def test_imagefolder():
data = ds.ImageFolderDataset("../data/dataset/testPK/data/")
assert data.get_dataset_size() == 44
assert data.num_classes() == 4
data = data.shuffle(100)
assert data.num_classes() == 4
data = ds.ImageFolderDataset("../data/dataset/testPK/data/",
num_samples=10)
assert data.get_dataset_size() == 10
assert data.num_classes() == 4
data = ds.ImageFolderDataset("../data/dataset/testPK/data/",
class_indexing={
"class1": 1,
"class2": 22
})
assert data.num_classes() == 2
data = ds.ImageFolderDataset("../data/dataset/testPK/data/",
class_indexing={
"class1": 1,
"wrong name": 22
})
err_msg = ""
try:
data.num_classes()
except RuntimeError as e:
err_msg = str(e)
assert "wrong name doesn't exist" in err_msg
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(
cutoff=-10.0),
F.ToTensor()])],
input_columns=["image"])
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(
operations=[mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(cutoff=120.0),
F.ToTensor()])],
input_columns=["image"])
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_sampler_list():
data1 = ds.ImageFolderDataset("../data/dataset/testPK/data", sampler=[1, 3, 5])
data21 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(2).skip(1)
data22 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(4).skip(3)
data23 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(6).skip(5)
dataset_equal(data1, data21 + data22 + data23, 0)
def test_random_color_py(degrees=(0.1, 1.9), plot=False):
"""
Test Python RandomColor
"""
logger.info("Test RandomColor")
# Original Images
data = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = mindspore.dataset.transforms.py_transforms.Compose(
[F.Decode(), F.Resize((224, 224)),
F.ToTensor()])
ds_original = data.map(operations=transforms_original,
input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = np.transpose(image.asnumpy(), (0, 2, 3, 1))
else:
images_original = np.append(images_original,
np.transpose(image.asnumpy(),
(0, 2, 3, 1)),
axis=0)
# Random Color Adjusted Images
data = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_random_color = mindspore.dataset.transforms.py_transforms.Compose(
[
F.Decode(),
F.Resize((224, 224)),
F.RandomColor(degrees=degrees),
F.ToTensor()
])
ds_random_color = data.map(operations=transforms_random_color,
input_columns="image")
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.asnumpy(), (0, 2, 3, 1))
else:
images_random_color = np.append(images_random_color,
np.transpose(
image.asnumpy(), (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_color[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_original, images_random_color)
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])], input_columns=["image"])
# invalid ignore
data_set = data_set.map(operations=C.AutoContrast(cutoff=-10.0), input_columns="image")
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(),
C.Resize((224, 224)),
lambda img: np.array(img[:, :, 0])], input_columns=["image"])
# invalid ignore
data_set = data_set.map(operations=C.AutoContrast(cutoff=120.0), input_columns="image")
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(
ignore=255.5),
F.ToTensor()])],
input_columns=["image"])
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(
ignore=(10, 100)),
F.ToTensor()])],
input_columns=["image"])
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_ignore_param_c():
"""
Test AutoContrast C Op with invalid ignore parameter
"""
logger.info("Test AutoContrast C Op with invalid ignore parameter")
try:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[
C.Decode(),
C.Resize((224, 224)), lambda img: np.array(img[:, :, 0])
],
input_columns=["image"])
# invalid ignore
data_set = data_set.map(operations=C.AutoContrast(ignore=255.5),
input_columns="image")
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:
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[
C.Decode(),
C.Resize((224, 224)), lambda img: np.array(img[:, :, 0])
],
input_columns=["image"])
# invalid ignore
data_set = data_set.map(operations=C.AutoContrast(ignore=(10, 100)),
input_columns="image")
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_imagefolder_zip():
logger.info("Test Case zip")
# define parameters
repeat_count = 2
# apply dataset operations
data1 = ds.ImageFolderDataset(DATA_DIR, num_samples=10)
data2 = ds.ImageFolderDataset(DATA_DIR, num_samples=10)
data1 = data1.repeat(repeat_count)
# rename dataset2 for no conflict
data2 = data2.rename(input_columns=["image", "label"],
output_columns=["image1", "label1"])
data3 = ds.zip((data1, data2))
num_iter = 0
for item in data3.create_dict_iterator(
num_epochs=1): # each data is a dictionary
# in this example, each dictionary has keys "image" and "label"
logger.info("image is {}".format(item["image"]))
logger.info("label is {}".format(item["label"]))
num_iter += 1
logger.info("Number of data in data1: {}".format(num_iter))
assert num_iter == 10
def test_sampler_list():
data1 = ds.ImageFolderDataset("../data/dataset/testPK/data", sampler=[1, 3, 5])
data21 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(2).skip(1)
data22 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(4).skip(3)
data23 = ds.ImageFolderDataset("../data/dataset/testPK/data", shuffle=False).take(6).skip(5)
dataset_equal(data1, data21 + data22 + data23, 0)
data3 = ds.ImageFolderDataset("../data/dataset/testPK/data", sampler=1)
dataset_equal(data3, data21, 0)
def bad_pipeline(sampler, msg):
with pytest.raises(Exception) as info:
data1 = ds.ImageFolderDataset("../data/dataset/testPK/data", sampler=sampler)
for _ in data1:
pass
assert msg in str(info.value)
bad_pipeline(sampler=[1.5, 7],
msg="Type of indices element must be int, but got list[0]: 1.5, type: <class 'float'>")
bad_pipeline(sampler=["a", "b"],
msg="Type of indices element must be int, but got list[0]: a, type: <class 'str'>.")
bad_pipeline(sampler="a", msg="Unsupported sampler object of type (<class 'str'>)")
bad_pipeline(sampler="", msg="Unsupported sampler object of type (<class 'str'>)")
bad_pipeline(sampler=np.array([1, 2]),
msg="Type of indices element must be int, but got list[0]: 1, type: <class 'numpy.int64'>.")
def test_config(plot, file_name, op_list):
data_dir = "../data/dataset/testImageNetData/train/"
data1 = ds.ImageFolderDataset(dataset_dir=data_dir, shuffle=False)
data1 = data1.map(operations=op_list, input_columns=["image"])
data2 = ds.ImageFolderDataset(dataset_dir=data_dir, shuffle=False)
data2 = data2.map(operations=c_vision.Decode(),
input_columns=["image"])
original_images = []
transformed_images = []
for item in data1.create_dict_iterator(num_epochs=1,
output_numpy=True):
transformed_images.append(item["image"])
for item in data2.create_dict_iterator(num_epochs=1,
output_numpy=True):
original_images.append(item["image"])
if run_golden:
# Compare with expected md5 from images
save_and_check_md5(data1,
file_name,
generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(original_images, transformed_images)
def test_concat_14():
"""
Test concat: Testing concat on two different source datasets with different dataset operations.
"""
logger.info("test_concat_14")
DATA_DIR = "../data/dataset/testPK/data"
DATA_DIR2 = "../data/dataset/testImageNetData/train/"
data1 = ds.ImageFolderDataset(DATA_DIR, num_samples=3)
data2 = ds.ImageFolderDataset(DATA_DIR2, num_samples=2)
transforms1 = mindspore.dataset.transforms.py_transforms.Compose(
[F.Decode(), F.Resize((224, 224)),
F.ToTensor()])
data1 = data1.map(operations=transforms1, input_columns=["image"])
data2 = data2.map(operations=transforms1, input_columns=["image"])
data3 = data1 + data2
expected, output = [], []
for d in data1.create_tuple_iterator(output_numpy=True):
expected.append(d[0])
for d in data2.create_tuple_iterator(output_numpy=True):
expected.append(d[0])
for d in data3.create_tuple_iterator(output_numpy=True):
output.append(d[0])
assert len(expected) == len(output)
np.array_equal(np.array(output), np.array(expected))
assert sum([1 for _ in data3]) == 5
assert data3.get_dataset_size() == 5
def test_auto_contrast_py(plot=False):
"""
Test AutoContrast
"""
logger.info("Test AutoContrast Python Op")
# Original Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.ToTensor()])
ds_original = data_set.map(operations=transforms_original, input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = np.transpose(image.asnumpy(), (0, 2, 3, 1))
else:
images_original = np.append(images_original,
np.transpose(image.asnumpy(), (0, 2, 3, 1)),
axis=0)
# AutoContrast Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_auto_contrast = \
mindspore.dataset.transforms.py_transforms.Compose([F.Decode(),
F.Resize((224, 224)),
F.AutoContrast(cutoff=10.0, ignore=[10, 20]),
F.ToTensor()])
ds_auto_contrast = data_set.map(operations=transforms_auto_contrast, input_columns="image")
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.asnumpy(), (0, 2, 3, 1))
else:
images_auto_contrast = np.append(images_auto_contrast,
np.transpose(image.asnumpy(), (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_auto_contrast[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
# Compare with expected md5 from images
filename = "autocontrast_01_result_py.npz"
save_and_check_md5(ds_auto_contrast, filename, generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(images_original, images_auto_contrast)
def test_equalize_py(plot=False):
"""
Test Equalize py op
"""
logger.info("Test Equalize")
# Original Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = mindspore.dataset.transforms.py_transforms.Compose(
[F.Decode(), F.Resize((224, 224)),
F.ToTensor()])
ds_original = data_set.map(operations=transforms_original,
input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = np.transpose(image.asnumpy(), (0, 2, 3, 1))
else:
images_original = np.append(images_original,
np.transpose(image.asnumpy(),
(0, 2, 3, 1)),
axis=0)
# Color Equalized Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_equalize = mindspore.dataset.transforms.py_transforms.Compose(
[F.Decode(),
F.Resize((224, 224)),
F.Equalize(),
F.ToTensor()])
ds_equalize = data_set.map(operations=transforms_equalize,
input_columns="image")
ds_equalize = ds_equalize.batch(512)
for idx, (image, _) in enumerate(ds_equalize):
if idx == 0:
images_equalize = np.transpose(image.asnumpy(), (0, 2, 3, 1))
else:
images_equalize = np.append(images_equalize,
np.transpose(image.asnumpy(),
(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_cpp_uniform_augment(plot=False, num_ops=2):
"""
Test UniformAugment
"""
logger.info("Test CPP UniformAugment")
# Original Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(), C.Resize(size=[224, 224]),
F.ToTensor()]
ds_original = data_set.map(operations=transforms_original, input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = np.transpose(image.asnumpy(), (0, 2, 3, 1))
else:
images_original = np.append(images_original,
np.transpose(image.asnumpy(), (0, 2, 3, 1)),
axis=0)
# UniformAugment Images
data_set = ds.ImageFolderDataset(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(transforms=transforms_ua, num_ops=num_ops)
transforms_all = [C.Decode(), C.Resize(size=[224, 224]),
uni_aug,
F.ToTensor()]
ds_ua = data_set.map(operations=transforms_all, input_columns="image", 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.asnumpy(), (0, 2, 3, 1))
else:
images_ua = np.append(images_ua,
np.transpose(image.asnumpy(), (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 test_equalize_py_c(plot=False):
"""
Test Equalize Cpp op and python op
"""
logger.info("Test Equalize cpp and python op")
# equalize Images in cpp
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(),
C.Resize((224, 224))],
input_columns=["image"])
ds_c_equalize = data_set.map(operations=C.Equalize(),
input_columns="image")
ds_c_equalize = ds_c_equalize.batch(512)
for idx, (image, _) in enumerate(ds_c_equalize):
if idx == 0:
images_c_equalize = image.asnumpy()
else:
images_c_equalize = np.append(images_c_equalize,
image.asnumpy(),
axis=0)
# Equalize images in python
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(),
C.Resize((224, 224))],
input_columns=["image"])
transforms_p_equalize = mindspore.dataset.transforms.py_transforms.Compose(
[lambda img: img.astype(np.uint8),
F.ToPIL(),
F.Equalize(), np.array])
ds_p_equalize = data_set.map(operations=transforms_p_equalize,
input_columns="image")
ds_p_equalize = ds_p_equalize.batch(512)
for idx, (image, _) in enumerate(ds_p_equalize):
if idx == 0:
images_p_equalize = image.asnumpy()
else:
images_p_equalize = np.append(images_p_equalize,
image.asnumpy(),
axis=0)
num_samples = images_c_equalize.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_p_equalize[i], images_c_equalize[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
if plot:
visualize_list(images_c_equalize, images_p_equalize, visualize_mode=2)
def create_dataset(dataset_path,
do_train,
repeat_num=1,
batch_size=32,
target="GPU",
dtype="fp16",
device_num=1):
ds.config.set_numa_enable(True)
if device_num == 1:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=4,
shuffle=True)
else:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=4,
shuffle=True,
num_shards=device_num,
shard_id=get_rank())
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
normalize_op = C.Normalize(mean=mean, std=std)
if dtype == "fp16":
if args_opt.eval:
x_dtype = "float32"
else:
x_dtype = "float16"
normalize_op = C.NormalizePad(mean=mean, std=std, dtype=x_dtype)
if do_train:
trans = [
C.RandomCropDecodeResize(image_size,
scale=(0.08, 1.0),
ratio=(0.75, 1.333)),
C.RandomHorizontalFlip(prob=0.5),
normalize_op,
]
else:
trans = [
C.Decode(),
C.Resize(256),
C.CenterCrop(image_size),
normalize_op,
]
if dtype == "fp32":
trans.append(C.HWC2CHW())
data_set = data_set.map(operations=trans,
input_columns="image",
num_parallel_workers=8)
# apply batch operations
data_set = data_set.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
if repeat_num > 1:
data_set = data_set.repeat(repeat_num)
return data_set
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 = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(), C.Resize((224, 224))]
ds_original = data.map(operations=transforms_original,
input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(
ds_original.create_tuple_iterator(output_numpy=True)):
if idx == 0:
images_original = image
else:
images_original = np.append(images_original, image, axis=0)
# Random Sharpness Adjusted Images
data = ds.ImageFolderDataset(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(operations=transforms_random_sharpness,
input_columns="image")
ds_random_sharpness = ds_random_sharpness.batch(512)
for idx, (image, _) in enumerate(
ds_random_sharpness.create_tuple_iterator(output_numpy=True)):
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 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:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=config.work_nums,
shuffle=True)
else:
data_set = ds.ImageFolderDataset(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
]
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)
data_set = data_set.map(operations=trans,
input_columns="image",
num_parallel_workers=config.work_nums)
data_set = data_set.map(operations=type_cast_op,
input_columns="label",
num_parallel_workers=config.work_nums)
# apply batch operations
data_set = data_set.batch(config.batch_size, drop_remainder=True)
# apply dataset repeat operation
data_set = data_set.repeat(repeat_num)
return data_set
def test_auto_contrast_one_channel_c(plot=False):
"""
Test AutoContrast C op with one channel
"""
logger.info("Test AutoContrast C Op With One Channel Images")
# AutoContrast Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(), C.Resize((224, 224))], input_columns=["image"])
python_op = F.AutoContrast()
c_op = C.AutoContrast()
# not using F.ToTensor() since it converts to floats
transforms_op = mindspore.dataset.transforms.py_transforms.Compose(
[lambda img: (np.array(img)[:, :, 0]).astype(np.uint8),
F.ToPIL(),
python_op,
np.array])
ds_auto_contrast_py = data_set.map(operations=transforms_op, input_columns="image")
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.asnumpy()
else:
images_auto_contrast_py = np.append(images_auto_contrast_py,
image.asnumpy(),
axis=0)
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(), C.Resize((224, 224)), lambda img: np.array(img[:, :, 0])],
input_columns=["image"])
ds_auto_contrast_c = data_set.map(operations=c_op, input_columns="image")
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.asnumpy()
else:
images_auto_contrast_c = np.append(images_auto_contrast_c,
image.asnumpy(),
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 test_auto_contrast_c(plot=False):
"""
Test AutoContrast C Op
"""
logger.info("Test AutoContrast C Op")
# AutoContrast Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(), C.Resize((224, 224))], input_columns=["image"])
python_op = F.AutoContrast(cutoff=10.0, ignore=[10, 20])
c_op = C.AutoContrast(cutoff=10.0, ignore=[10, 20])
transforms_op = mindspore.dataset.transforms.py_transforms.Compose([lambda img: F.ToPIL()(img.astype(np.uint8)),
python_op,
np.array])
ds_auto_contrast_py = data_set.map(operations=transforms_op, input_columns="image")
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.asnumpy()
else:
images_auto_contrast_py = np.append(images_auto_contrast_py,
image.asnumpy(),
axis=0)
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data_set = data_set.map(operations=[C.Decode(), C.Resize((224, 224))], input_columns=["image"])
ds_auto_contrast_c = data_set.map(operations=c_op, input_columns="image")
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.asnumpy()
else:
images_auto_contrast_c = np.append(images_auto_contrast_c,
image.asnumpy(),
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)
# Compare with expected md5 from images
filename = "autocontrast_01_result_c.npz"
save_and_check_md5(ds_auto_contrast_c, filename, generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(images_auto_contrast_c, images_auto_contrast_py, visualize_mode=2)
def test_cutmix_batch_success3(plot=False):
"""
Test CutMixBatch op with default values for alpha and prob on a batch of HWC images on ImageFolderDataset
"""
logger.info("test_cutmix_batch_success3")
ds_original = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False)
decode_op = vision.Decode()
ds_original = ds_original.map(operations=[decode_op],
input_columns=["image"])
resize_op = vision.Resize([224, 224])
ds_original = ds_original.map(operations=[resize_op],
input_columns=["image"])
ds_original = ds_original.batch(4, pad_info={}, drop_remainder=True)
images_original = None
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = image.asnumpy()
else:
images_original = np.append(images_original,
image.asnumpy(),
axis=0)
# CutMix Images
data1 = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False)
decode_op = vision.Decode()
data1 = data1.map(operations=[decode_op], input_columns=["image"])
resize_op = vision.Resize([224, 224])
data1 = data1.map(operations=[resize_op], input_columns=["image"])
one_hot_op = data_trans.OneHot(num_classes=10)
data1 = data1.map(operations=one_hot_op, input_columns=["label"])
cutmix_batch_op = vision.CutMixBatch(mode.ImageBatchFormat.NHWC)
data1 = data1.batch(4, pad_info={}, drop_remainder=True)
data1 = data1.map(operations=cutmix_batch_op,
input_columns=["image", "label"])
images_cutmix = None
for idx, (image, _) in enumerate(data1):
if idx == 0:
images_cutmix = image.asnumpy()
else:
images_cutmix = np.append(images_cutmix, image.asnumpy(), axis=0)
if plot:
visualize_list(images_original, images_cutmix)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_cutmix[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
def test_imagefolder():
data = ds.ImageFolderDataset("../data/dataset/testPK/data/")
assert data.get_dataset_size() == 44
assert data.num_classes() == 4
data = data.shuffle(100)
assert data.num_classes() == 4
data = ds.ImageFolderDataset("../data/dataset/testPK/data/",
num_samples=10)
assert data.get_dataset_size() == 10
assert data.num_classes() == 4
def create_dataset(dataset_path,
do_train,
batch_size=16,
device_num=1,
rank=0):
"""
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.
batch_size(int): the batch size of dataset. Default: 16.
device_num (int): Number of shards that the dataset should be divided into (default=1).
rank (int): The shard ID within num_shards (default=0).
Returns:
dataset
"""
if device_num == 1:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=8,
shuffle=True)
else:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=8,
shuffle=True,
num_shards=device_num,
shard_id=rank)
# define map operations
if do_train:
trans = [
C.RandomCropDecodeResize(299),
C.RandomHorizontalFlip(prob=0.5),
C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
]
else:
trans = [C.Decode(), C.Resize(320), C.CenterCrop(299)]
trans += [
C.Normalize(mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5]),
C.HWC2CHW(),
C2.TypeCast(mstype.float32)
]
type_cast_op = C2.TypeCast(mstype.int32)
data_set = data_set.map(input_columns="image",
operations=trans,
num_parallel_workers=8)
data_set = data_set.map(input_columns="label",
operations=type_cast_op,
num_parallel_workers=8)
# apply batch operations
data_set = data_set.batch(batch_size, drop_remainder=True)
return data_set
def test_imagenet_rawdata_dataset_size():
ds_total = ds.ImageFolderDataset(IMAGENET_RAWDATA_DIR)
assert ds_total.get_dataset_size() == 6
ds_shard_1_0 = ds.ImageFolderDataset(IMAGENET_RAWDATA_DIR, num_shards=1, shard_id=0)
assert ds_shard_1_0.get_dataset_size() == 6
ds_shard_2_0 = ds.ImageFolderDataset(IMAGENET_RAWDATA_DIR, num_shards=2, shard_id=0)
assert ds_shard_2_0.get_dataset_size() == 3
ds_shard_3_0 = ds.ImageFolderDataset(IMAGENET_RAWDATA_DIR, num_shards=3, shard_id=0)
assert ds_shard_3_0.get_dataset_size() == 2
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.
"""
do_shuffle = bool(do_train)
if device_num == 1 or not do_train:
ds = de.ImageFolderDataset(dataset_path, num_parallel_workers=config.work_nums, shuffle=do_shuffle)
else:
ds = de.ImageFolderDataset(dataset_path, num_parallel_workers=config.work_nums,
shuffle=do_shuffle, num_shards=device_num, shard_id=device_id)
image_length = 299
if do_train:
trans = [
C.RandomCropDecodeResize(image_length, 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(image_length),
C.CenterCrop(image_length)
]
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="label", operations=type_cast_op, num_parallel_workers=config.work_nums)
ds = ds.map(input_columns="image", operations=trans, num_parallel_workers=config.work_nums)
# 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:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=cfg.work_nums,
shuffle=True)
else:
data_set = ds.ImageFolderDataset(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(224),
C.RandomHorizontalFlip(prob=0.5),
C.RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
]
else:
trans = [C.Decode(), C.Resize(256), C.CenterCrop(224)]
trans += [
toBGR(),
C.Rescale(1.0 / 255.0, 0.0),
C.HWC2CHW(),
C2.TypeCast(mstype.float32)
]
type_cast_op = C2.TypeCast(mstype.int32)
data_set = data_set.map(operations=trans,
input_columns="image",
num_parallel_workers=cfg.work_nums)
data_set = data_set.map(operations=type_cast_op,
input_columns="label",
num_parallel_workers=cfg.work_nums)
# apply batch operations
data_set = data_set.batch(cfg.batch_size, drop_remainder=True)
return data_set
def create_dataset_imagenet(dataset_path, do_train, cfg, 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.
cfg (dict): the config for creating dataset.
repeat_num(int): the repeat times of dataset. Default: 1.
Returns:
dataset
"""
if cfg.group_size == 1:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=cfg.work_nums,
shuffle=True)
else:
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=cfg.work_nums,
shuffle=True,
num_shards=cfg.group_size,
shard_id=cfg.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)
data_set = data_set.map(operations=trans,
input_columns="image",
num_parallel_workers=cfg.work_nums)
data_set = data_set.map(operations=type_cast_op,
input_columns="label",
num_parallel_workers=cfg.work_nums)
# apply batch operations
data_set = data_set.batch(cfg.batch_size, drop_remainder=True)
# apply dataset repeat operation
data_set = data_set.repeat(repeat_num)
return data_set
def test_mixup_batch_success2(plot=False):
"""
Test MixUpBatch op with specified alpha parameter on ImageFolderDataset
"""
logger.info("test_mixup_batch_success2")
# Original Images
ds_original = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False)
decode_op = vision.Decode()
ds_original = ds_original.map(operations=[decode_op],
input_columns=["image"])
ds_original = ds_original.batch(4, pad_info={}, drop_remainder=True)
images_original = None
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = image.asnumpy()
else:
images_original = np.append(images_original,
image.asnumpy(),
axis=0)
# MixUp Images
data1 = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False)
decode_op = vision.Decode()
data1 = data1.map(operations=[decode_op], input_columns=["image"])
one_hot_op = data_trans.OneHot(num_classes=10)
data1 = data1.map(operations=one_hot_op, input_columns=["label"])
mixup_batch_op = vision.MixUpBatch(2.0)
data1 = data1.batch(4, pad_info={}, drop_remainder=True)
data1 = data1.map(operations=mixup_batch_op,
input_columns=["image", "label"])
images_mixup = None
for idx, (image, _) in enumerate(data1):
if idx == 0:
images_mixup = image.asnumpy()
else:
images_mixup = np.append(images_mixup, image.asnumpy(), axis=0)
if plot:
visualize_list(images_original, images_mixup)
num_samples = images_original.shape[0]
mse = np.zeros(num_samples)
for i in range(num_samples):
mse[i] = diff_mse(images_mixup[i], images_original[i])
logger.info("MSE= {}".format(str(np.mean(mse))))
def test_equalize_c(plot=False):
"""
Test Equalize Cpp op
"""
logger.info("Test Equalize cpp op")
# Original Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transforms_original = [C.Decode(), C.Resize(size=[224, 224])]
ds_original = data_set.map(operations=transforms_original,
input_columns="image")
ds_original = ds_original.batch(512)
for idx, (image, _) in enumerate(ds_original):
if idx == 0:
images_original = image.asnumpy()
else:
images_original = np.append(images_original,
image.asnumpy(),
axis=0)
# Equalize Images
data_set = ds.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
transform_equalize = [C.Decode(), C.Resize(size=[224, 224]), C.Equalize()]
ds_equalize = data_set.map(operations=transform_equalize,
input_columns="image")
ds_equalize = ds_equalize.batch(512)
for idx, (image, _) in enumerate(ds_equalize):
if idx == 0:
images_equalize = image.asnumpy()
else:
images_equalize = np.append(images_equalize,
image.asnumpy(),
axis=0)
if plot:
visualize_list(images_original, images_equalize)
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))))
def test_imagefolder_exception():
logger.info("Test imagefolder exception")
def exception_func(item):
raise Exception("Error occur!")
def exception_func2(image, label):
raise Exception("Error occur!")
try:
data = ds.ImageFolderDataset(DATA_DIR)
data = data.map(operations=exception_func,
input_columns=["image"],
num_parallel_workers=1)
for _ in data.__iter__():
pass
assert False
except RuntimeError as e:
assert "map operation: [PyFunc] failed. The corresponding data files" in str(
e)
try:
data = ds.ImageFolderDataset(DATA_DIR)
data = data.map(operations=exception_func2,
input_columns=["image", "label"],
output_columns=["image", "label", "label1"],
column_order=["image", "label", "label1"],
num_parallel_workers=1)
for _ in data.__iter__():
pass
assert False
except RuntimeError as e:
assert "map operation: [PyFunc] failed. The corresponding data files" in str(
e)
try:
data = ds.ImageFolderDataset(DATA_DIR)
data = data.map(operations=vision.Decode(),
input_columns=["image"],
num_parallel_workers=1)
data = data.map(operations=exception_func,
input_columns=["image"],
num_parallel_workers=1)
for _ in data.__iter__():
pass
assert False
except RuntimeError as e:
assert "map operation: [PyFunc] failed. The corresponding data files" in str(
e)
