def test_random_vertical_flip_with_bbox_op_rand_c(plot_vis=False):
"""
Prints images and bboxes side by side with and without RandomVerticalFlipWithBBox Op applied,
tests with MD5 check, expected to pass
"""
logger.info("test_random_vertical_flip_with_bbox_op_rand_c")
original_seed = config_get_set_seed(29847)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Load dataset
dataVoc1 = ds.VOCDataset(DATA_DIR_VOC,
task="Detection",
mode="train",
decode=True,
shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR_VOC,
task="Detection",
mode="train",
decode=True,
shuffle=False)
test_op = c_vision.RandomVerticalFlipWithBBox(0.8)
# map to apply ops
dataVoc2 = dataVoc2.map(input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
columns_order=["image", "bbox"],
operations=[test_op])
filename = "random_vertical_flip_with_bbox_01_c_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(dataVoc1.create_dict_iterator(),
dataVoc2.create_dict_iterator()):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_bounding_box_augment_with_rotation_op(plot_vis=False):
"""
Test BoundingBoxAugment op (passing rotation op as transform)
Prints images side by side with and without Aug applied + bboxes to compare and test
"""
logger.info("test_bounding_box_augment_with_rotation_op")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
dataVoc1 = ds.VOCDataset(DATA_DIR,
task="Detection",
mode="train",
decode=True,
shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR,
task="Detection",
mode="train",
decode=True,
shuffle=False)
# Ratio is set to 1 to apply rotation on all bounding boxes.
test_op = c_vision.BoundingBoxAugment(c_vision.RandomRotation(90), 1)
# map to apply ops
dataVoc2 = dataVoc2.map(input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
columns_order=["image", "bbox"],
operations=[test_op])
filename = "bounding_box_augment_rotation_c_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(dataVoc1.create_dict_iterator(),
dataVoc2.create_dict_iterator()):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def 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 = F.ComposeOp([lambda img: img.astype(np.uint8), F.ToPIL(),
p_op, np.array])
data1 = data1.map(input_columns=["image"], operations=[vision.Decode(), c_op])
data2 = data2.map(input_columns=["image"], operations=[vision.Decode()])
data2 = data2.map(input_columns=["image"], operations=transforms_random_color_py())
image_random_color_op = []
image = []
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
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_textline_dataset_shuffle_files4():
original_num_parallel_workers = config_get_set_num_parallel_workers(4)
original_seed = config_get_set_seed(135)
data = ds.TextFileDataset(DATA_ALL_FILE, shuffle=ds.Shuffle.FILES)
count = 0
line = [
"This is a text file.", "Another file.", "Be happy every day.",
"End of file.", "Good luck to everyone."
]
for i in data.create_dict_iterator(num_epochs=1, output_numpy=True):
strs = i["text"].item().decode("utf8")
assert strs == line[count]
count += 1
assert count == 5
# Restore configuration
ds.config.set_num_parallel_workers(original_num_parallel_workers)
ds.config.set_seed(original_seed)
def test_random_resize_with_bbox_op_voc_c(plot_vis=False):
"""
Prints images and bboxes side by side with and without RandomResizeWithBBox Op applied
testing with VOC dataset
"""
logger.info("test_random_resize_with_bbox_op_voc_c")
original_seed = config_get_set_seed(123)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Load dataset
dataVoc1 = ds.VOCDataset(DATA_DIR,
task="Detection",
usage="train",
shuffle=False,
decode=True)
dataVoc2 = ds.VOCDataset(DATA_DIR,
task="Detection",
usage="train",
shuffle=False,
decode=True)
test_op = c_vision.RandomResizeWithBBox(100)
# map to apply ops
dataVoc2 = dataVoc2.map(operations=[test_op],
input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
column_order=["image", "bbox"])
filename = "random_resize_with_bbox_op_01_c_voc_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(
dataVoc1.create_dict_iterator(num_epochs=1, output_numpy=True),
dataVoc2.create_dict_iterator(num_epochs=1, output_numpy=True)):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def skip_test_random_posterize_op_c(plot=False, run_golden=True):
"""
Test RandomPosterize in C transformations
"""
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(input_columns=["image"], operations=transforms1)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=[c_vision.Decode()])
image_posterize = []
image_original = []
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
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_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_grayscale_input_grayscale_images():
"""
Test RandomGrayscale Op: valid parameter with grayscale images as input, expect to pass
"""
logger.info("test_random_grayscale_input_grayscale_images")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
transforms1 = [
py_vision.Decode(),
py_vision.Grayscale(1),
# Note: If the input images is grayscale image with 1 channel.
py_vision.RandomGrayscale(0.5),
py_vision.ToTensor()
]
transform1 = py_vision.ComposeOp(transforms1)
data1 = data1.map(input_columns=["image"], operations=transform1())
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
transforms2 = [
py_vision.Decode(),
py_vision.ToTensor()
]
transform2 = py_vision.ComposeOp(transforms2)
data2 = data2.map(input_columns=["image"], operations=transform2())
image_gray = []
image = []
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
image1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image2 = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_gray.append(image1)
image.append(image2)
assert len(image1.shape) == 3
assert image1.shape[2] == 1
assert len(image2.shape) == 3
assert image2.shape[2] == 3
# Restore config
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_rotation_md5():
"""
Test RandomRotation with md5 check
"""
logger.info("Test RandomRotation with md5 check")
original_seed = config_get_set_seed(5)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Fisrt dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
resize_op = c_vision.RandomRotation((0, 90),
expand=True,
resample=Inter.BILINEAR,
center=(50, 50),
fill_value=150)
data1 = data1.map(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=resize_op, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, shuffle=False)
transform2 = mindspore.dataset.transforms.py_transforms.Compose([
py_vision.Decode(),
py_vision.RandomRotation((0, 90),
expand=True,
resample=Inter.BILINEAR,
center=(50, 50),
fill_value=150),
py_vision.ToTensor()
])
data2 = data2.map(operations=transform2, input_columns=["image"])
# Compare with expected md5 from images
filename1 = "random_rotation_01_c_result.npz"
save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
filename2 = "random_rotation_01_py_result.npz"
save_and_check_md5(data2, filename2, 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_crop_with_bbox_op2_c(plot_vis=False):
"""
Prints images and bboxes side by side with and without RandomCropWithBBox Op applied,
with md5 check, expected to pass
"""
logger.info("test_random_crop_with_bbox_op2_c")
original_seed = config_get_set_seed(593447)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Load dataset
dataVoc1 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
# define test OP with values to match existing Op unit - test
test_op = c_vision.RandomCropWithBBox(512, [200, 200, 200, 200], fill_value=(255, 255, 255))
dataVoc1 = dataVoc1.map(input_columns=["annotation"],
output_columns=["annotation"],
operations=fix_annotate)
dataVoc2 = dataVoc2.map(input_columns=["annotation"],
output_columns=["annotation"],
operations=fix_annotate)
# map to apply ops
dataVoc2 = dataVoc2.map(input_columns=["image", "annotation"],
output_columns=["image", "annotation"],
columns_order=["image", "annotation"],
operations=[test_op]) # Add column for "annotation"
filename = "random_crop_with_bbox_01_c_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(dataVoc1.create_dict_iterator(), dataVoc2.create_dict_iterator()):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_and_resize_02():
"""
Test RandomCropAndResize with md5 check:Image interpolation mode is Inter.NEAREST,
expected to pass
"""
logger.info("test_random_crop_and_resize_02")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
random_crop_and_resize_op = c_vision.RandomResizedCrop(
(256, 512), interpolation=mode.Inter.NEAREST)
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"],
operations=random_crop_and_resize_op)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [
py_vision.Decode(),
py_vision.RandomResizedCrop((256, 512),
interpolation=mode.Inter.NEAREST),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data2 = data2.map(input_columns=["image"], operations=transform())
filename1 = "random_crop_and_resize_02_c_result.npz"
filename2 = "random_crop_and_resize_02_py_result.npz"
save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_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_random_crop_decode_resize_md5():
"""
Test RandomCropDecodeResize with md5 check
"""
logger.info("Test RandomCropDecodeResize with md5 check")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
random_crop_decode_resize_op = vision.RandomCropDecodeResize((256, 512), (1, 1), (0.5, 0.5))
data = data.map(operations=random_crop_decode_resize_op, input_columns=["image"])
# Compare with expected md5 from images
filename = "random_crop_decode_resize_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_crop_and_resize_03():
"""
Test RandomCropAndResize with md5 check: max_attempts is 1, expected to pass
"""
logger.info("test_random_crop_and_resize_03")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
random_crop_and_resize_op = c_vision.RandomResizedCrop((256, 512),
max_attempts=1)
data1 = data1.map(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=random_crop_and_resize_op,
input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [
py_vision.Decode(),
py_vision.RandomResizedCrop((256, 512), max_attempts=1),
py_vision.ToTensor()
]
transform = mindspore.dataset.transforms.py_transforms.Compose(transforms)
data2 = data2.map(operations=transform, input_columns=["image"])
filename1 = "random_crop_and_resize_03_c_result.npz"
filename2 = "random_crop_and_resize_03_py_result.npz"
save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_serdes_cifar10_dataset(remove_json_files=True):
"""
Test serdes on Cifar10 dataset pipeline
"""
data_dir = "../data/dataset/testCifar10Data"
original_seed = config_get_set_seed(1)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
data1 = ds.Cifar10Dataset(data_dir, num_samples=10, shuffle=False)
data1 = data1.take(6)
trans = [
vision.RandomCrop((32, 32), (4, 4, 4, 4)),
vision.Resize((224, 224)),
vision.Rescale(1.0 / 255.0, 0.0),
vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
vision.HWC2CHW()
]
type_cast_op = c.TypeCast(mstype.int32)
data1 = data1.map(operations=type_cast_op, input_columns="label")
data1 = data1.map(operations=trans, input_columns="image")
data1 = data1.batch(3, drop_remainder=True)
data1 = data1.repeat(1)
data2 = util_check_serialize_deserialize_file(data1,
"cifar10_dataset_pipeline",
remove_json_files)
num_samples = 0
# Iterate and compare the data in the original pipeline (data1) against the deserialized pipeline (data2)
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)):
np.testing.assert_array_equal(item1['image'], item2['image'])
num_samples += 1
assert num_samples == 2
# Restore configuration num_parallel_workers
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_serdes_voc_dataset(remove_json_files=True):
"""
Test serdes on VOC dataset pipeline.
"""
data_dir = "../data/dataset/testVOC2012"
original_seed = config_get_set_seed(1)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
random_color_adjust_op = vision.RandomColorAdjust(brightness=(0.5, 0.5))
random_rotation_op = vision.RandomRotation((0, 90),
expand=True,
resample=Inter.BILINEAR,
center=(50, 50),
fill_value=150)
data1 = ds.VOCDataset(data_dir,
task="Detection",
usage="train",
decode=True)
data1 = data1.map(operations=random_color_adjust_op,
input_columns=["image"])
data1 = data1.map(operations=random_rotation_op, input_columns=["image"])
data1 = data1.skip(2)
data2 = util_check_serialize_deserialize_file(data1,
"voc_dataset_pipeline",
remove_json_files)
num_samples = 0
# Iterate and compare the data in the original pipeline (data1) against the deserialized pipeline (data2)
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)):
np.testing.assert_array_equal(item1['image'], item2['image'])
num_samples += 1
assert num_samples == 7
# Restore configuration num_parallel_workers
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_serdes_random_crop():
"""
Test serdes on RandomCrop pipeline.
"""
logger.info("test_random_crop")
DATA_DIR = [
"../data/dataset/test_tf_file_3_images/train-0000-of-0001.data"
]
SCHEMA_DIR = "../data/dataset/test_tf_file_3_images/datasetSchema.json"
original_seed = config_get_set_seed(1)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"])
decode_op = vision.Decode()
random_crop_op = vision.RandomCrop([512, 512], [200, 200, 200, 200])
data1 = data1.map(operations=decode_op, input_columns="image")
data1 = data1.map(operations=random_crop_op, input_columns="image")
# Serializing into python dictionary
ds1_dict = ds.serialize(data1)
# Serializing into json object
_ = json.dumps(ds1_dict, indent=2)
# Reconstruct dataset pipeline from its serialized form
data1_1 = ds.deserialize(input_dict=ds1_dict)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"])
data2 = data2.map(operations=decode_op, input_columns="image")
for item1, item1_1, item2 in zip(
data1.create_dict_iterator(num_epochs=1, output_numpy=True),
data1_1.create_dict_iterator(num_epochs=1, output_numpy=True),
data2.create_dict_iterator(num_epochs=1, output_numpy=True)):
np.testing.assert_array_equal(item1['image'], item1_1['image'])
_ = item2["image"]
# Restore configuration num_parallel_workers
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_vertical_valid_prob_c():
"""
Test RandomVerticalFlip op with c_transforms: valid non-default input, expect to pass
"""
logger.info("test_random_vertical_valid_prob_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = c_vision.Decode()
random_horizontal_op = c_vision.RandomVerticalFlip(0.8)
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_horizontal_op)
filename = "random_vertical_01_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_case_0():
"""
Test 1D Generator.
Test without explicit kwargs for input args.
"""
original_seed = config_get_set_seed(55)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# apply dataset qoperations
data1 = ds.GeneratorDataset(generator_1d, ["data"])
data1 = data1.shuffle(2)
data1 = data1.map((lambda x: x), ["data"])
data1 = data1.batch(2)
expected_data = np.array([[[1], [2]], [[3], [0]]])
for i, data_row in enumerate(
data1.create_tuple_iterator(output_numpy=True)):
np.testing.assert_array_equal(data_row[0], expected_data[i])
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers((original_num_parallel_workers))
def test_random_color_adjust_md5():
"""
Test RandomColorAdjust with md5 check
"""
logger.info("Test RandomColorAdjust with md5 check")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
random_adjust_op = c_vision.RandomColorAdjust(0.4, 0.4, 0.4, 0.1)
data1 = data1.map(operations=decode_op, input_columns=["image"])
data1 = data1.map(operations=random_adjust_op, input_columns=["image"])
# Second dataset
transforms = [
py_vision.Decode(),
py_vision.RandomColorAdjust(0.4, 0.4, 0.4, 0.1),
py_vision.ToTensor()
]
transform = mindspore.dataset.transforms.py_transforms.Compose(transforms)
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(operations=transform, input_columns=["image"])
# Compare with expected md5 from images
filename = "random_color_adjust_01_c_result.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
filename = "random_color_adjust_01_py_result.npz"
save_and_check_md5(data2, 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_crop_03_c():
"""
Test RandomCrop op with c_transforms: input image size == crop size, expected to pass
"""
logger.info("test_random_crop_03_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: The size of the image is 4032*2268
random_crop_op = c_vision.RandomCrop([2268, 4032])
decode_op = c_vision.Decode()
data = data.map(operations=decode_op, input_columns=["image"])
data = data.map(operations=random_crop_op, input_columns=["image"])
filename = "random_crop_03_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_02_c():
"""
Test RandomCrop op with c_transforms: size is a list/tuple with length 2, expected to pass
"""
logger.info("test_random_crop_02_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: If size is a sequence of length 2, it should be (height, width).
random_crop_op = c_vision.RandomCrop([512, 375])
decode_op = c_vision.Decode()
data = data.map(operations=decode_op, input_columns=["image"])
data = data.map(operations=random_crop_op, input_columns=["image"])
filename = "random_crop_02_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_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.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(operations=transforms, input_columns=["image"])
# 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_random_crop_01_c():
"""
Test RandomCrop op with c_transforms: size is a single integer, expected to pass
"""
logger.info("test_random_crop_01_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: If size is an int, a square crop of size (size, size) is returned.
random_crop_op = c_vision.RandomCrop(512)
decode_op = c_vision.Decode()
data = data.map(operations=decode_op, input_columns=["image"])
data = data.map(operations=random_crop_op, input_columns=["image"])
filename = "random_crop_01_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_solarize_md5():
"""
Test RandomSolarize
"""
logger.info("Test RandomSolarize")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = vision.Decode()
random_solarize_op = vision.RandomSolarize((10, 150))
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"], operations=random_solarize_op)
# Compare with expected md5 from images
filename = "random_solarize_01_result.npz"
save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_mixup_batch_md5():
"""
Test MixUpBatch with MD5:
"""
logger.info("test_mixup_batch_md5")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# MixUp Images
data = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False)
one_hot_op = data_trans.OneHot(num_classes=10)
data = data.map(input_columns=["label"], operations=one_hot_op)
mixup_batch_op = vision.MixUpBatch()
data = data.batch(5, drop_remainder=True)
data = data.map(input_columns=["image", "label"], operations=mixup_batch_op)
filename = "mixup_batch_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_sharpness_py_md5():
"""
Test RandomSharpness python op with md5 comparison
"""
logger.info("Test RandomSharpness python op 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((20.0, 25.0)), F.ToTensor()]
transform = mindspore.dataset.transforms.py_transforms.Compose(transforms)
# Generate dataset
data = de.ImageFolderDataset(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(operations=transform, input_columns=["image"])
# check results with md5 comparison
filename = "random_sharpness_py_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_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 test_cutmix_batch_nhwc_md5():
"""
Test CutMixBatch on a batch of HWC images with MD5:
"""
logger.info("test_cutmix_batch_nhwc_md5")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# CutMixBatch Images
data = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False)
one_hot_op = data_trans.OneHot(num_classes=10)
data = data.map(operations=one_hot_op, input_columns=["label"])
cutmix_batch_op = vision.CutMixBatch(mode.ImageBatchFormat.NHWC)
data = data.batch(5, drop_remainder=True)
data = data.map(operations=cutmix_batch_op, input_columns=["image", "label"])
filename = "cutmix_batch_c_nhwc_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_08_c():
"""
Test RandomCrop op with c_transforms: padding_mode is Border.EDGE,
expected to pass
"""
logger.info("test_random_crop_08_c")
original_seed = config_get_set_seed(0)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
# Note: The padding_mode is Border.EDGE.
random_crop_op = c_vision.RandomCrop(512, [200, 200, 200, 200], padding_mode=mode.Border.EDGE)
decode_op = c_vision.Decode()
data = data.map(operations=decode_op, input_columns=["image"])
data = data.map(operations=random_crop_op, input_columns=["image"])
filename = "random_crop_08_c_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_bounding_box_augment_valid_ratio_c(plot_vis=False):
"""
Test BoundingBoxAugment op (testing with valid ratio, less than 1.
Prints images side by side with and without Aug applied + bboxes to compare and test
"""
logger.info("test_bounding_box_augment_valid_ratio_c")
original_seed = config_get_set_seed(1)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
dataVoc1 = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False, decode=True)
dataVoc2 = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False, decode=True)
test_op = c_vision.BoundingBoxAugment(c_vision.RandomHorizontalFlip(1), 0.9)
# map to apply ops
dataVoc2 = dataVoc2.map(operations=[test_op], input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
column_order=["image", "bbox"]) # Add column for "bbox"
filename = "bounding_box_augment_valid_ratio_c_result.npz"
save_and_check_md5(dataVoc2, filename, generate_golden=GENERATE_GOLDEN)
unaugSamp, augSamp = [], []
for unAug, Aug in zip(dataVoc1.create_dict_iterator(num_epochs=1, output_numpy=True),
dataVoc2.create_dict_iterator(num_epochs=1, output_numpy=True)):
unaugSamp.append(unAug)
augSamp.append(Aug)
if plot_vis:
visualize_with_bounding_boxes(unaugSamp, augSamp)
# Restore config setting
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)