def test_random_affine_op_c(plot=False):
"""
Test RandomAffine in C transformations
"""
logger.info("test_random_affine_op_c")
# define map operations
transforms1 = [
c_vision.Decode(),
c_vision.RandomAffine(degrees=0, translate=(0.5, 0.5, 0, 0))
]
transforms2 = [
c_vision.Decode()
]
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
data1 = data1.map(operations=transforms1, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
data2 = data2.map(operations=transforms2, input_columns=["image"])
image_affine = []
image_original = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image1 = item1["image"]
image2 = item2["image"]
image_affine.append(image1)
image_original.append(image2)
if plot:
visualize_list(image_original, image_affine)
def test_random_posterize_op_fixed_point_c(plot=False, run_golden=True):
"""
Test RandomPosterize in C transformations with fixed point
"""
logger.info("test_random_posterize_op_c")
# define map operations
transforms1 = [
c_vision.Decode(),
c_vision.RandomPosterize(1)
]
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
data1 = data1.map(operations=transforms1, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
data2 = data2.map(operations=[c_vision.Decode()], input_columns=["image"])
image_posterize = []
image_original = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image1 = item1["image"]
image2 = item2["image"]
image_posterize.append(image1)
image_original.append(image2)
if run_golden:
# check results with md5 comparison
filename = "random_posterize_fixed_point_01_result_c.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(image_original, image_posterize)
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_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_eager_exceptions():
try:
img = "../data/dataset/apple.jpg"
img = C.Decode()(img)
assert False
except TypeError as e:
assert "Input should be a 1-D NumPy with integer type" in str(e)
try:
img = np.array(["a", "b", "c"])
img = C.Decode()(img)
assert False
except TypeError as e:
assert "Input should be a 1-D NumPy with integer type" in str(e)
try:
img = cv2.imread("../data/dataset/apple.jpg")
img = C.Resize(size=(-32, 32))(img)
assert False
except ValueError as e:
assert "not within the required interval" in str(e)
try:
img = "../data/dataset/apple.jpg"
img = C.Pad(padding=4)(img)
assert False
except TypeError as e:
assert "Input should be NumPy or PIL image" in str(e)
def test_pipeline():
"""
Test that our configuration pipeline works when we set parameters at different locations in dataset code
"""
# Save original configuration values
num_parallel_workers_original = ds.config.get_num_parallel_workers()
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, shuffle=False)
data1 = data1.map(operations=[c_vision.Decode(True)], input_columns=["image"])
ds.serialize(data1, "testpipeline.json")
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, num_parallel_workers=num_parallel_workers_original,
shuffle=False)
data2 = data2.map(operations=[c_vision.Decode(True)], input_columns=["image"])
ds.serialize(data2, "testpipeline2.json")
# check that the generated output is different
assert filecmp.cmp('testpipeline.json', 'testpipeline2.json')
# this test passes currently because our num_parallel_workers don't get updated.
# remove generated jason files
file_list = glob.glob('*.json')
for f in file_list:
try:
os.remove(f)
except IOError:
logger.info("Error while deleting: {}".format(f))
# Restore original configuration values
ds.config.set_num_parallel_workers(num_parallel_workers_original)
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 test_compare_random_color_op(degrees=None, plot=False):
"""
Compare Random Color op in Python and Cpp
"""
logger.info("test_random_color_op")
original_seed = config_get_set_seed(5)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Decode with rgb format set to True
data1 = ds.TFRecordDataset(C_DATA_DIR,
C_SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = ds.TFRecordDataset(C_DATA_DIR,
C_SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
if degrees is None:
c_op = vision.RandomColor()
p_op = F.RandomColor()
else:
c_op = vision.RandomColor(degrees)
p_op = F.RandomColor(degrees)
transforms_random_color_py = mindspore.dataset.transforms.py_transforms.Compose(
[lambda img: img.astype(np.uint8),
F.ToPIL(), p_op, np.array])
data1 = data1.map(operations=[vision.Decode(), c_op],
input_columns=["image"])
data2 = data2.map(operations=[vision.Decode()], input_columns=["image"])
data2 = data2.map(operations=transforms_random_color_py,
input_columns=["image"])
image_random_color_op = []
image = []
for item1, item2 in zip(
data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
actual = item1["image"]
expected = item2["image"]
image_random_color_op.append(actual)
image.append(expected)
assert actual.shape == expected.shape
mse = diff_mse(actual, expected)
logger.info("MSE= {}".format(str(np.mean(mse))))
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
if plot:
visualize_list(image, image_random_color_op)
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_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.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 = de.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 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_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_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_cutmix_batch_success4(plot=False):
"""
Test CutMixBatch on a dataset where OneHot returns a 2D vector
"""
logger.info("test_cutmix_batch_success4")
ds_original = ds.CelebADataset(DATA_DIR3, 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(2, 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.CelebADataset(dataset_dir=DATA_DIR3, 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=100)
data1 = data1.map(operations=one_hot_op, input_columns=["attr"])
cutmix_batch_op = vision.CutMixBatch(mode.ImageBatchFormat.NHWC, 0.5, 0.9)
data1 = data1.batch(2, drop_remainder=True)
data1 = data1.map(operations=cutmix_batch_op,
input_columns=["image", "attr"])
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_random_posterize_op_c(plot=False, run_golden=False):
"""
Test RandomPosterize in C transformations (uses assertion on mse as using md5 could have jpeg decoding
inconsistencies)
"""
logger.info("test_random_posterize_op_c")
original_seed = config_get_set_seed(55)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms1 = [c_vision.Decode(), c_vision.RandomPosterize((1, 8))]
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data1 = data1.map(operations=transforms1, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(operations=[c_vision.Decode()], input_columns=["image"])
image_posterize = []
image_original = []
for item1, item2 in zip(
data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image1 = item1["image"]
image2 = item2["image"]
image_posterize.append(image1)
image_original.append(image2)
# check mse as md5 can be inconsistent.
# mse = 2.9668956 is calculated from
# a thousand runs of diff_mse(np.array(image_original), np.array(image_posterize)) that all produced the same mse.
# allow for an error of 0.0000005
assert abs(2.9668956 - diff_mse(np.array(image_original),
np.array(image_posterize))) <= 0.0000005
if run_golden:
# check results with md5 comparison
filename = "random_posterize_01_result_c.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(image_original, image_posterize)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_color_c(degrees=(0.1, 1.9), plot=False, run_golden=True):
"""
Test Cpp RandomColor
"""
logger.info("test_random_color_op")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Decode with rgb format set to True
data1 = ds.TFRecordDataset(C_DATA_DIR,
C_SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = ds.TFRecordDataset(C_DATA_DIR,
C_SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# Serialize and Load dataset requires using vision.Decode instead of vision.Decode().
if degrees is None:
c_op = vision.RandomColor()
else:
c_op = vision.RandomColor(degrees)
data1 = data1.map(operations=[vision.Decode()], input_columns=["image"])
data2 = data2.map(operations=[vision.Decode(), c_op],
input_columns=["image"])
image_random_color_op = []
image = []
for item1, item2 in zip(
data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
actual = item1["image"]
expected = item2["image"]
image.append(actual)
image_random_color_op.append(expected)
if run_golden:
# Compare with expected md5 from images
filename = "random_color_op_02_result.npz"
save_and_check_md5(data2, filename, generate_golden=GENERATE_GOLDEN)
if plot:
visualize_list(image, image_random_color_op)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers((original_num_parallel_workers))
def test_mixup_batch_success4(plot=False):
"""
Test MixUpBatch op on a dataset where OneHot returns a 2D vector.
Alpha parameter will be selected by default in this case
"""
logger.info("test_mixup_batch_success4")
# Original Images
ds_original = ds.CelebADataset(DATA_DIR3, shuffle=False)
decode_op = vision.Decode()
ds_original = ds_original.map(operations=[decode_op],
input_columns=["image"])
ds_original = ds_original.batch(2, 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.CelebADataset(DATA_DIR3, shuffle=False)
decode_op = vision.Decode()
data1 = data1.map(operations=[decode_op], input_columns=["image"])
one_hot_op = data_trans.OneHot(num_classes=100)
data1 = data1.map(operations=one_hot_op, input_columns=["attr"])
mixup_batch_op = vision.MixUpBatch()
data1 = data1.batch(2, drop_remainder=True)
data1 = data1.map(operations=mixup_batch_op,
input_columns=["image", "attr"])
images_mixup = np.array([])
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_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_c_py_compose_vision_module(plot=False, run_golden=True):
"""
Test combining Python and C++ vision transforms
"""
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
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)
test_config(op_list=[c_vision.Decode(),
py_vision.ToPIL(),
py_vision.Resize((224, 224)),
np.array],
plot=plot, file_name="compose_c_py_1.npz")
test_config(op_list=[c_vision.Decode(),
c_vision.Resize((224, 244)),
py_vision.ToPIL(),
np.array,
c_vision.Resize((24, 24))],
plot=plot, file_name="compose_c_py_2.npz")
test_config(op_list=[py_vision.Decode(),
py_vision.Resize((224, 224)),
np.array,
c_vision.RandomColor()],
plot=plot, file_name="compose_c_py_3.npz")
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers((original_num_parallel_workers))
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_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(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=center_crop_op, input_columns=["image"])
# 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 = mindspore.dataset.transforms.py_transforms.Compose(transforms)
data2 = data2.map(operations=transform, input_columns=["image"])
image_c_cropped = []
image_py_cropped = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
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_center_crop_op(height=375, width=375, plot=False):
"""
Test CenterCrop
"""
logger.info("Test CenterCrop")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"])
decode_op = vision.Decode()
# 3 images [375, 500] [600, 500] [512, 512]
center_crop_op = vision.CenterCrop([height, width])
data1 = data1.map(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=center_crop_op, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"])
data2 = data2.map(operations=decode_op, input_columns=["image"])
image_cropped = []
image = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image_cropped.append(item1["image"].copy())
image.append(item2["image"].copy())
if plot:
visualize_list(image, image_cropped)
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(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=random_crop_op, input_columns=["image"])
# 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 = mindspore.dataset.transforms.py_transforms.Compose(transforms)
data2 = data2.map(operations=transform, input_columns=["image"])
image_c_cropped = []
image_py_cropped = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
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 util_test_normalize(mean, std, op_type):
"""
Utility function for testing Normalize. Input arguments are given by other tests
"""
if op_type == "cpp":
# define map operations
decode_op = c_vision.Decode()
normalize_op = c_vision.Normalize(mean, std)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data = data.map(operations=decode_op, input_columns=["image"])
data = data.map(operations=normalize_op, input_columns=["image"])
elif op_type == "python":
# define map operations
transforms = [
py_vision.Decode(),
py_vision.ToTensor(),
py_vision.Normalize(mean, std)
]
transform = mindspore.dataset.transforms.py_transforms.Compose(
transforms)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data = data.map(operations=transform, input_columns=["image"])
else:
raise ValueError("Wrong parameter value")
return data
def test_decode_normalize_op():
"""
Test Decode op followed by Normalize op
"""
logger.info("Test [Decode, Normalize] in one Map")
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image", "label"],
num_parallel_workers=1,
shuffle=False)
# define map operations
decode_op = c_vision.Decode()
normalize_op = c_vision.Normalize([121.0, 115.0, 100.0],
[70.0, 68.0, 71.0])
# apply map operations on images
data1 = data1.map(operations=[decode_op, normalize_op],
input_columns=["image"])
num_iter = 0
for item in data1.create_dict_iterator(num_epochs=1):
logger.info("Looping inside iterator {}".format(num_iter))
_ = item["image"]
num_iter += 1
def test_serdes_uniform_augment(remove_json_files=True):
"""
Test serdes on uniform augment.
"""
data_dir = "../data/dataset/testPK/data"
data = ds.ImageFolderDataset(dataset_dir=data_dir, shuffle=False)
ds.config.set_seed(1)
transforms_ua = [
vision.RandomHorizontalFlip(),
vision.RandomVerticalFlip(),
vision.RandomColor(),
vision.RandomSharpness(),
vision.Invert(),
vision.AutoContrast(),
vision.Equalize()
]
transforms_all = [
vision.Decode(),
vision.Resize(size=[224, 224]),
vision.UniformAugment(transforms=transforms_ua, num_ops=5)
]
data = data.map(operations=transforms_all,
input_columns="image",
num_parallel_workers=1)
util_check_serialize_deserialize_file(data, "uniform_augment_pipeline",
remove_json_files)
def test_resize_md5_parameters(test_name, size, filename, seed, plot):
"""
Test Resize with md5 check
"""
logger.info("Test Resize with md5 check: {0}".format(test_name))
original_seed = config_get_set_seed(seed)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = vision.Decode()
resize_op = vision.Resize(size)
data1 = data1.map(operations=decode_op, input_columns=["image"])
data2 = data1.map(operations=resize_op, input_columns=["image"])
image_original = []
image_resized = []
# Compare with expected md5 from images
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image_1 = item1["image"]
image_2 = item2["image"]
image_original.append(image_1)
image_resized.append(image_2)
if plot:
visualize_list(image_original, image_resized)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_resize_op_parameters(test_name, size, plot):
"""
Test resize_op
"""
logger.info("Test resize: {0}".format(test_name))
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# define map operations
decode_op = vision.Decode()
resize_op = vision.Resize(size)
# apply map operations on images
data1 = data1.map(operations=decode_op, input_columns=["image"])
data2 = data1.map(operations=resize_op, input_columns=["image"])
image_original = []
image_resized = []
for item1, item2 in zip(data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image_1 = item1["image"]
image_2 = item2["image"]
image_original.append(image_1)
image_resized.append(image_2)
if plot:
visualize_list(image_original, image_resized)
def test_pipeline_get_dataset_size():
dataset = ds.TFRecordDataset(IMAGENET_TFFILE_DIR,
SCHEMA_FILE,
columns_list=["image"],
shuffle=False)
assert dataset.get_dataset_size() == 12
dataset = dataset.shuffle(buffer_size=3)
assert dataset.get_dataset_size() == 12
decode_op = vision.Decode()
resize_op = vision.RandomResize(10)
dataset = dataset.map([decode_op, resize_op], input_columns=["image"])
assert dataset.get_dataset_size() == 12
dataset = dataset.batch(batch_size=3)
assert dataset.get_dataset_size() == 4
dataset = dataset.repeat(count=2)
assert dataset.get_dataset_size() == 8
tf1 = ds.TFRecordDataset(IMAGENET_TFFILE_DIR, shuffle=True)
tf2 = ds.TFRecordDataset(IMAGENET_TFFILE_DIR, shuffle=True)
assert tf2.concat(tf1).get_dataset_size() == 24
def test_rescale_op(plot=False):
"""
Test rescale
"""
logger.info("Test rescale")
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
# define map operations
decode_op = vision.Decode()
rescale_op = vision.Rescale(1.0 / 255.0, -1.0)
# apply map operations on images
data1 = data1.map(operations=decode_op, input_columns=["image"])
data2 = data1.map(operations=rescale_op, input_columns=["image"])
num_iter = 0
for item1, item2 in zip(
data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
image_original = item1["image"]
image_de_rescaled = item2["image"]
image_np_rescaled = get_rescaled(num_iter)
mse = diff_mse(image_de_rescaled, image_np_rescaled)
assert mse < 0.001 # rounding error
logger.info("image_{}, mse: {}".format(num_iter + 1, mse))
num_iter += 1
if plot:
visualize_image(image_original, image_de_rescaled, mse,
image_np_rescaled)
