def test_auto_contrast_invalid_ignore_param_c():
"""
Test AutoContrast C Op with invalid ignore parameter
"""
logger.info("Test AutoContrast C Op with invalid ignore parameter")
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])
])
# invalid ignore
ds = ds.map(input_columns="image",
operations=C.AutoContrast(ignore=255.5))
except TypeError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Argument ignore with value 255.5 is not of type" in str(error)
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])
])
# invalid ignore
ds = ds.map(input_columns="image",
operations=C.AutoContrast(ignore=(10, 100)))
except TypeError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Argument ignore with value (10,100) is not of type" in str(
error)
def test_auto_contrast_invalid_cutoff_param_py():
"""
Test AutoContrast python Op with invalid cutoff parameter
"""
logger.info("Test AutoContrast python Op with invalid cutoff parameter")
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
F.ComposeOp([
F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(cutoff=-10.0),
F.ToTensor()
])
])
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Input cutoff is not within the required interval of (0 to 100)." in str(
error)
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
F.ComposeOp([
F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(cutoff=120.0),
F.ToTensor()
])
])
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Input cutoff is not within the required interval of (0 to 100)." in str(
error)
def test_auto_contrast_invalid_ignore_param_py():
"""
Test AutoContrast python Op with invalid ignore parameter
"""
logger.info("Test AutoContrast python Op with invalid ignore parameter")
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
F.ComposeOp([
F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(ignore=255.5),
F.ToTensor()
])
])
except TypeError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Argument ignore with value 255.5 is not of type" in str(error)
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
F.ComposeOp([
F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(ignore=(10, 100)),
F.ToTensor()
])
])
except TypeError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Argument ignore with value (10,100) is not of type" in str(
error)
def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32, target="Ascend"):
"""
create a train or eval imagenet2012 dataset for resnet50
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, rank_id = _get_rank_info()
else:
init("nccl")
rank_id = get_rank()
device_num = get_group_size()
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)
image_size = 224
mean = [0.485 * 255, 0.456 * 255, 0.406 * 255]
std = [0.229 * 255, 0.224 * 255, 0.225 * 255]
# define map operations
if do_train:
trans = [
C.RandomCropDecodeResize(image_size, scale=(0.08, 1.0), ratio=(0.75, 1.333)),
C.RandomHorizontalFlip(prob=0.5),
C.Normalize(mean=mean, std=std),
C.HWC2CHW()
]
else:
trans = [
C.Decode(),
C.Resize(256),
C.CenterCrop(image_size),
C.Normalize(mean=mean, std=std),
C.HWC2CHW()
]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image", num_parallel_workers=8, operations=trans)
ds = ds.map(input_columns="label", num_parallel_workers=8, operations=type_cast_op)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def test_random_sharpness_invalid_params():
"""
Test RandomSharpness with invalid input parameters.
"""
logger.info("Test RandomSharpness with invalid input parameters.")
try:
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"],
operations=[C.Decode(),
C.Resize((224, 224)),
C.RandomSharpness(10)])
except TypeError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "tuple" in str(error)
try:
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"],
operations=[C.Decode(),
C.Resize((224, 224)),
C.RandomSharpness((-10, 10))])
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "interval" in str(error)
try:
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"],
operations=[C.Decode(),
C.Resize((224, 224)),
C.RandomSharpness((10, 5))])
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "(min,max)" in str(error)
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_random_sharpness_py(degrees=(0.7, 0.7), plot=False):
"""
Test RandomSharpness python op
"""
logger.info("Test RandomSharpness python op")
# Original Images
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = F.ComposeOp(
[F.Decode(), F.Resize((224, 224)),
F.ToTensor()])
ds_original = data.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)
# Random Sharpness Adjusted Images
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
py_op = F.RandomSharpness()
if degrees is not None:
py_op = F.RandomSharpness(degrees)
transforms_random_sharpness = F.ComposeOp(
[F.Decode(), F.Resize((224, 224)), py_op,
F.ToTensor()])
ds_random_sharpness = data.map(input_columns="image",
operations=transforms_random_sharpness())
ds_random_sharpness = ds_random_sharpness.batch(512)
for idx, (image, _) in enumerate(ds_random_sharpness):
if idx == 0:
images_random_sharpness = np.transpose(image, (0, 2, 3, 1))
else:
images_random_sharpness = np.append(images_random_sharpness,
np.transpose(
image, (0, 2, 3, 1)),
axis=0)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_random_sharpness[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_original, images_random_sharpness)
def test_auto_contrast_invalid_cutoff_param_c():
"""
Test AutoContrast C Op with invalid cutoff parameter
"""
logger.info("Test AutoContrast C Op with invalid cutoff parameter")
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])
])
# invalid ignore
ds = ds.map(input_columns="image",
operations=C.AutoContrast(cutoff=-10.0))
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Input cutoff is not within the required interval of (0 to 100)." in str(
error)
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])
])
# invalid ignore
ds = ds.map(input_columns="image",
operations=C.AutoContrast(cutoff=120.0))
except ValueError as error:
logger.info("Got an exception in DE: {}".format(str(error)))
assert "Input cutoff is not within the required interval of (0 to 100)." in str(
error)
def test_random_sharpness_c(degrees=(1.6, 1.6), plot=False):
"""
Test RandomSharpness cpp op
"""
print(degrees)
logger.info("Test RandomSharpness cpp op")
# Original Images
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(),
C.Resize((224, 224))]
ds_original = data.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 = image
else:
images_original = np.append(images_original,
image,
axis=0)
# Random Sharpness Adjusted Images
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
c_op = C.RandomSharpness()
if degrees is not None:
c_op = C.RandomSharpness(degrees)
transforms_random_sharpness = [C.Decode(),
C.Resize((224, 224)),
c_op]
ds_random_sharpness = data.map(input_columns="image",
operations=transforms_random_sharpness)
ds_random_sharpness = ds_random_sharpness.batch(512)
for idx, (image, _) in enumerate(ds_random_sharpness):
if idx == 0:
images_random_sharpness = image
else:
images_random_sharpness = np.append(images_random_sharpness,
image,
axis=0)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_random_sharpness[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_original, images_random_sharpness)
def test_random_sharpness_c_py(degrees=(1.0, 1.0), plot=False):
"""
Test Random Sharpness C and python Op
"""
logger.info("Test RandomSharpness C and python Op")
# RandomSharpness Images
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((200, 300))])
python_op = F.RandomSharpness(degrees)
c_op = C.RandomSharpness(degrees)
transforms_op = F.ComposeOp(
[lambda img: F.ToPIL()(img.astype(np.uint8)), python_op, np.array])()
ds_random_sharpness_py = data.map(input_columns="image",
operations=transforms_op)
ds_random_sharpness_py = ds_random_sharpness_py.batch(512)
for idx, (image, _) in enumerate(ds_random_sharpness_py):
if idx == 0:
images_random_sharpness_py = image
else:
images_random_sharpness_py = np.append(images_random_sharpness_py,
image,
axis=0)
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((200, 300))])
ds_images_random_sharpness_c = data.map(input_columns="image",
operations=c_op)
ds_images_random_sharpness_c = ds_images_random_sharpness_c.batch(512)
for idx, (image, _) in enumerate(ds_images_random_sharpness_c):
if idx == 0:
images_random_sharpness_c = image
else:
images_random_sharpness_c = np.append(images_random_sharpness_c,
image,
axis=0)
num_samples = images_random_sharpness_c.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_random_sharpness_c[i],
images_random_sharpness_py[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_random_sharpness_c,
images_random_sharpness_py,
visualize_mode=2)
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, 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 == "GPU":
if do_train:
from mindspore.communication.management import get_rank, get_group_size
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
num_shards=get_group_size(), shard_id=get_rank())
else:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
else:
raise ValueError("Unsupported device_target.")
resize_height = config.image_height
resize_width = config.image_width
buffer_size = 1000
# define map operations
decode_op = C.Decode()
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)
resize_op = C.Resize(256)
center_crop = C.CenterCrop(resize_width)
rescale_op = C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
normalize_op = C.Normalize(mean=[0.485*255, 0.456*255, 0.406*255], std=[0.229*255, 0.224*255, 0.225*255])
change_swap_op = C.HWC2CHW()
if do_train:
trans = [resize_crop_op, horizontal_flip_op, rescale_op, normalize_op, change_swap_op]
else:
trans = [decode_op, resize_op, center_crop, normalize_op, change_swap_op]
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", 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 test_random_color(degrees=(0.1, 1.9), plot=False):
"""
Test RandomColor
"""
logger.info("Test RandomColor")
# Original Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = F.ComposeOp(
[F.Decode(), F.Resize((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)
# Random Color Adjusted Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_random_color = F.ComposeOp([
F.Decode(),
F.Resize((224, 224)),
F.RandomColor(degrees=degrees),
F.ToTensor()
])
ds_random_color = ds.map(input_columns="image",
operations=transforms_random_color())
ds_random_color = ds_random_color.batch(512)
for idx, (image, _) in enumerate(ds_random_color):
if idx == 0:
images_random_color = np.transpose(image, (0, 2, 3, 1))
else:
images_random_color = np.append(images_random_color,
np.transpose(image, (0, 2, 3, 1)),
axis=0)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = np.mean((images_random_color[i] - images_original[i])**2)
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize(images_original, images_random_color)
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
"""
rank_size = int(os.getenv("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
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)
resize_height = config.image_height
resize_width = config.image_width
buffer_size = 1000
# define map operations
decode_op = C.Decode()
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)
resize_op = C.Resize((256, 256))
center_crop = C.CenterCrop(resize_width)
rescale_op = C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
normalize_op = C.Normalize(mean=[0.485*255, 0.456*255, 0.406*255], std=[0.229*255, 0.224*255, 0.225*255])
change_swap_op = C.HWC2CHW()
if do_train:
trans = [resize_crop_op, horizontal_flip_op, rescale_op, normalize_op, change_swap_op]
else:
trans = [decode_op, resize_op, center_crop, rescale_op, normalize_op, change_swap_op]
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", 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 test_auto_contrast_c(plot=False):
"""
Test AutoContrast C Op
"""
logger.info("Test AutoContrast C Op")
# AutoContrast Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((224, 224))])
python_op = F.AutoContrast()
c_op = C.AutoContrast()
transforms_op = F.ComposeOp(
[lambda img: F.ToPIL()(img.astype(np.uint8)), python_op, np.array])()
ds_auto_contrast_py = ds.map(input_columns="image",
operations=transforms_op)
ds_auto_contrast_py = ds_auto_contrast_py.batch(512)
for idx, (image, _) in enumerate(ds_auto_contrast_py):
if idx == 0:
images_auto_contrast_py = image
else:
images_auto_contrast_py = np.append(images_auto_contrast_py,
image,
axis=0)
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((224, 224))])
ds_auto_contrast_c = ds.map(input_columns="image", operations=c_op)
ds_auto_contrast_c = ds_auto_contrast_c.batch(512)
for idx, (image, _) in enumerate(ds_auto_contrast_c):
if idx == 0:
images_auto_contrast_c = image
else:
images_auto_contrast_c = np.append(images_auto_contrast_c,
image,
axis=0)
num_samples = images_auto_contrast_c.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_auto_contrast_c[i],
images_auto_contrast_py[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
np.testing.assert_equal(np.mean(mse), 0.0)
if plot:
visualize_list(images_auto_contrast_c,
images_auto_contrast_py,
visualize_mode=2)
def create_dataset(dataset_path, config, do_train, repeat_num=1):
"""
create a train or eval dataset
Args:
dataset_path(string): the path of dataset.
config(dict): config of dataset.
do_train(bool): whether dataset is used for train or eval.
repeat_num(int): the repeat times of dataset. Default: 1.
Returns:
dataset
"""
rank = config.rank
group_size = config.group_size
if group_size == 1:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=config.work_nums,
shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=config.work_nums,
shuffle=True,
num_shards=group_size,
shard_id=rank)
# define map operations
if do_train:
trans = [
C.RandomCropDecodeResize(config.image_size),
C.RandomHorizontalFlip(prob=0.5),
C.RandomColorAdjust(brightness=0.4, saturation=0.5) # fast mode
#C.RandomColorAdjust(brightness=0.4, contrast=0.5, saturation=0.5, hue=0.2)
]
else:
trans = [
C.Decode(),
C.Resize(int(config.image_size / 0.875)),
C.CenterCrop(config.image_size)
]
trans += [
C.Rescale(1.0 / 255.0, 0.0),
C.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
C.HWC2CHW()
]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image",
operations=trans,
num_parallel_workers=config.work_nums)
ds = ds.map(input_columns="label",
operations=type_cast_op,
num_parallel_workers=config.work_nums)
# apply batch operations
ds = ds.batch(config.batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def test_equalize_py(plot=False):
"""
Test Equalize py op
"""
logger.info("Test Equalize")
# Original Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = F.ComposeOp(
[F.Decode(), F.Resize((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)
# Color Equalized Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_equalize = F.ComposeOp(
[F.Decode(),
F.Resize((224, 224)),
F.Equalize(),
F.ToTensor()])
ds_equalize = ds.map(input_columns="image",
operations=transforms_equalize())
ds_equalize = ds_equalize.batch(512)
for idx, (image, _) in enumerate(ds_equalize):
if idx == 0:
images_equalize = np.transpose(image, (0, 2, 3, 1))
else:
images_equalize = np.append(images_equalize,
np.transpose(image, (0, 2, 3, 1)),
axis=0)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_equalize[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_original, images_equalize)
def test_auto_contrast(plot=False):
"""
Test AutoContrast
"""
logger.info("Test AutoContrast")
# Original Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = F.ComposeOp(
[F.Decode(), F.Resize((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)
# AutoContrast Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_auto_contrast = F.ComposeOp(
[F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(),
F.ToTensor()])
ds_auto_contrast = ds.map(input_columns="image",
operations=transforms_auto_contrast())
ds_auto_contrast = ds_auto_contrast.batch(512)
for idx, (image, _) in enumerate(ds_auto_contrast):
if idx == 0:
images_auto_contrast = np.transpose(image, (0, 2, 3, 1))
else:
images_auto_contrast = np.append(images_auto_contrast,
np.transpose(image, (0, 2, 3, 1)),
axis=0)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = np.mean((images_auto_contrast[i] - images_original[i])**2)
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize(images_original, images_auto_contrast)
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("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
if device_num == 1:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=False)
else:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
num_shards=device_num, shard_id=rank_id)
image_size = 224
mean = [0.485 * 255, 0.456 * 255, 0.406 * 255]
std = [0.229 * 255, 0.224 * 255, 0.225 * 255]
if do_train:
transform_img = [
V_C.RandomCropDecodeResize(image_size, scale=(0.08, 1.0), ratio=(0.75, 1.333)),
V_C.RandomHorizontalFlip(prob=0.5),
V_C.Normalize(mean=mean, std=std),
V_C.HWC2CHW()
]
else:
transform_img = [
V_C.Decode(),
V_C.Resize((256, 256)),
V_C.CenterCrop(image_size),
V_C.Normalize(mean=mean, std=std),
V_C.HWC2CHW()
]
# type_cast_op = C2.TypeCast(mstype.float16)
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image", operations=transform_img, num_parallel_workers=8)
ds = ds.map(input_columns="label", operations=type_cast_op, num_parallel_workers=8)
# 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
def create_dataset(dataset_path, do_train, rank, group_size, 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.
rank (int): The shard ID within num_shards (default=None).
group_size (int): Number of shards that the dataset should be divided into (default=None).
repeat_num(int): the repeat times of dataset. Default: 1.
Returns:
dataset
"""
if group_size == 1:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=cfg.work_nums,
shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=cfg.work_nums,
shuffle=True,
num_shards=group_size,
shard_id=rank)
# define map operations
if do_train:
trans = [
C.RandomCropDecodeResize(299,
scale=(0.08, 1.0),
ratio=(0.75, 1.333)),
C.RandomHorizontalFlip(prob=0.5),
C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
]
else:
trans = [C.Decode(), C.Resize(299), C.CenterCrop(299)]
trans += [
C.Rescale(1.0 / 255.0, 0.0),
C.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
C.HWC2CHW()
]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image",
operations=trans,
num_parallel_workers=cfg.work_nums)
ds = ds.map(input_columns="label",
operations=type_cast_op,
num_parallel_workers=cfg.work_nums)
# apply batch operations
ds = ds.batch(cfg.batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def test_invert_py_c(plot=False):
"""
Test Invert Cpp op and python op
"""
logger.info("Test Invert cpp and python op")
# Invert Images in cpp
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((224, 224))])
ds_c_invert = ds.map(input_columns="image", operations=C.Invert())
ds_c_invert = ds_c_invert.batch(512)
for idx, (image, _) in enumerate(ds_c_invert):
if idx == 0:
images_c_invert = image
else:
images_c_invert = np.append(images_c_invert, image, axis=0)
# invert images in python
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[C.Decode(), C.Resize((224, 224))])
transforms_p_invert = F.ComposeOp(
[lambda img: img.astype(np.uint8),
F.ToPIL(),
F.Invert(), np.array])
ds_p_invert = ds.map(input_columns="image",
operations=transforms_p_invert())
ds_p_invert = ds_p_invert.batch(512)
for idx, (image, _) in enumerate(ds_p_invert):
if idx == 0:
images_p_invert = image
else:
images_p_invert = np.append(images_p_invert, image, axis=0)
num_samples = images_c_invert.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_p_invert[i], images_c_invert[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_c_invert, images_p_invert, visualize_mode=2)
def test_random_sharpness_md5():
"""
Test RandomSharpness with md5 comparison
"""
logger.info("Test RandomSharpness with md5 comparison")
original_seed = config_get_set_seed(5)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms = [
F.Decode(),
F.RandomSharpness((0.1, 1.9)),
F.ToTensor()
]
transform = F.ComposeOp(transforms)
# Generate dataset
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"], operations=transform())
# check results with md5 comparison
filename = "random_sharpness_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_random_sharpness_c_md5():
"""
Test RandomSharpness cpp op with md5 comparison
"""
logger.info("Test RandomSharpness cpp op with md5 comparison")
original_seed = config_get_set_seed(200)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms = [
C.Decode(),
C.RandomSharpness((10.0, 15.0))
]
# Generate dataset
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"], operations=transforms)
# check results with md5 comparison
filename = "random_sharpness_cpp_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_invert_c(plot=False):
"""
Test Invert Cpp op
"""
logger.info("Test Invert cpp op")
# Original Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(), C.Resize(size=[224, 224])]
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 = image
else:
images_original = np.append(images_original, image, axis=0)
# Invert Images
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transform_invert = [C.Decode(), C.Resize(size=[224, 224]), C.Invert()]
ds_invert = ds.map(input_columns="image", operations=transform_invert)
ds_invert = ds_invert.batch(512)
for idx, (image, _) in enumerate(ds_invert):
if idx == 0:
images_invert = image
else:
images_invert = np.append(images_invert, image, axis=0)
if plot:
visualize_list(images_original, images_invert)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_invert[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
def test_equalize_md5_py():
"""
Test Equalize py op with md5 check
"""
logger.info("Test Equalize")
# First dataset
data1 = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms = F.ComposeOp([F.Decode(), F.Equalize(), F.ToTensor()])
data1 = data1.map(input_columns="image", operations=transforms())
# Compare with expected md5 from images
filename = "equalize_01_result.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
def test_invert_md5_py():
"""
Test Invert python op with md5 check
"""
logger.info("Test Invert python op with md5 check")
# Generate dataset
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_invert = F.ComposeOp([F.Decode(), F.Invert(), F.ToTensor()])
data = ds.map(input_columns="image", operations=transforms_invert())
# Compare with expected md5 from images
filename = "invert_01_result_py.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
def test_invert_md5_c():
"""
Test Invert cpp op with md5 check
"""
logger.info("Test Invert cpp op with md5 check")
# Generate dataset
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms_invert = [
C.Decode(),
C.Resize(size=[224, 224]),
C.Invert(),
F.ToTensor()
]
data = ds.map(input_columns="image", operations=transforms_invert)
# Compare with expected md5 from images
filename = "invert_01_result_c.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
def test_invert_one_channel():
"""
Test Invert cpp op with one channel image
"""
logger.info("Test Invert C Op With One Channel Images")
c_op = C.Invert()
try:
ds = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
ds = ds.map(input_columns=["image"],
operations=[
C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])
])
ds.map(input_columns="image", operations=c_op)
except RuntimeError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "The shape" in str(e)
def test_random_color_md5():
"""
Test RandomColor with md5 check
"""
logger.info("Test RandomColor with md5 check")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
transforms = F.ComposeOp(
[F.Decode(), F.RandomColor((0.1, 1.9)),
F.ToTensor()])
data = data.map(input_columns="image", operations=transforms())
# Compare with expected md5 from images
filename = "random_color_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 create_dataset3(dataset_path, do_train, repeat_num=1, batch_size=32):
"""
create a train or eval imagenet2012 dataset for resnet101
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("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
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)
resize_height = 224
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
decode_op = C.Decode()
random_resize_crop_op = C.RandomResizedCrop(resize_height, (0.08, 1.0), (0.75, 1.33), max_attempts=100)
horizontal_flip_op = C.RandomHorizontalFlip(rank_id / (rank_id + 1))
resize_op_256 = C.Resize((256, 256))
center_crop = C.CenterCrop(224)
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize((0.475, 0.451, 0.392), (0.275, 0.267, 0.278))
changeswap_op = C.HWC2CHW()
if do_train:
trans = [decode_op,
random_resize_crop_op,
horizontal_flip_op,
rescale_op,
normalize_op,
changeswap_op]
else:
trans = [decode_op,
resize_op_256,
center_crop,
rescale_op,
normalize_op,
changeswap_op]
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", operations=type_cast_op, num_parallel_workers=8)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds