def test_random_order_op(plot=False): """ Test RandomOrder in python transformations """ logger.info("test_random_order_op") # define map operations transforms_list = [py_vision.CenterCrop(64), py_vision.RandomRotation(30)] transforms1 = [ py_vision.Decode(), py_vision.RandomOrder(transforms_list), py_vision.ToTensor() ] transform1 = py_vision.ComposeOp(transforms1) transforms2 = [ py_vision.Decode(), py_vision.ToTensor() ] transform2 = py_vision.ComposeOp(transforms2) # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) data1 = data1.map(input_columns=["image"], operations=transform1()) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) data2 = data2.map(input_columns=["image"], operations=transform2()) image_order = [] image_original = [] 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_order.append(image1) image_original.append(image2) if plot: visualize(image_original, image_order)
def test_rgb_hsv_pipeline(): # First dataset transforms1 = [vision.Decode(), vision.Resize([64, 64]), vision.ToTensor()] transforms1 = vision.ComposeOp(transforms1) ds1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) ds1 = ds1.map(input_columns=["image"], operations=transforms1()) # Second dataset transforms2 = [ vision.Decode(), vision.Resize([64, 64]), vision.ToTensor(), vision.RgbToHsv(), vision.HsvToRgb() ] transform2 = vision.ComposeOp(transforms2) ds2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) ds2 = ds2.map(input_columns=["image"], operations=transform2()) num_iter = 0 for data1, data2 in zip(ds1.create_dict_iterator(), ds2.create_dict_iterator()): num_iter += 1 ori_img = data1["image"] cvt_img = data2["image"] assert_allclose(ori_img.flatten(), cvt_img.flatten(), rtol=1e-5, atol=0) assert ori_img.shape == cvt_img.shape
def test_random_color_adjust_op_contrast(): """ Test RandomColorAdjust op """ logger.info("test_random_color_adjust_op") # 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((1, 1), (0.5, 0.5), (1, 1), (0, 0)) ctrans = [decode_op, random_adjust_op ] data1 = data1.map(input_columns=["image"], operations=ctrans) # Second dataset transforms = [ py_vision.Decode(), py_vision.RandomColorAdjust((1, 1), (0.5, 0.5), (1, 1), (0, 0)), 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 logger.info("contrast difference c is : {}".format(c_image[0][0])) logger.info("contrast difference py is : {}".format(py_image[0][0])) logger.info("contrast difference is : {}".format(diff[0][0])) # mse = (np.sum(np.power(diff, 2))) / (c_image.shape[0] * c_image.shape[1]) mse = diff_mse(c_image, py_image) logger.info("mse is {}".format(mse))
def test_deterministic_python_seed_multi_thread(): """ Test deterministic execution with seed in python, this fails with multi-thread pyfunc run """ logger.info("deterministic_random_crop_op_python_2") ds.config.set_seed(0) # when we set the seed all operations within our dataset should be deterministic # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [ py_vision.Decode(), py_vision.RandomCrop([512, 512], [200, 200, 200, 200]), py_vision.ToTensor(), ] transform = py_vision.ComposeOp(transforms) data1 = data1.map(input_columns=["image"], operations=transform(), python_multiprocessing=True) data1_output = [] # config.set_seed() calls random.seed() for data_one in data1.create_dict_iterator(): data1_output.append(data_one["image"]) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) # If seed is set up on constructor data2 = data2.map(input_columns=["image"], operations=transform(), python_multiprocessing=True) # config.set_seed() calls random.seed() ds.config.set_seed(0) data2_output = [] for data_two in data2.create_dict_iterator(): data2_output.append(data_two["image"]) try: np.testing.assert_equal(data1_output, data2_output) except BaseException as e: # expect output to not match during multi-threaded excution logger.info("Got an exception in DE: {}".format(str(e))) assert "Array" in str(e)
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()) 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) 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)) mse = diff_mse(c_image, py_image) logger.info("mse is {}".format(mse)) assert mse < 0.01
def test_random_affine_py_exception_non_pil_images(): """ Test RandomAffine: input img is ndarray and not PIL, expected to raise RuntimeError """ logger.info("test_random_affine_exception_negative_degrees") dataset = ds.MnistDataset(MNIST_DATA_DIR, num_parallel_workers=3) try: transform = py_vision.ComposeOp([py_vision.ToTensor(), py_vision.RandomAffine(degrees=(15, 15))]) dataset = dataset.map(input_columns=["image"], operations=transform(), num_parallel_workers=3, python_multiprocessing=True) for _ in dataset.create_dict_iterator(): break except RuntimeError as e: logger.info("Got an exception in DE: {}".format(str(e))) assert "Pillow image" in str(e)
def test_equalize_md5(): """ Test Equalize with md5 check """ logger.info("Test Equalize") # First dataset data1 = de.ImageFolderDatasetV2(dataset_dir=DATA_DIR, shuffle=False) transforms = F.ComposeOp([F.Decode(), F.Equalize(), F.ToTensor()]) data1 = data1.map(input_columns="image", operations=transforms()) # Compare with expected md5 from images filename = "equalize_01_result.npz" save_and_check_md5(data1, filename, generate_golden=GENERATE_GOLDEN)
def test_five_crop_error_msg(): """ Test FiveCrop error message. """ logger.info("test_five_crop_error_msg") data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [vision.Decode(), vision.FiveCrop(200), vision.ToTensor()] transform = vision.ComposeOp(transforms) data = data.map(input_columns=["image"], operations=transform()) with pytest.raises(RuntimeError): data.create_tuple_iterator().__next__()
def test_HWC2CHW_comp(plot=False): """ Test HWC2CHW between python and c image augmentation """ logger.info("Test HWC2CHW with c_transform and py_transform comparison") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = c_vision.Decode() hwc2chw_op = c_vision.HWC2CHW() data1 = data1.map(input_columns=["image"], operations=decode_op) data1 = data1.map(input_columns=["image"], operations=hwc2chw_op) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [ py_vision.Decode(), py_vision.ToTensor(), py_vision.HWC2CHW() ] transform = py_vision.ComposeOp(transforms) data2 = data2.map(input_columns=["image"], operations=transform()) image_c_transposed = [] image_py_transposed = [] 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) # compare images between that applying c_transform and py_transform mse = diff_mse(py_image, c_image) # the images aren't exactly the same due to rounding error assert mse < 0.001 image_c_transposed.append(item1["image"].copy()) image_py_transposed.append(item2["image"].copy()) if plot: visualize(image_c_transposed, image_py_transposed)
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 = F.ComposeOp([lambda img: img.astype(np.uint8), F.ToPIL(), p_op, np.array]) data1 = data1.map(input_columns=["image"], operations=[vision.Decode(), c_op]) data2 = data2.map(input_columns=["image"], operations=[vision.Decode()]) data2 = data2.map(input_columns=["image"], operations=transforms_random_color_py()) image_random_color_op = [] image = [] for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()): 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_vertical_comp(plot=False): """ Test test_random_vertical_flip and compare between python and c image augmentation ops """ logger.info("test_random_vertical_comp") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = c_vision.Decode() # Note: The image must be flipped if prob is set to be 1 random_horizontal_op = c_vision.RandomVerticalFlip(1) data1 = data1.map(input_columns=["image"], operations=decode_op) data1 = data1.map(input_columns=["image"], operations=random_horizontal_op) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [ py_vision.Decode(), # Note: The image must be flipped if prob is set to be 1 py_vision.RandomVerticalFlip(1), py_vision.ToTensor() ] transform = py_vision.ComposeOp(transforms) data2 = data2.map(input_columns=["image"], operations=transform()) images_list_c = [] images_list_py = [] for item1, item2 in zip(data1.create_dict_iterator(), data2.create_dict_iterator()): image_c = item1["image"] image_py = (item2["image"].transpose(1, 2, 0) * 255).astype(np.uint8) images_list_c.append(image_c) images_list_py.append(image_py) # Check if the output images are the same mse = diff_mse(image_c, image_py) assert mse < 0.001 if plot: visualize_list(images_list_c, images_list_py, visualize_mode=2)
def test_cut_out_op(plot=False): """ Test Cutout """ logger.info("test_cut_out") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms_1 = [f.Decode(), f.ToTensor(), f.RandomErasing(value='random')] transform_1 = f.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) decode_op = c.Decode() cut_out_op = c.CutOut(80) transforms_2 = [decode_op, cut_out_op] data2 = data2.map(input_columns=["image"], operations=transforms_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) # C image doesn't require transpose 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)) mse = diff_mse(image_1, image_2) if plot: visualize_image(image_1, image_2, mse)
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_list(image, image_transformed)
def util_test_normalize_grayscale(num_output_channels, mean, std): """ Utility function for testing Normalize. Input arguments are given by other tests """ transforms = [ py_vision.Decode(), py_vision.Grayscale(num_output_channels), py_vision.ToTensor(), py_vision.Normalize(mean, std) ] 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()) return data
def test_random_rotation_md5(): """ Test RandomRotation with md5 check """ logger.info("Test RandomRotation with md5 check") original_seed = config_get_set_seed(5) original_num_parallel_workers = config_get_set_num_parallel_workers(1) # Fisrt dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = c_vision.Decode() resize_op = c_vision.RandomRotation((0, 90), expand=True, resample=Inter.BILINEAR, center=(50, 50), fill_value=150) data1 = data1.map(input_columns=["image"], operations=decode_op) data1 = data1.map(input_columns=["image"], operations=resize_op) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, shuffle=False) transform2 = py_vision.ComposeOp([ py_vision.Decode(), py_vision.RandomRotation((0, 90), expand=True, resample=Inter.BILINEAR, center=(50, 50), fill_value=150), py_vision.ToTensor() ]) data2 = data2.map(input_columns=["image"], operations=transform2()) # Compare with expected md5 from images filename1 = "random_rotation_01_c_result.npz" save_and_check_md5(data1, filename1, generate_golden=GENERATE_GOLDEN) filename2 = "random_rotation_01_py_result.npz" save_and_check_md5(data2, filename2, generate_golden=GENERATE_GOLDEN) # Restore configuration ds.config.set_seed(original_seed) ds.config.set_num_parallel_workers(original_num_parallel_workers)
def test_pad_grayscale(): """ Tests that the pad works for grayscale images """ # Note: image.transpose performs channel swap to allow py transforms to # work with c transforms transforms = [ py_vision.Decode(), py_vision.Grayscale(1), py_vision.ToTensor(), (lambda image: (image.transpose(1, 2, 0) * 255).astype(np.uint8)) ] 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_type_cast(): """ Test TypeCast op """ logger.info("test_type_cast") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = c_vision.Decode() type_cast_op = data_util.TypeCast(mstype.float32) ctrans = [ decode_op, type_cast_op, ] data1 = data1.map(input_columns=["image"], operations=ctrans) # Second dataset transforms = [py_vision.Decode(), 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)) assert c_image.dtype == "float32"
def test_cut_out_comp(plot=False): """ Test Cutout with c++ and python op comparison """ logger.info("test_cut_out_comp") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms_1 = [f.Decode(), f.ToTensor(), f.Cutout(200)] transform_1 = f.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 = [c.Decode(), c.CutOut(200)] data2 = data2.map(input_columns=["image"], operations=transforms_2) num_iter = 0 image_list_1, image_list_2 = [], [] 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) # C image doesn't require transpose image_2 = item2["image"] image_list_1.append(image_1) image_list_2.append(image_2) 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(image_list_1, image_list_2, visualize_mode=2)
def test_normalize_op_py(plot=False): """ Test Normalize in python transformations """ logger.info("Test Normalize in python") mean = [0.475, 0.45, 0.392] std = [0.275, 0.267, 0.278] # define map operations transforms = [py_vision.Decode(), py_vision.ToTensor()] transform = py_vision.ComposeOp(transforms) normalize_op = py_vision.Normalize(mean, std) # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) data1 = data1.map(input_columns=["image"], operations=transform()) data1 = data1.map(input_columns=["image"], operations=normalize_op) # Second dataset 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()): image_de_normalized = (item1["image"].transpose(1, 2, 0) * 255).astype( np.uint8) image_np_normalized = ( normalize_np(item2["image"].transpose(1, 2, 0), mean, std) * 255).astype(np.uint8) image_original = (item2["image"].transpose(1, 2, 0) * 255).astype( np.uint8) mse = diff_mse(image_de_normalized, image_np_normalized) logger.info("image_{}, mse: {}".format(num_iter + 1, mse)) assert mse < 0.01 if plot: visualize_image(image_original, image_de_normalized, mse, image_np_normalized) num_iter += 1
def test_deterministic_python_seed(): """ Test deterministic execution with seed in python """ logger.info("test_deterministic_python_seed") # Save original configuration values num_parallel_workers_original = ds.config.get_num_parallel_workers() seed_original = ds.config.get_seed() 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) transforms = [ py_vision.Decode(), py_vision.RandomCrop([512, 512], [200, 200, 200, 200]), py_vision.ToTensor(), ] transform = py_vision.ComposeOp(transforms) data1 = data1.map(input_columns=["image"], operations=transform()) data1_output = [] # config.set_seed() calls random.seed() for data_one in data1.create_dict_iterator(): data1_output.append(data_one["image"]) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) data2 = data2.map(input_columns=["image"], operations=transform()) # config.set_seed() calls random.seed(), resets seed for next dataset iterator ds.config.set_seed(0) data2_output = [] for data_two in data2.create_dict_iterator(): data2_output.append(data_two["image"]) np.testing.assert_equal(data1_output, data2_output) # Restore original configuration values ds.config.set_num_parallel_workers(num_parallel_workers_original) ds.config.set_seed(seed_original)
def test_random_color_adjust_op_brightness(): """ Test RandomColorAdjust op """ logger.info("test_random_color_adjust_op") # 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((0.8, 0.8), (1, 1), (1, 1), (0, 0)) ctrans = [decode_op, random_adjust_op, ] data1 = data1.map(input_columns=["image"], operations=ctrans) # Second dataset transforms = [ py_vision.Decode(), py_vision.RandomColorAdjust((0.8, 0.8), (1, 1), (1, 1), (0, 0)), 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)) mse = diff_mse(c_image, py_image) logger.info("mse is {}".format(mse)) assert mse < 0.01
def test_random_grayscale_invalid_param(): """ Test RandomGrayscale: invalid parameter given, expect to raise error """ logger.info("test_random_grayscale_invalid_param") # Generate dataset data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) try: transforms = [ py_vision.Decode(), py_vision.RandomGrayscale(1.5), py_vision.ToTensor() ] transform = py_vision.ComposeOp(transforms) data = data.map(input_columns=["image"], operations=transform()) except ValueError as e: logger.info("Got an exception in DE: {}".format(str(e))) assert "Input is not within the required range" in str(e)
def create_icdar_train_dataset(img_path, gt_path, batch_size=32, repeat_num=10, is_training=True, num_parallel_workers=1, length=512, scale=0.25): dataloader = ds.GeneratorDataset(source=custom_dataset(img_path, gt_path, scale=scale, length=length), column_names=["img", "score_map", "geo_map", "ignored_map"], shuffle=is_training, num_parallel_workers=num_parallel_workers) dataloader.set_dataset_size(1000) transform = py_transforms.ComposeOp([py_transforms.RandomColorAdjust(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.25), \ py_transforms.ToTensor(), \ py_transforms.Normalize(mean=(0.5,0.5,0.5),std=(0.5,0.5,0.5))]) dataloader = dataloader.map(input_columns="img", operations=transform, num_parallel_workers=num_parallel_workers, python_multiprocessing=is_training) dataloader = dataloader.batch(batch_size, drop_remainder=True) return dataloader
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_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_rotation_diff(): """ Test Rotation op """ logger.info("test_random_rotation_op") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = c_vision.Decode() rotation_op = c_vision.RandomRotation((45, 45), expand=True) ctrans = [decode_op, rotation_op] data1 = data1.map(input_columns=["image"], operations=ctrans) # Second dataset transforms = [ py_vision.Decode(), py_vision.RandomRotation((45, 45), expand=True), 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))
def test_random_crop_comp(plot=False): """ Test RandomCrop and compare between python and c image augmentation """ logger.info("Test RandomCrop with c_transform and py_transform comparison") ds.config.set_seed(0) ds.config.set_num_parallel_workers(1) cropped_size = 512 # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) random_crop_op = c_vision.RandomCrop(cropped_size) decode_op = c_vision.Decode() data1 = data1.map(input_columns=["image"], operations=decode_op) data1 = data1.map(input_columns=["image"], operations=random_crop_op) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [ py_vision.Decode(), py_vision.RandomCrop(cropped_size), 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) if plot: visualize(image_c_cropped, image_py_cropped)
def test_random_vertical_invalid_prob_py(): """ Test RandomVerticalFlip op in py_transforms: invalid input, expect to raise error """ logger.info("test_random_vertical_invalid_prob_py") # Generate dataset data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) try: transforms = [ py_vision.Decode(), # Note: Valid range of prob should be [0.0, 1.0] py_vision.RandomVerticalFlip(1.5), py_vision.ToTensor() ] transform = py_vision.ComposeOp(transforms) data = data.map(input_columns=["image"], operations=transform()) except ValueError as e: logger.info("Got an exception in DE: {}".format(str(e))) assert 'Input prob is not within the required interval of (0.0 to 1.0).' in str(e)
def test_five_crop_error_msg(): """ Test FiveCrop error message. """ logger.info("test_five_crop_error_msg") data = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [vision.Decode(), vision.FiveCrop(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_center_crop_comp(height=375, width=375, plot=False): """ Test CenterCrop between python and c image augmentation """ logger.info("Test CenterCrop") # First dataset data1 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) decode_op = vision.Decode() center_crop_op = vision.CenterCrop([height, width]) data1 = data1.map(input_columns=["image"], operations=decode_op) data1 = data1.map(input_columns=["image"], operations=center_crop_op) # Second dataset data2 = ds.TFRecordDataset(DATA_DIR, SCHEMA_DIR, columns_list=["image"], shuffle=False) transforms = [ py_vision.Decode(), py_vision.CenterCrop([height, width]), py_vision.ToTensor() ] transform = py_vision.ComposeOp(transforms) data2 = data2.map(input_columns=["image"], operations=transform()) image_cropped = [] image = [] 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) # Note: The images aren't exactly the same due to rounding error assert diff_mse(py_image, c_image) < 0.001 image_cropped.append(item1["image"].copy()) image.append(item2["image"].copy()) if plot: visualize(image, image_cropped)