def test_random_crop_and_resize_06():
"""
Test RandomCropAndResize with c_transforms: invalid values for scale,
expected to raise ValueError
"""
logger.info("test_random_crop_and_resize_05_c")
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
try:
random_crop_and_resize_op = c_vision.RandomResizedCrop((256, 512),
scale="",
ratio=(1, 0.5))
data = data.map(input_columns=["image"], operations=decode_op)
data.map(input_columns=["image"], operations=random_crop_and_resize_op)
except TypeError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Argument scale with value \"\" is not of type (<class 'tuple'>,)" in str(
e)
try:
random_crop_and_resize_op = c_vision.RandomResizedCrop((256, 512),
scale=(1, "2"),
ratio=(1, 0.5))
data = data.map(input_columns=["image"], operations=decode_op)
data.map(input_columns=["image"], operations=random_crop_and_resize_op)
except TypeError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Argument scale[1] with value 2 is not of type (<class 'float'>, <class 'int'>)." in str(
e)
def test_random_crop_and_resize_05_c():
"""
Test RandomCropAndResize with c_transforms: invalid range of ratio (max<min),
expected to raise ValueError
"""
logger.info("test_random_crop_and_resize_05_c")
ds.config.set_seed(0)
ds.config.set_num_parallel_workers(1)
try:
# Generate dataset
data = 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), (1, 1), (1, 0.5))
# If input range of ratio is not in the order of (min, max), ValueError will be raised.
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"],
operations=random_crop_and_resize_op)
image_list = []
for item in data.create_dict_iterator():
image = item["image"]
image_list.append(image.shape)
except ValueError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Input range is not valid" in str(e)
def test_random_crop_and_resize_op_c(plot=False):
"""
Test RandomCropAndResize op in c transforms
"""
logger.info("test_random_crop_and_resize_op_c")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = c_vision.Decode()
# With these inputs we expect the code to crop the whole image
random_crop_and_resize_op = c_vision.RandomResizedCrop((256, 512), (2, 2), (1, 3))
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)
data2 = data2.map(input_columns=["image"], operations=decode_op)
num_iter = 0
crop_and_resize_images = []
original_images = []
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
crop_and_resize = item1["image"]
original = item2["image"]
# Note: resize the original image with the same size as the one applied RandomResizedCrop()
original = cv2.resize(original, (512, 256))
mse = diff_mse(crop_and_resize, original)
assert mse == 0
logger.info("random_crop_and_resize_op_{}, mse: {}".format(num_iter + 1, mse))
num_iter += 1
crop_and_resize_images.append(crop_and_resize)
original_images.append(original)
if plot:
visualize_list(original_images, crop_and_resize_images)
def test_random_crop_and_resize_comp(plot=False):
"""
Test RandomCropAndResize and compare between python and c image augmentation
"""
logger.info("test_random_crop_and_resize_comp")
# 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(512, (1, 1), (0.5, 0.5))
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(512, (1, 1), (0.5, 0.5)),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data2 = data2.map(input_columns=["image"], operations=transform())
image_c_cropped = []
image_py_cropped = []
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
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)
mse = diff_mse(c_image, py_image)
assert mse < 0.02 # rounding error
if plot:
visualize_list(image_c_cropped, image_py_cropped, visualize_mode=2)
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(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), max_attempts=1),
py_vision.ToTensor()
]
transform = py_vision.ComposeOp(transforms)
data2 = data2.map(input_columns=["image"], operations=transform())
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_random_crop_and_resize_op():
"""
Test RandomCropAndResize op
"""
logger.info("test_random_crop_and_resize_op")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = vision.Decode()
random_crop_and_resize_op = vision.RandomResizedCrop((256, 512), (1, 1), (0.5, 0.5))
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)
data2 = data2.map(input_columns=["image"], operations=decode_op)
num_iter = 0
for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
if num_iter > 0:
break
crop_and_resize = item1["image"]
original = item2["image"]
original = cv2.resize(original, (512, 256))
diff = crop_and_resize - original
mse = np.sum(np.power(diff, 2))
logger.info("random_crop_and_resize_op_{}, mse: {}".format(num_iter + 1, mse))
# Uncomment below line if you want to visualize images
# visualize(crop_and_resize, mse, original)
num_iter += 1
def test_random_crop_and_resize_05_c():
"""
Test RandomCropAndResize with c_transforms: invalid range of ratio (max<min),
expected to raise ValueError
"""
logger.info("test_random_crop_and_resize_05_c")
# Generate dataset
data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = c_vision.Decode()
try:
random_crop_and_resize_op = c_vision.RandomResizedCrop((256, 512), (1, 1), (1, 0.5))
# If input range of ratio is not in the order of (min, max), ValueError will be raised.
data = data.map(input_columns=["image"], operations=decode_op)
data = data.map(input_columns=["image"], operations=random_crop_and_resize_op)
except ValueError as e:
logger.info("Got an exception in DE: {}".format(str(e)))
assert "Input range is not valid" in str(e)
def test_random_crop_decode_resize_op(plot=False):
"""
Test RandomCropDecodeResize op
"""
logger.info("test_random_decode_resize_op")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = vision.Decode()
random_crop_decode_resize_op = vision.RandomCropDecodeResize(
(256, 512), (1, 1), (0.5, 0.5))
data1 = data1.map(input_columns=["image"],
operations=random_crop_decode_resize_op)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
random_crop_resize_op = vision.RandomResizedCrop((256, 512), (1, 1),
(0.5, 0.5))
data2 = data2.map(input_columns=["image"], operations=decode_op)
data2 = data2.map(input_columns=["image"],
operations=random_crop_resize_op)
num_iter = 0
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
if num_iter > 0:
break
image1 = item1["image"]
image2 = item2["image"]
mse = diff_mse(image1, image2)
assert mse == 0
logger.info("random_crop_decode_resize_op_{}, mse: {}".format(
num_iter + 1, mse))
if plot:
visualize_image(image1, image2, mse)
num_iter += 1
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")
ds.config.set_seed(0)
ds.config.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)
def create_dataset3(dataset_path, do_train, repeat_num=1, batch_size=32):
"""
create a train or eval imagenet2012 dataset for resnet101
Args:
dataset_path(string): the path of dataset.
do_train(bool): whether dataset is used for train or eval.
repeat_num(int): the repeat times of dataset. Default: 1
batch_size(int): the batch size of dataset. Default: 32
Returns:
dataset
"""
device_num = int(os.getenv("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
if device_num == 1:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path, num_parallel_workers=8, shuffle=True,
num_shards=device_num, shard_id=rank_id)
resize_height = 224
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
decode_op = C.Decode()
random_resize_crop_op = C.RandomResizedCrop(resize_height, (0.08, 1.0), (0.75, 1.33), max_attempts=100)
horizontal_flip_op = C.RandomHorizontalFlip(rank_id / (rank_id + 1))
resize_op_256 = C.Resize((256, 256))
center_crop = C.CenterCrop(224)
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize((0.475, 0.451, 0.392), (0.275, 0.267, 0.278))
changeswap_op = C.HWC2CHW()
if do_train:
trans = [decode_op,
random_resize_crop_op,
horizontal_flip_op,
rescale_op,
normalize_op,
changeswap_op]
else:
trans = [decode_op,
resize_op_256,
center_crop,
rescale_op,
normalize_op,
changeswap_op]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image", operations=trans, num_parallel_workers=8)
ds = ds.map(input_columns="label", operations=type_cast_op, num_parallel_workers=8)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32):
"""
create a train or eval dataset
Args:
dataset_path(string): the path of dataset.
do_train(bool): whether dataset is used for train or eval.
repeat_num(int): the repeat times of dataset. Default: 1
batch_size(int): the batch size of dataset. Default: 32
Returns:
dataset
"""
rank_size = int(os.getenv("RANK_SIZE"))
rank_id = int(os.getenv("RANK_ID"))
if rank_size == 1:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=16,
shuffle=True)
else:
ds = de.ImageFolderDatasetV2(dataset_path,
num_parallel_workers=16,
shuffle=True,
num_shards=rank_size,
shard_id=rank_id)
resize_height = config.image_height
resize_width = config.image_width
rescale = 1.0 / 255.0
shift = 0.0
buffer_size = 1000
# define map operations
decode_op = C.Decode()
resize_crop_op = C.RandomResizedCrop(resize_height,
scale=(0.08, 1.0),
ratio=(0.75, 1.333))
horizontal_flip_op = C.RandomHorizontalFlip(prob=0.5)
resize_op = C.Resize((256, 256))
center_crop = C.CenterCrop(resize_width)
rescale_op = C.Rescale(rescale, shift)
normalize_op = C.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
change_swap_op = C.HWC2CHW()
if do_train:
trans = [
decode_op, resize_crop_op, horizontal_flip_op, rescale_op,
normalize_op, change_swap_op
]
else:
trans = [
decode_op, resize_op, center_crop, rescale_op, normalize_op,
change_swap_op
]
type_cast_op = C2.TypeCast(mstype.int32)
ds = ds.map(input_columns="image", operations=trans)
ds = ds.map(input_columns="label", operations=type_cast_op)
# apply shuffle operations
ds = ds.shuffle(buffer_size=buffer_size)
# apply batch operations
ds = ds.batch(batch_size, drop_remainder=True)
# apply dataset repeat operation
ds = ds.repeat(repeat_num)
return ds
