def test_ten_crop_invalid_size_error_msg():
"""
Tests TenCrop error message when the size arg is not positive
"""
logger.info("test_ten_crop_invalid_size_error_msg")
with pytest.raises(ValueError) as info:
transforms = [
vision.Decode(),
vision.TenCrop(0),
lambda images: np.stack(
[vision.ToTensor()(image)
for image in images]) # 4D stack of 10 images
]
error_msg = "Input is not within the required range"
assert error_msg == str(info.value)
with pytest.raises(ValueError) as info:
transforms = [
vision.Decode(),
vision.TenCrop(-10),
lambda images: np.stack(
[vision.ToTensor()(image)
for image in images]) # 4D stack of 10 images
]
assert error_msg == str(info.value)
def util_test_ten_crop(crop_size, vertical_flip=False, plot=False):
"""
Utility function for testing TenCrop. Input arguments are given by other tests
"""
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms_1 = [
vision.Decode(),
vision.ToTensor(),
]
transform_1 = vision.ComposeOp(transforms_1)
data1 = data1.map(input_columns=["image"], operations=transform_1())
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms_2 = [
vision.Decode(),
vision.TenCrop(crop_size, use_vertical_flip=vertical_flip),
lambda images: np.stack([vision.ToTensor()(image)
for image in images]) # 4D stack of 10 images
]
transform_2 = vision.ComposeOp(transforms_2)
data2 = data2.map(input_columns=["image"], operations=transform_2())
num_iter = 0
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
num_iter += 1
image_1 = (item1["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
image_2 = item2["image"]
logger.info("shape of image_1: {}".format(image_1.shape))
logger.info("shape of image_2: {}".format(image_2.shape))
logger.info("dtype of image_1: {}".format(image_1.dtype))
logger.info("dtype of image_2: {}".format(image_2.dtype))
if plot:
visualize_list(np.array([image_1] * 10),
(image_2 * 255).astype(np.uint8).transpose(
0, 2, 3, 1))
# The output data should be of a 4D tensor shape, a stack of 10 images.
assert len(image_2.shape) == 4
assert image_2.shape[0] == 10
def test_ten_crop_list_size_error_msg():
"""
Tests TenCrop error message when the size arg has more than 2 elements
"""
logger.info("test_ten_crop_list_size_error_msg")
with pytest.raises(TypeError) as info:
transforms = [
vision.Decode(),
vision.TenCrop([200, 200, 200]),
lambda images: np.stack(
[vision.ToTensor()(image)
for image in images]) # 4D stack of 10 images
]
error_msg = "Size should be a single integer or a list/tuple (h, w) of length 2."
assert error_msg == str(info.value)
def test_ten_crop_wrong_img_error_msg():
"""
Tests TenCrop error message when the image is not in the correct format.
"""
logger.info("test_ten_crop_wrong_img_error_msg")
data = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms = [vision.Decode(), vision.TenCrop(200), vision.ToTensor()]
transform = vision.ComposeOp(transforms)
data = data.map(input_columns=["image"], operations=transform())
with pytest.raises(RuntimeError) as info:
data.create_tuple_iterator().get_next()
error_msg = "TypeError: img should be PIL Image or Numpy array. Got <class 'tuple'>"
# error msg comes from ToTensor()
assert error_msg in str(info.value)
def test_ten_crop_md5():
"""
Tests TenCrops for giving the same results in multiple runs.
Since TenCrop is a deterministic function, we expect it to return the same result for a specific input every time
"""
logger.info("test_ten_crop_md5")
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
transforms_2 = [
vision.Decode(),
vision.TenCrop((200, 100), use_vertical_flip=True),
lambda images: np.stack([vision.ToTensor()(image)
for image in images]) # 4D stack of 10 images
]
transform_2 = vision.ComposeOp(transforms_2)
data2 = data2.map(input_columns=["image"], operations=transform_2())
# Compare with expected md5 from images
filename = "ten_crop_01_result.npz"
save_and_check_md5(data2, filename, generate_golden=GENERATE_GOLDEN)
