add UTs for LinearTransformation, ToPIL, ToType

tests/ut/python/dataset/test_linear_transformation.py

@@ -0,0 +1,225 @@
+# Copyright 2020 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""
+Testing LinearTransformation op in DE
+"""
+import numpy as np
+import mindspore.dataset as ds
+import mindspore.dataset.transforms.vision.py_transforms as py_vision
+from mindspore import log as logger
+from util import diff_mse, visualize, save_and_check_md5
+
+GENERATE_GOLDEN = False
+
+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"
+
+
+def test_linear_transformation_op(plot=False):
+    """
+    Test LinearTransformation op: verify if images transform correctly
+    """
+    logger.info("test_linear_transformation_01")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    transformation_matrix = np.eye(dim)
+    mean_vector = np.zeros(dim)
+
+    # Define operations
+    transforms = [
+        py_vision.Decode(),
+        py_vision.CenterCrop([height, weight]),
+        py_vision.ToTensor()
+    ]
+    transform = py_vision.ComposeOp(transforms)
+
+    # First dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    data1 = data1.map(input_columns=["image"], operations=transform())
+    # Note: if transformation matrix is diagonal matrix with all 1 in diagonal,
+    #       the output matrix in expected to be the same as the input matrix.
+    data1 = data1.map(input_columns=["image"],
+                      operations=py_vision.LinearTransformation(transformation_matrix, mean_vector))
+
+    # Second dataset
+    data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    data2 = data2.map(input_columns=["image"], operations=transform())
+
+    image_transformed = []
+    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_transformed.append(image1)
+        image.append(image2)
+
+        mse = diff_mse(image1, image2)
+        assert mse == 0
+    if plot:
+        visualize(image, image_transformed)
+
+def test_linear_transformation_md5_01():
+    """
+    Test LinearTransformation op: valid params (transformation_matrix, mean_vector)
+    Expected to pass
+    """
+    logger.info("test_linear_transformation_md5_01")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    transformation_matrix = np.ones([dim, dim])
+    mean_vector = np.zeros(dim)
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    transforms = [
+        py_vision.Decode(),
+        py_vision.CenterCrop([height, weight]),
+        py_vision.ToTensor(),
+        py_vision.LinearTransformation(transformation_matrix, mean_vector)
+    ]
+    transform = py_vision.ComposeOp(transforms)
+    data1 = data1.map(input_columns=["image"], operations=transform())
+
+    # Compare with expected md5 from images
+    filename = "linear_transformation_01_result.npz"
+    save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
+
+def test_linear_transformation_md5_02():
+    """
+    Test LinearTransformation op: transformation_matrix is not provided
+    Expected to raise ValueError
+    """
+    logger.info("test_linear_transformation_md5_02")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    mean_vector = np.zeros(dim)
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    try:
+        transforms = [
+            py_vision.Decode(),
+            py_vision.CenterCrop([height, weight]),
+            py_vision.ToTensor(),
+            py_vision.LinearTransformation(None, mean_vector)
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data1 = data1.map(input_columns=["image"], operations=transform())
+    except ValueError as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "not provided" in str(e)
+
+def test_linear_transformation_md5_03():
+    """
+    Test LinearTransformation op: mean_vector is not provided
+    Expected to raise ValueError
+    """
+    logger.info("test_linear_transformation_md5_03")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    transformation_matrix = np.ones([dim, dim])
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    try:
+        transforms = [
+            py_vision.Decode(),
+            py_vision.CenterCrop([height, weight]),
+            py_vision.ToTensor(),
+            py_vision.LinearTransformation(transformation_matrix, None)
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data1 = data1.map(input_columns=["image"], operations=transform())
+    except ValueError as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "not provided" in str(e)
+
+def test_linear_transformation_md5_04():
+    """
+    Test LinearTransformation op: transformation_matrix is not a square matrix
+    Expected to raise ValueError
+    """
+    logger.info("test_linear_transformation_md5_04")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    transformation_matrix = np.ones([dim, dim - 1])
+    mean_vector = np.zeros(dim)
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    try:
+        transforms = [
+            py_vision.Decode(),
+            py_vision.CenterCrop([height, weight]),
+            py_vision.ToTensor(),
+            py_vision.LinearTransformation(transformation_matrix, mean_vector)
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data1 = data1.map(input_columns=["image"], operations=transform())
+    except ValueError as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "square matrix" in str(e)
+
+def test_linear_transformation_md5_05():
+    """
+    Test LinearTransformation op: mean_vector does not match dimension of transformation_matrix
+    Expected to raise ValueError
+    """
+    logger.info("test_linear_transformation_md5_05")
+
+    # Initialize parameters
+    height = 50
+    weight = 50
+    dim = 3 * height * weight
+    transformation_matrix = np.ones([dim, dim])
+    mean_vector = np.zeros(dim-1)
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    try:
+        transforms = [
+            py_vision.Decode(),
+            py_vision.CenterCrop([height, weight]),
+            py_vision.ToTensor(),
+            py_vision.LinearTransformation(transformation_matrix, mean_vector)
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data1 = data1.map(input_columns=["image"], operations=transform())
+    except ValueError as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "should match" in str(e)
+
+if __name__ == '__main__':
+    test_linear_transformation_op(True)
+    test_linear_transformation_md5_01()
+    test_linear_transformation_md5_02()
+    test_linear_transformation_md5_03()
+    test_linear_transformation_md5_04()
+    test_linear_transformation_md5_05()

tests/ut/python/dataset/test_to_pil.py

@@ -0,0 +1,79 @@
+# Copyright 2020 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""
+Testing ToPIL op in DE
+"""
+import mindspore.dataset as ds
+import mindspore.dataset.transforms.vision.c_transforms as c_vision
+import mindspore.dataset.transforms.vision.py_transforms as py_vision
+from mindspore import log as logger
+from util import save_and_check_md5
+
+GENERATE_GOLDEN = False
+
+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"
+
+
+def test_to_pil_01():
+    """
+    Test ToPIL Op with md5 comparison: input is already PIL image
+    Expected to pass
+    """
+    logger.info("test_to_pil_01")
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    transforms = [
+        py_vision.Decode(),
+        # If input is already PIL image.
+        py_vision.ToPIL(),
+        py_vision.CenterCrop(375),
+        py_vision.ToTensor()
+    ]
+    transform = py_vision.ComposeOp(transforms)
+    data1 = data1.map(input_columns=["image"], operations=transform())
+
+    # Compare with expected md5 from images
+    filename = "to_pil_01_result.npz"
+    save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
+
+def test_to_pil_02():
+    """
+    Test ToPIL Op with md5 comparison: input is not PIL image
+    Expected to pass
+    """
+    logger.info("test_to_pil_02")
+
+    # Generate dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    decode_op = c_vision.Decode()
+    transforms = [
+        # If input type is not PIL.
+        py_vision.ToPIL(),
+        py_vision.CenterCrop(375),
+        py_vision.ToTensor()
+    ]
+    transform = py_vision.ComposeOp(transforms)
+    data1 = data1.map(input_columns=["image"], operations=decode_op)
+    data1 = data1.map(input_columns=["image"], operations=transform())
+
+    # Compare with expected md5 from images
+    filename = "to_pil_02_result.npz"
+    save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
+
+if __name__ == "__main__":
+    test_to_pil_01()
+    test_to_pil_02()

tests/ut/python/dataset/test_to_type.py

@@ -0,0 +1,180 @@
+# Copyright 2020 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""
+Testing ToType op in DE
+"""
+import numpy as np
+import mindspore.dataset as ds
+import mindspore.dataset.transforms.vision.py_transforms as py_vision
+from mindspore import log as logger
+from util import save_and_check_md5
+
+GENERATE_GOLDEN = False
+
+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"
+
+
+def test_to_type_op():
+    """
+    Test ToType Op
+    """
+    logger.info("test_to_type_op")
+
+    # First dataset
+    data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    transforms1 = [
+        py_vision.Decode(),
+        py_vision.ToTensor(),
+        # Note: Convert the datatype from float32 to int16
+        py_vision.ToType(np.int16)
+    ]
+    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())
+
+    for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()):
+        image1 = item1["image"]
+        image2 = item2["image"]
+
+        assert isinstance(image1, np.ndarray)
+        assert isinstance(image2, np.ndarray)
+        assert image1.dtype == np.int16
+        assert image2.dtype == np.float32
+        assert image1.shape == image2.shape
+
+def test_to_type_01():
+    """
+    Test ToType Op with md5 comparison: valid input (Numpy dtype)
+    Expect to pass
+    """
+    logger.info("test_to_type_01")
+
+    # Generate dataset
+    data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    transforms = [
+        py_vision.Decode(),
+        py_vision.ToTensor(),
+        # Note: Convert the datatype from float32 to int32
+        py_vision.ToType(np.int32)
+    ]
+    transform = py_vision.ComposeOp(transforms)
+    data = data.map(input_columns=["image"], operations=transform())
+
+    # Compare with expected md5 from images
+    filename = "to_type_01_result.npz"
+    save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
+
+def test_to_type_02():
+    """
+    Test ToType Op with md5 comparison: valid input (str)
+    Expect to pass
+    """
+    logger.info("test_to_type_02")
+    # Generate dataset
+    data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+    transforms = [
+        py_vision.Decode(),
+        py_vision.ToTensor(),
+        # Note: Convert to type int
+        py_vision.ToType('int')
+    ]
+    transform = py_vision.ComposeOp(transforms)
+    data = data.map(input_columns=["image"], operations=transform())
+
+    # Compare with expected md5 from images
+    filename = "to_type_02_result.npz"
+    save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN)
+
+def test_to_type_03():
+    """
+    Test ToType Op: invalid input image type
+    Expect to raise error
+    """
+    logger.info("test_to_type_03")
+
+    try:
+        # Generate dataset
+        data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+        transforms = [
+            py_vision.Decode(),
+            # Note: If the object is not numpy, e.g. PIL image, TypeError will raise
+            py_vision.ToType(np.int32)
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data = data.map(input_columns=["image"], operations=transform())
+    except BaseException as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "Numpy" in str(e)
+
+def test_to_type_04():
+    """
+    Test ToType Op: no output_type given
+    Expect to raise error
+    """
+    logger.info("test_to_type_04")
+
+    try:
+        # Generate dataset
+        data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+        transforms = [
+            py_vision.Decode(),
+            py_vision.ToTensor(),
+            # Note: if output_type is not explicitly given
+            py_vision.ToType()
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data = data.map(input_columns=["image"], operations=transform())
+    except BaseException as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "missing" in str(e)
+
+def test_to_type_05():
+    """
+    Test ToType Op: invalid output_type
+    Expect to raise error
+    """
+    logger.info("test_to_type_05")
+
+    try:
+        # Generate dataset
+        data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False)
+        transforms = [
+            py_vision.Decode(),
+            py_vision.ToTensor(),
+            # Note: if output_type is not explicitly given
+            py_vision.ToType('invalid')
+        ]
+        transform = py_vision.ComposeOp(transforms)
+        data = data.map(input_columns=["image"], operations=transform())
+    except BaseException as e:
+        logger.info("Got an exception in DE: {}".format(str(e)))
+        assert "data type" in str(e)
+
+if __name__ == "__main__":
+    test_to_type_op()
+    test_to_type_01()
+    test_to_type_02()
+    test_to_type_03()
+    test_to_type_04()
+    test_to_type_05()