def test_cutmix_batch_nchw_md5():
"""
Test CutMixBatch on a batch of CHW images with MD5:
"""
logger.info("test_cutmix_batch_nchw_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)
hwc2chw_op = vision.HWC2CHW()
data = data.map(input_columns=["image"], operations=hwc2chw_op)
one_hot_op = data_trans.OneHot(num_classes=10)
data = data.map(input_columns=["label"], operations=one_hot_op)
cutmix_batch_op = vision.CutMixBatch(mode.ImageBatchFormat.NCHW)
data = data.batch(5, drop_remainder=True)
data = data.map(input_columns=["image", "label"],
operations=cutmix_batch_op)
filename = "cutmix_batch_c_nchw_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_horizontal_valid_prob_py():
"""
Test RandomHorizontalFlip op with py_transforms: valid non-default input, expect to pass
"""
logger.info("test_random_horizontal_valid_prob_py")
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)
transforms = [
py_vision.Decode(),
py_vision.RandomHorizontalFlip(0.8),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
filename = "random_horizontal_01_py_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_unmappable_randomize_repeatable():
original_num_parallel_workers = config_get_set_num_parallel_workers(4)
# the labels outputted by ShuffleOp for seed 53 is [0, 2, 1, 4, 3]
ds.config.set_seed(53)
d = ds.TextFileDataset(text_file_dataset_path, shuffle=False)
s1, s2 = d.split([0.8, 0.2])
num_epochs = 5
s1 = s1.repeat(num_epochs)
s2 = s2.repeat(num_epochs)
s1_output = []
for item in s1.create_dict_iterator():
s1_output.append(item["text"].item().decode("utf8"))
s2_output = []
for item in s2.create_dict_iterator():
s2_output.append(item["text"].item().decode("utf8"))
# note no overlap
assert s1_output == [
text_file_data[0], text_file_data[2], text_file_data[1],
text_file_data[4]
] * num_epochs
assert s2_output == [text_file_data[3]] * num_epochs
# Restore configuration num_parallel_workers
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_erasing_md5():
"""
Test RandomErasing with md5 check
"""
logger.info("Test RandomErasing with md5 check")
original_seed = config_get_set_seed(5)
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)
transforms_1 = [
vision.Decode(),
vision.ToTensor(),
vision.RandomErasing(value='random')
]
transform_1 = vision.ComposeOp(transforms_1)
data = data.map(input_columns=["image"], operations=transform_1())
# Compare with expected md5 from images
filename = "random_erasing_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_cut_out_md5():
"""
Test Cutout with md5 check
"""
logger.info("test_cut_out_md5")
original_seed = config_get_set_seed(2)
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.Decode()
cut_out_op = c.CutOut(100)
data1 = data1.map(input_columns=["image"], operations=decode_op)
data1 = data1.map(input_columns=["image"], operations=cut_out_op)
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [f.Decode(), f.ToTensor(), f.Cutout(100)]
transform = f.ComposeOp(transforms)
data2 = data2.map(input_columns=["image"], operations=transform())
# Compare with expected md5 from images
filename1 = "cut_out_01_c_result.npz"
save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
filename2 = "cut_out_01_py_result.npz"
save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN)
# Restore config
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", mode="train", decode=True, shuffle=False)
dataVoc2 = ds.VOCDataset(DATA_DIR, task="Detection", mode="train", decode=True, shuffle=False)
test_op = c_vision.BoundingBoxAugment(c_vision.RandomHorizontalFlip(1), 0.9)
# 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 = "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(), 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_07_c():
"""
Test RandomCrop op with c_transforms:
padding_mode is Border.CONSTANT and fill_value is 255 (White),
expected to pass
"""
logger.info("test_random_crop_07_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 default as Border.CONSTANT and set filling color to be white.
random_crop_op = c_vision.RandomCrop(512, [200, 200, 200, 200],
fill_value=(255, 255, 255))
decode_op = c_vision.Decode()
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
filename = "random_crop_07_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.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"], operations=transforms)
# check results with md5 comparison
filename = "random_sharpness_cpp_01_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_02_py():
"""
Test RandomCrop op with py_transforms: size is a list/tuple with length 2, expected to pass
"""
logger.info("test_random_crop_02_py")
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).
transforms = [
py_vision.Decode(),
py_vision.RandomCrop([512, 375]),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
filename = "random_crop_02_py_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_05_py():
"""
Test RandomCrop op with py_transforms:
input image size < crop size but pad_if_needed is enabled,
expected to pass
"""
logger.info("test_random_crop_05_py")
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
transforms = [
py_vision.Decode(),
py_vision.RandomCrop([2268, 4033], [200, 200, 200, 200],
pad_if_needed=True),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
filename = "random_crop_05_py_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_py():
"""
Test RandomCrop op with py_transforms: padding_mode is Border.EDGE,
expected to pass
"""
logger.info("test_random_crop_08_py")
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.
transforms = [
py_vision.Decode(),
py_vision.RandomCrop(512, [200, 200, 200, 200],
padding_mode=mode.Border.EDGE),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
filename = "random_crop_08_py_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_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_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_affine_c_md5():
"""
Test RandomAffine C Op with md5 comparison
"""
logger.info("test_random_affine_c_md5")
original_seed = config_get_set_seed(1)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms = [
c_vision.Decode(),
c_vision.RandomAffine(degrees=(-5, 15),
translate=(0.1, 0.3),
scale=(0.9, 1.1),
shear=(-10, 10, -5, 5))
]
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data = data.map(input_columns=["image"], operations=transforms)
# check results with md5 comparison
filename = "random_affine_01_c_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_grayscale_md5_no_param():
"""
Test RandomGrayscale with md5 comparison: no parameter given, expect to pass
"""
logger.info("test_random_grayscale_md5_no_param")
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)
transforms = [
py_vision.Decode(),
py_vision.RandomGrayscale(),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
# Check output images with md5 comparison
filename = "random_grayscale_02_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore config
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop():
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_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(input_columns="image", operations=decode_op)
data1 = data1.map(input_columns="image", operations=random_crop_op)
# 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(input_columns="image", operations=decode_op)
for item1, item1_1, item2 in zip(data1.create_dict_iterator(),
data1_1.create_dict_iterator(),
data2.create_dict_iterator()):
assert np.array_equal(item1['image'], item1_1['image'])
_ = item2["image"]
# Restore configuration num_parallel_workers
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_bounding_box_augment_valid_edge_c(plot_vis=False):
"""
Test BoundingBoxAugment op (testing with valid edge case, box covering full image).
Prints images side by side with and without Aug applied + bboxes to compare and test
"""
logger.info("test_bounding_box_augment_valid_edge_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), 1)
# map to apply ops
# Add column for "bbox"
dataVoc1 = dataVoc1.map(
operations=lambda img, bbox:
(img, np.array([[0, 0, img.shape[1], img.shape[0], 0, 0, 0]]).astype(
np.float32)),
input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
column_order=["image", "bbox"])
dataVoc2 = dataVoc2.map(
operations=lambda img, bbox:
(img, np.array([[0, 0, img.shape[1], img.shape[0], 0, 0, 0]]).astype(
np.float32)),
input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
column_order=["image", "bbox"])
dataVoc2 = dataVoc2.map(operations=[test_op],
input_columns=["image", "bbox"],
output_columns=["image", "bbox"],
column_order=["image", "bbox"])
filename = "bounding_box_augment_valid_edge_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)
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 skip_test_random_perspective_md5():
"""
Test RandomPerspective with md5 comparison
"""
logger.info("test_random_perspective_md5")
original_seed = config_get_set_seed(5)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms = [
py_vision.Decode(),
py_vision.RandomPerspective(distortion_scale=0.3, prob=0.7,
interpolation=Inter.BILINEAR),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
data = data.map(input_columns=["image"], operations=transform())
# check results with md5 comparison
filename = "random_perspective_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_apply_exception_random_crop_badinput():
"""
Test RandomApply: test invalid input for one of the transform functions,
expected to raise error
"""
logger.info("test_random_apply_exception_random_crop_badinput")
original_seed = config_get_set_seed(200)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms_list = [
py_vision.Resize([32, 32]),
py_vision.RandomCrop(100), # crop size > image size
py_vision.RandomRotation(30)
]
transforms = [
py_vision.Decode(),
py_transforms.RandomApply(transforms_list, prob=0.6),
py_vision.ToTensor()
]
transform = 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"])
try:
_ = data.create_dict_iterator(num_epochs=1).get_next()
except RuntimeError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Crop size" in str(e)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_random_crop_01_py():
"""
Test RandomCrop op with py_transforms: size is a single integer, expected to pass
"""
logger.info("test_random_crop_01_py")
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.
transforms = [
py_vision.Decode(),
py_vision.RandomCrop(512),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
filename = "random_crop_01_py_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_apply_md5():
"""
Test RandomApply op with md5 check
"""
logger.info("test_random_apply_md5")
original_seed = config_get_set_seed(10)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms_list = [py_vision.CenterCrop(64), py_vision.RandomRotation(30)]
transforms = [
py_vision.Decode(),
# Note: using default value "prob=0.5"
py_transforms.RandomApply(transforms_list),
py_vision.ToTensor()
]
transform = 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"])
# check results with md5 comparison
filename = "random_apply_01_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers((original_num_parallel_workers))
def test_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(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_op)
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_sharpness_md5():
"""
Test RandomSharpness with md5 comparison
"""
logger.info("Test RandomSharpness with md5 comparison")
original_seed = config_get_set_seed(5)
original_num_parallel_workers = config_get_set_num_parallel_workers(1)
# define map operations
transforms = [
F.Decode(),
F.RandomSharpness((0.1, 1.9)),
F.ToTensor()
]
transform = F.ComposeOp(transforms)
# Generate dataset
data = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False)
data = data.map(input_columns=["image"], operations=transform())
# check results with md5 comparison
filename = "random_sharpness_01_result.npz"
save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
# Restore configuration
ds.config.set_seed(original_seed)
ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_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_random_horizontal_bbox_with_bbox_valid_rand_c(plot_vis=False):
"""
Uses a valid non-default input, expect to pass
Prints images side by side with and without Aug applied + bboxes to
compare and test
"""
logger.info("test_random_horizontal_bbox_valid_rand_c")
original_seed = config_get_set_seed(1)
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)
test_op = c_vision.RandomHorizontalFlipWithBBox(0.6)
# maps to fix annotations to minddata standard
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])
filename = "random_horizontal_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_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_resize_with_bbox_op_rand_c(plot_vis=False):
"""
Prints images and bboxes side by side with and without RandomResizeWithBBox Op applied,
tests with MD5 check, expected to pass
"""
logger.info("test_random_resize_with_bbox_rand_c")
original_seed = config_get_set_seed(1)
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)
test_op = c_vision.RandomResizeWithBBox(200)
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])
filename = "random_resize_with_bbox_op_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_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 = mindspore.dataset.transforms.py_transforms.Compose(
transforms1)
data1 = data1.map(operations=transform1, input_columns=["image"])
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms2 = [py_vision.Decode(), py_vision.ToTensor()]
transform2 = mindspore.dataset.transforms.py_transforms.Compose(
transforms2)
data2 = data2.map(operations=transform2, input_columns=["image"])
image_gray = []
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)):
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)
