def test_pad_md5():
"""
Test Pad with md5 check
"""
logger.info("test_pad_md5")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
decode_op = c_vision.Decode()
pad_op = c_vision.Pad(150)
ctrans = [decode_op,
pad_op,
]
data1 = data1.map(input_columns=["image"], operations=ctrans)
# Second dataset
data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
pytrans = [
py_vision.Decode(),
py_vision.Pad(150),
py_vision.ToTensor(),
]
transform = py_vision.ComposeOp(pytrans)
data2 = data2.map(input_columns=["image"], operations=transform())
# Compare with expected md5 from images
filename1 = "pad_01_c_result.npz"
save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN)
filename2 = "pad_01_py_result.npz"
save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN)
def test_pad_grayscale():
"""
Tests that the pad works for grayscale images
"""
def channel_swap(image):
"""
Py func hack for our pytransforms to work with c transforms
"""
return (image.transpose(1, 2, 0) * 255).astype(np.uint8)
transforms = [
py_vision.Decode(),
py_vision.Grayscale(1),
py_vision.ToTensor(), (lambda image: channel_swap(image))
]
transform = py_vision.ComposeOp(transforms)
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data1 = data1.map(input_columns=["image"], operations=transform())
# if input is grayscale, the output dimensions should be single channel
pad_gray = c_vision.Pad(100, fill_value=(20, 20, 20))
data1 = data1.map(input_columns=["image"], operations=pad_gray)
dataset_shape_1 = []
for item1 in data1.create_dict_iterator():
c_image = item1["image"]
dataset_shape_1.append(c_image.shape)
# Dataset for comparison
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
# we use the same padding logic
ctrans = [decode_op, pad_gray]
dataset_shape_2 = []
data2 = data2.map(input_columns=["image"], operations=ctrans)
for item2 in data2.create_dict_iterator():
c_image = item2["image"]
dataset_shape_2.append(c_image.shape)
for shape1, shape2 in zip(dataset_shape_1, dataset_shape_2):
# validate that the first two dimensions are the same
# we have a little inconsistency here because the third dimension is 1 after py_vision.Grayscale
assert (shape1[0:1] == shape2[0:1])
def test_pad_op():
"""
Test Pad op
"""
logger.info("test_random_color_jitter_op")
# First dataset
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
decode_op = c_vision.Decode()
pad_op = c_vision.Pad((100, 100, 100, 100))
ctrans = [
decode_op,
pad_op,
]
data1 = data1.map(input_columns=["image"], operations=ctrans)
# Second dataset
transforms = [
py_vision.Decode(),
py_vision.Pad(100),
py_vision.ToTensor(),
]
transform = py_vision.ComposeOp(transforms)
data2 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
data2 = data2.map(input_columns=["image"], operations=transform())
num_iter = 0
for item1, item2 in zip(data1.create_dict_iterator(),
data2.create_dict_iterator()):
num_iter += 1
c_image = item1["image"]
py_image = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8)
logger.info("shape of c_image: {}".format(c_image.shape))
logger.info("shape of py_image: {}".format(py_image.shape))
logger.info("dtype of c_image: {}".format(c_image.dtype))
logger.info("dtype of py_image: {}".format(py_image.dtype))
diff = c_image - py_image
mse = diff_mse(c_image, py_image)
logger.info("mse is {}".format(mse))
assert mse < 0.01
def test_pad_exception():
try:
data1 = ds.TFRecordDataset(DATA_DIR,
SCHEMA_DIR,
columns_list=["image"],
shuffle=False)
pad_op = c_vision.Pad(150)
data1 = data1.map(input_columns=["image"], operations=pad_op)
for _ in data1.create_dict_iterator():
pass
assert False
except RuntimeError as e:
assert "Pad error: invalid image shape, only support 3 channels image" in str(
e)