applied + bboxes to compare and test
"""
logger.info("test_bounding_box_augment_with_crop_op")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
dataVoc1 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
# Ratio is set to 0.9 to apply RandomCrop of size (50, 50) on 90% of the bounding boxes.
test_op = c_vision.BoundingBoxAugment(c_vision.RandomCrop(50), 0.9)
# map to apply ops
dataVoc2 = dataVoc2.map(input_columns=["image", "annotation"],
output_columns=["image", "annotation"],
columns_order=["image", "annotation"],
operations=[test_op])
filename = "bounding_box_augment_crop_c_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(dataVoc1.create_dict_iterator(), dataVoc2.create_dict_iterator()):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def create_dataset(data_path, batch_size=32, repeat_size=1, status="train"):
"""
create dataset for train or test
"""
rank_id = int(os.getenv('DEVICE_ID'))
device_num = int(os.getenv('RANK_SIZE'))
if device_num == 1:
cifar_ds = ds.Cifar10Dataset(data_path, num_parallel_workers=8, shuffle=True)
else:
cifar_ds = ds.Cifar10Dataset(data_path, num_parallel_workers=8, shuffle=True,
num_shards=device_num, shard_id=rank_id)
rescale = 1.0 / 255.0
shift = 0.0
resize_op = CV.Resize((cfg.image_height, cfg.image_width))
rescale_op = CV.Rescale(rescale, shift)
normalize_op = CV.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
if status == "train":
random_crop_op = CV.RandomCrop([32, 32], [4, 4, 4, 4])
random_horizontal_op = CV.RandomHorizontalFlip()
channel_swap_op = CV.HWC2CHW()
typecast_op = C.TypeCast(mstype.int32)
cifar_ds = cifar_ds.map(input_columns="label", operations=typecast_op)
if status == "train":
cifar_ds = cifar_ds.map(input_columns="image", operations=random_crop_op)
cifar_ds = cifar_ds.map(input_columns="image", operations=random_horizontal_op)
cifar_ds = cifar_ds.map(input_columns="image", operations=resize_op)
cifar_ds = cifar_ds.map(input_columns="image", operations=rescale_op)
cifar_ds = cifar_ds.map(input_columns="image", operations=normalize_op)
cifar_ds = cifar_ds.map(input_columns="image", operations=channel_swap_op)
cifar_ds = cifar_ds.shuffle(buffer_size=cfg.buffer_size)
cifar_ds = cifar_ds.batch(batch_size, drop_remainder=True)
cifar_ds = cifar_ds.repeat(repeat_size)
return cifar_ds
def test_random_crop_05_c():
"""
Test RandomCrop op with c_transforms:
input image size < crop size but pad_if_needed is enabled,
expected to pass
"""
logger.info("test_random_crop_05_c")
ds.config.set_seed(0)
ds.config.set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# Note: The size of the image is 4032*2268
random_crop_op = c_vision.RandomCrop([2268, 4033], [200, 200, 200, 200],
pad_if_needed=True)
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_05_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
def test_random_crop_07_c():
"""
Test RandomCrop op with c_transforms:
padding_mode is Border.CONSTANT and fill_value is 255 (White),
expected to pass
"""
logger.info("test_random_crop_07_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: The padding_mode is default as Border.CONSTANT and set filling color to be white.
random_crop_op = c_vision.RandomCrop(512, [200, 200, 200, 200], fill_value=(255, 255, 255))
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_07_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_04_c():
"""
Test RandomCrop op with c_transforms: input image size < crop size, expected to fail
"""
logger.info("test_random_crop_04_c")
ds.config.set_seed(0)
ds.config.set_num_parallel_workers(1)
try:
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# Note: The size of the image is 4032*2268
random_crop_op = c_vision.RandomCrop([2268, 4033])
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
image_list = []
for item in data.create_dict_iterator():
image = item["image"]
image_list.append(image.shape)
except Exception as e:
logger.info("Got an exception in DE: {}".format(str(e)))
def create_dataset(dataset_path, do_train, config, repeat_num=1):
"""
Create a train or eval dataset.
Args:
dataset_path (string): The path of dataset.
do_train (bool): Whether dataset is used for train or eval.
config: configuration
repeat_num (int): The repeat times of dataset. Default: 1.
Returns:
Dataset.
"""
if do_train:
dataset_path = os.path.join(dataset_path, 'train')
do_shuffle = True
else:
dataset_path = os.path.join(dataset_path, 'eval')
do_shuffle = False
device_id = 0
device_num = 1
if config.platform == "GPU":
if config.run_distribute:
from mindspore.communication.management import get_rank, get_group_size
device_id = get_rank()
device_num = get_group_size()
elif config.platform == "Ascend":
device_id = int(os.getenv('DEVICE_ID'))
device_num = int(os.getenv('RANK_SIZE'))
if device_num == 1 or not do_train:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=do_shuffle)
else:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=do_shuffle,
num_shards=device_num,
shard_id=device_id)
resize_height = config.image_height
resize_width = config.image_width
buffer_size = 100
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
random_crop_op = C.RandomCrop((32, 32), (4, 4, 4, 4))
random_horizontal_flip_op = C.RandomHorizontalFlip(device_id /
(device_id + 1))
resize_op = C.Resize((resize_height, resize_width))
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
change_swap_op = C.HWC2CHW()
trans = []
if do_train:
trans += [random_crop_op, random_horizontal_flip_op]
trans += [resize_op, rescale_op, normalize_op, change_swap_op]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="label", operations=type_cast_op)
ds = ds.map(input_columns="image", operations=trans)
# apply shuffle operations
ds = ds.shuffle(buffer_size=buffer_size)
# apply batch operations
ds = ds.batch(config.batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32):
"""
Create a train or eval dataset.
Args:
dataset_path (str): The path of dataset.
do_train (bool): Whether dataset is used for train or eval.
repeat_num (int): The repeat times of dataset. Default: 1.
batch_size (int): The batch size of dataset. Default: 32.
Returns:
Dataset.
"""
if do_train:
dataset_path = os.path.join(dataset_path, 'train')
do_shuffle = True
else:
dataset_path = os.path.join(dataset_path, 'eval')
do_shuffle = False
if device_num == 1 or not do_train:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=do_shuffle)
else:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=do_shuffle,
num_shards=device_num,
shard_id=device_id)
resize_height = 224
resize_width = 224
buffer_size = 100
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
random_crop_op = C.RandomCrop((32, 32), (4, 4, 4, 4))
random_horizontal_flip_op = C.RandomHorizontalFlip(device_id /
(device_id + 1))
resize_op = C.Resize((resize_height, resize_width))
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
change_swap_op = C.HWC2CHW()
trans = []
if do_train:
trans += [random_crop_op, random_horizontal_flip_op]
trans += [resize_op, rescale_op, normalize_op, change_swap_op]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="label", operations=type_cast_op)
ds = ds.map(input_columns="image", operations=trans)
# apply shuffle operations
ds = ds.shuffle(buffer_size=buffer_size)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def create_dataset(dataset_path,
do_train,
repeat_num=1,
batch_size=32,
target="Ascend"):
"""
create a train or eval dataset
Args:
dataset_path(string): the path of dataset.
do_train(bool): whether dataset is used for train or eval.
repeat_num(int): the repeat times of dataset. Default: 1
batch_size(int): the batch size of dataset. Default: 32
target(str): the device target. Default: Ascend
Returns:
dataset
"""
if target == "Ascend":
device_num = int(os.getenv("DEVICE_NUM"))
rank_id = int(os.getenv("RANK_ID"))
else:
init("nccl")
rank_id = get_rank()
device_num = get_group_size()
if device_num == 1:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=8,
shuffle=True)
else:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=8,
shuffle=True,
num_shards=device_num,
shard_id=rank_id)
# define map operations
trans = []
if do_train:
trans += [
C.RandomCrop((32, 32), (4, 4, 4, 4)),
C.RandomHorizontalFlip(prob=0.5)
]
trans += [
C.Resize((config.image_height, config.image_width)),
C.Rescale(1.0 / 255.0, 0.0),
C.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
C.HWC2CHW()
]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="label",
num_parallel_workers=8,
operations=type_cast_op)
ds = ds.map(input_columns="image",
num_parallel_workers=8,
operations=trans)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def test_cpp_uniform_augment(plot=False, num_ops=2):
"""
Test UniformAugment
"""
logger.info("Test CPP UniformAugment")
# Original Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(), C.Resize(size=[224, 224]), F.ToTensor()]
ds_original = ds.map(input_columns="image", operations=transforms_original)
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = np.transpose(image, (0, 2, 3, 1))
else:
images_original = np.append(images_original,
np.transpose(image, (0, 2, 3, 1)),
axis=0)
# UniformAugment Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_ua = [
C.RandomCrop(size=[224, 224], padding=[32, 32, 32, 32]),
C.RandomHorizontalFlip(),
C.RandomVerticalFlip(),
C.RandomColorAdjust(),
C.RandomRotation(degrees=45)
]
uni_aug = C.UniformAugment(operations=transforms_ua, num_ops=num_ops)
transforms_all = [
C.Decode(),
C.Resize(size=[224, 224]), uni_aug,
F.ToTensor()
]
ds_ua = ds.map(input_columns="image",
operations=transforms_all,
num_parallel_workers=1)
ds_ua = ds_ua.batch(512)
for idx, (image, _) in enumerate(ds_ua):
if idx == 0:
images_ua = np.transpose(image, (0, 2, 3, 1))
else:
images_ua = np.append(images_ua,
np.transpose(image, (0, 2, 3, 1)),
axis=0)
if plot:
visualize_list(images_original, images_ua)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_ua[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32):
"""
create a train or eval dataset
Args:
dataset_path(string): the path of dataset.
do_train(bool): whether dataset is used for train or eval.
repeat_num(int): the repeat times of dataset. Default: 1
batch_size(int): the batch size of dataset. Default: 32
Returns:
dataset
"""
device_num = int(os.getenv("DEVICE_NUM"))
rank_id = int(os.getenv("RANK_ID"))
if device_num == 1:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=True)
else:
ds = de.Cifar10Dataset(dataset_path,
num_parallel_workers=4,
shuffle=True,
num_shards=device_num,
shard_id=rank_id)
resize_height = config.image_height
resize_width = config.image_width
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
random_crop_op = C.RandomCrop((32, 32), (4, 4, 4, 4))
random_horizontal_flip_op = C.RandomHorizontalFlip(rank_id / (rank_id + 1))
resize_op = C.Resize((resize_height, resize_width))
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
change_swap_op = C.HWC2CHW()
trans = []
if do_train:
trans += [random_crop_op, random_horizontal_flip_op]
trans += [resize_op, rescale_op, normalize_op, change_swap_op]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="label", operations=type_cast_op)
ds = ds.map(input_columns="image", operations=trans)
# apply shuffle operations
ds = ds.shuffle(buffer_size=config.buffer_size)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
