def test_center_crop_comp(height=375, width=375, plot=False):
"""
Test CenterCrop between python and c image augmentation
"""
logger.info("Test CenterCrop")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = vision.Decode()
center_crop_op = vision.CenterCrop([height, width])
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"], operations=center_crop_op)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
transforms = [
py_vision.Decode(),
py_vision.CenterCrop([height, width]),
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)
# Note: The images aren't exactly the same due to rounding error
assert diff_mse(py_image, c_image) < 0.001
image_c_cropped.append(c_image.copy())
image_py_cropped.append(py_image.copy())
if plot:
visualize_list(image_c_cropped, image_py_cropped, visualize_mode=2)
def test_random_apply_md5():
"""
Test RandomApply op with md5 check
"""
logger.info("test_random_apply_md5")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms_list = [py_vision.CenterCrop(64), py_vision.RandomRotation(30)]
transforms = [
py_vision.Decode(),
# Note: using default value "prob=0.5"
py_vision.RandomApply(transforms_list),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data = data.map(input_columns=["image"], operations=transform())
# check results with md5 comparison
filename = "random_apply_01_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers((original_num_parallel_workers))
def test_linear_transformation_md5_01():
"""
Test LinearTransformation op: valid params (transformation_matrix, mean_vector)
Expected to pass
"""
logger.info("test_linear_transformation_md5_01")
# Initialize parameters
height = 50
weight = 50
dim = 3 * height * weight
transformation_matrix = np.ones([dim, dim])
mean_vector = np.zeros(dim)
# Generate dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [
py_vision.Decode(),
py_vision.CenterCrop([height, weight]),
py_vision.ToTensor(),
py_vision.LinearTransformation(transformation_matrix, mean_vector)
]
transform = py_vision.ComposeOp(transforms)
data1 = data1.map(input_columns=["image"], operations=transform())
# Compare with expected md5 from images
filename = "linear_transformation_01_result.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
def test_linear_transformation_md5_05():
"""
Test LinearTransformation op: mean_vector does not match dimension of transformation_matrix
Expected to raise ValueError
"""
logger.info("test_linear_transformation_md5_05")
# Initialize parameters
height = 50
weight = 50
dim = 3 * height * weight
transformation_matrix = np.ones([dim, dim])
mean_vector = np.zeros(dim - 1)
# Generate dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
try:
transforms = [
py_vision.Decode(),
py_vision.CenterCrop([height, weight]),
py_vision.ToTensor(),
py_vision.LinearTransformation(transformation_matrix, mean_vector)
]
transform = py_vision.ComposeOp(transforms)
data1 = data1.map(input_columns=["image"], operations=transform())
except ValueError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "should match" in str(e)
def create_dataset_py(dataset_path, do_train, config, device_target, 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
"""
if device_target == "Ascend":
rank_size = int(os.getenv("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
if do_train:
if rank_size == 1:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
num_shards=rank_size, shard_id=rank_id)
else:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
else:
raise ValueError("Unsupported device target.")
resize_height = config.image_height
if do_train:
buffer_size = 20480
# apply shuffle operations
ds = ds.shuffle(buffer_size=buffer_size)
# define map operations
decode_op = P.Decode()
resize_crop_op = P.RandomResizedCrop(resize_height, scale=(0.08, 1.0), ratio=(0.75, 1.333))
horizontal_flip_op = P.RandomHorizontalFlip(prob=0.5)
resize_op = P.Resize(256)
center_crop = P.CenterCrop(resize_height)
to_tensor = P.ToTensor()
normalize_op = P.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
if do_train:
trans = [decode_op, resize_crop_op, horizontal_flip_op, to_tensor, normalize_op]
else:
trans = [decode_op, resize_op, center_crop, to_tensor, normalize_op]
compose = P.ComposeOp(trans)
ds = ds.map(input_columns="image", operations=compose(), num_parallel_workers=8, python_multiprocessing=True)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def test_linear_transformation_exception_02():
"""
Test LinearTransformation op: mean_vector is not provided
Expected to raise ValueError
"""
logger.info("test_linear_transformation_exception_02")
# Initialize parameters
height = 50
weight = 50
dim = 3 * height * weight
transformation_matrix = np.ones([dim, dim])
# Generate dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
try:
transforms = [
py_vision.Decode(),
py_vision.CenterCrop([height, weight]),
py_vision.ToTensor(),
py_vision.LinearTransformation(transformation_matrix, None)
]
transform = py_vision.ComposeOp(transforms)
data1 = data1.map(input_columns=["image"], operations=transform())
except TypeError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Argument mean_vector with value None is not of type (<class 'numpy.ndarray'>,)" in str(e)
def test_random_choice_comp(plot=False):
"""
Test RandomChoice and compare with single CenterCrop results
"""
logger.info("test_random_choice_comp")
# define map operations
transforms_list = [py_vision.CenterCrop(64)]
transforms1 = [
py_vision.Decode(),
py_vision.RandomChoice(transforms_list),
py_vision.ToTensor()
]
transform1 = py_vision.ComposeOp(transforms1)
transforms2 = [
py_vision.Decode(),
py_vision.CenterCrop(64),
py_vision.ToTensor()
]
transform2 = py_vision.ComposeOp(transforms2)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data1 = data1.map(input_columns=["image"], operations=transform1())
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=transform2())
image_choice = []
image_original = []
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
image1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image2 = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_choice.append(image1)
image_original.append(image2)
mse = diff_mse(image1, image2)
assert mse == 0
if plot:
visualize_list(image_original, image_choice)
def test_linear_transformation_op(plot=False):
"""
Test LinearTransformation op: verify if images transform correctly
"""
logger.info("test_linear_transformation_01")
# Initialize parameters
height = 50
weight = 50
dim = 3 * height * weight
transformation_matrix = np.eye(dim)
mean_vector = np.zeros(dim)
# Define operations
transforms = [
py_vision.Decode(),
py_vision.CenterCrop([height, weight]),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data1 = data1.map(input_columns=["image"], operations=transform())
# Note: if transformation matrix is diagonal matrix with all 1 in diagonal,
# the output matrix in expected to be the same as the input matrix.
data1 = data1.map(input_columns=["image"],
operations=py_vision.LinearTransformation(
transformation_matrix, mean_vector))
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=transform())
image_transformed = []
image = []
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
image1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image2 = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_transformed.append(image1)
image.append(image2)
mse = diff_mse(image1, image2)
assert mse == 0
if plot:
visualize_list(image, image_transformed)
def test_random_apply_op(plot=False):
"""
Test RandomApply in python transformations
"""
logger.info("test_random_apply_op")
# define map operations
transforms_list = [py_vision.CenterCrop(64), py_vision.RandomRotation(30)]
transforms1 = [
py_vision.Decode(),
py_vision.RandomApply(transforms_list, prob=0.6),
py_vision.ToTensor()
]
transform1 = py_vision.ComposeOp(transforms1)
transforms2 = [py_vision.Decode(), py_vision.ToTensor()]
transform2 = py_vision.ComposeOp(transforms2)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data1 = data1.map(input_columns=["image"], operations=transform1())
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=transform2())
image_apply = []
image_original = []
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
image1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image2 = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_apply.append(image1)
image_original.append(image2)
if plot:
visualize(image_original, image_apply)
def test_to_pil_01():
"""
Test ToPIL Op with md5 comparison: input is already PIL image
Expected to pass
"""
logger.info("test_to_pil_01")
# Generate dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
transforms = [
py_vision.Decode(),
# If input is already PIL image.
py_vision.ToPIL(),
py_vision.CenterCrop(375),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data1 = data1.map(input_columns=["image"], operations=transform())
# Compare with expected md5 from images
filename = "to_pil_01_result.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
def create_dataset(dataset_path,
do_train,
config,
platform,
repeat_num=1,
batch_size=100):
"""
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
"""
if platform == "Ascend":
rank_size = int(os.getenv("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
if rank_size == 1:
ds = de.MindDataset(dataset_path,
num_parallel_workers=8,
shuffle=True)
else:
ds = de.MindDataset(dataset_path,
num_parallel_workers=8,
shuffle=True,
num_shards=rank_size,
shard_id=rank_id)
elif platform == "GPU":
if do_train:
from mindspore.communication.management import get_rank, get_group_size
ds = de.MindDataset(dataset_path,
num_parallel_workers=8,
shuffle=True,
num_shards=get_group_size(),
shard_id=get_rank())
else:
ds = de.MindDataset(dataset_path,
num_parallel_workers=8,
shuffle=False)
else:
raise ValueError("Unsupport platform.")
resize_height = config.image_height
buffer_size = 1000
# define map operations
resize_crop_op = C.RandomCropDecodeResize(resize_height,
scale=(0.08, 1.0),
ratio=(0.75, 1.333))
horizontal_flip_op = C.RandomHorizontalFlip(prob=0.5)
color_op = C.RandomColorAdjust(brightness=0.4,
contrast=0.4,
saturation=0.4)
rescale_op = C.Rescale(1 / 255.0, 0)
normalize_op = C.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
change_swap_op = C.HWC2CHW()
# define python operations
decode_p = P.Decode()
resize_p = P.Resize(256, interpolation=Inter.BILINEAR)
center_crop_p = P.CenterCrop(224)
totensor = P.ToTensor()
normalize_p = P.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
composeop = P.ComposeOp(
[decode_p, resize_p, center_crop_p, totensor, normalize_p])
if do_train:
trans = [
resize_crop_op, horizontal_flip_op, color_op, rescale_op,
normalize_op, change_swap_op
]
else:
trans = composeop()
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image",
operations=trans,
num_parallel_workers=8)
ds = ds.map(input_columns="label_list",
operations=type_cast_op,
num_parallel_workers=8)
# 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_py(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("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
else:
init("nccl")
rank_id = get_rank()
device_num = get_group_size()
if do_train:
if device_num == 1:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=8,
shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=8,
shuffle=True,
num_shards=device_num,
shard_id=rank_id)
else:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=8,
shuffle=False)
image_size = 224
# define map operations
decode_op = P.Decode()
resize_crop_op = P.RandomResizedCrop(image_size,
scale=(0.08, 1.0),
ratio=(0.75, 1.333))
horizontal_flip_op = P.RandomHorizontalFlip(prob=0.5)
resize_op = P.Resize(256)
center_crop = P.CenterCrop(image_size)
to_tensor = P.ToTensor()
normalize_op = P.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
# define map operations
if do_train:
trans = [
decode_op, resize_crop_op, horizontal_flip_op, to_tensor,
normalize_op
]
else:
trans = [decode_op, resize_op, center_crop, to_tensor, normalize_op]
compose = P.ComposeOp(trans)
ds = ds.map(input_columns="image",
operations=compose(),
num_parallel_workers=8,
python_multiprocessing=True)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
