def loader(self): """Dataloader arrtribute which is a unified interface to generate the data. :return: a batch data :rtype: dict, list, optional """ ms_dataset = GeneratorDataset(self.dataset, ["image", "label"], sampler=self.sampler) # ms_dataset.set_dataset_size(len(self.dataset)) # TODO delete, only mindspore 0.5 need ms_dataset = self.convert_dtype(ms_dataset) if self.args.shuffle: buffer_size = self.args.get("buffer_size", len(self.dataset)) ms_dataset = ms_dataset.shuffle(buffer_size=buffer_size) if self.args.get("mixup", False): num_class = self.args.get("num_class") one_hot_op = C2.OneHot(num_classes=num_class) ms_dataset = ms_dataset.map(operations=one_hot_op, input_columns=["label"]) mixup_batch_op = vision.MixUpBatch(2) ms_dataset = ms_dataset.batch(self.args.batch_size) ms_dataset = ms_dataset.map(operations=mixup_batch_op, input_columns=["image", "label"]) else: ms_dataset = ms_dataset.batch(self.args.batch_size) from mindspore.dataset.engine.datasets import BatchDataset, MapDataset BatchDataset.__len__ = BatchDataset.get_dataset_size MapDataset.__len__ = MapDataset.get_dataset_size return ms_dataset
def test_mixup_batch_fail4(): """ Test MixUpBatch Fail 2 We expect this to fail because alpha is zero """ logger.info("test_mixup_batch_fail4") # Original Images ds_original = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) ds_original = ds_original.batch(5) images_original = np.array([]) for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) one_hot_op = data_trans.OneHot(num_classes=10) data1 = data1.map(operations=one_hot_op, input_columns=["label"]) with pytest.raises(ValueError) as error: vision.MixUpBatch(0.0) error_message = "Input is not within the required interval" assert error_message in str(error.value)
def test_mixup_batch_fail5(): """ Test MixUpBatch Fail 5 We expect this to fail because labels are not OntHot encoded """ logger.info("test_mixup_batch_fail5") # Original Images ds_original = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) ds_original = ds_original.batch(5) images_original = np.array([]) for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) mixup_batch_op = vision.MixUpBatch() data1 = data1.batch(5, drop_remainder=True) data1 = data1.map(operations=mixup_batch_op, input_columns=["image", "label"]) with pytest.raises(RuntimeError) as error: images_mixup = np.array([]) for idx, (image, _) in enumerate(data1): if idx == 0: images_mixup = image.asnumpy() else: images_mixup = np.append(images_mixup, image.asnumpy(), axis=0) error_message = "MixUpBatch: Wrong labels shape. The second column (labels) must have a shape of NC or NLC" assert error_message in str(error.value)
def test_mixup_batch_fail3(): """ Test MixUpBatch op We expect this to fail because label column is not passed to mixup_batch """ logger.info("test_mixup_batch_fail3") # Original Images ds_original = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) ds_original = ds_original.batch(5, drop_remainder=True) images_original = None for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) one_hot_op = data_trans.OneHot(num_classes=10) data1 = data1.map(operations=one_hot_op, input_columns=["label"]) mixup_batch_op = vision.MixUpBatch() data1 = data1.batch(5, drop_remainder=True) data1 = data1.map(operations=mixup_batch_op, input_columns=["image"]) with pytest.raises(RuntimeError) as error: images_mixup = np.array([]) for idx, (image, _) in enumerate(data1): if idx == 0: images_mixup = image.asnumpy() else: images_mixup = np.append(images_mixup, image.asnumpy(), axis=0) error_message = "Both images and labels columns are required" assert error_message in str(error.value)
def test_mixup_batch_fail1(): """ Test MixUpBatch Fail 1 We expect this to fail because the images and labels are not batched """ logger.info("test_mixup_batch_fail1") # Original Images ds_original = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) ds_original = ds_original.batch(5) images_original = np.array([]) for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) one_hot_op = data_trans.OneHot(num_classes=10) data1 = data1.map(operations=one_hot_op, input_columns=["label"]) mixup_batch_op = vision.MixUpBatch(0.1) with pytest.raises(RuntimeError) as error: data1 = data1.map(operations=mixup_batch_op, input_columns=["image", "label"]) for idx, (image, _) in enumerate(data1): if idx == 0: images_mixup = image.asnumpy() else: images_mixup = np.append(images_mixup, image.asnumpy(), axis=0) error_message = "You must make sure images are HWC or CHW and batched" assert error_message in str(error.value)
def test_mixup_batch_success4(plot=False): """ Test MixUpBatch op on a dataset where OneHot returns a 2D vector. Alpha parameter will be selected by default in this case """ logger.info("test_mixup_batch_success4") # Original Images ds_original = ds.CelebADataset(DATA_DIR3, shuffle=False) decode_op = vision.Decode() ds_original = ds_original.map(operations=[decode_op], input_columns=["image"]) ds_original = ds_original.batch(2, drop_remainder=True) images_original = None for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.CelebADataset(DATA_DIR3, shuffle=False) decode_op = vision.Decode() data1 = data1.map(operations=[decode_op], input_columns=["image"]) one_hot_op = data_trans.OneHot(num_classes=100) data1 = data1.map(operations=one_hot_op, input_columns=["attr"]) mixup_batch_op = vision.MixUpBatch() data1 = data1.batch(2, drop_remainder=True) data1 = data1.map(operations=mixup_batch_op, input_columns=["image", "attr"]) images_mixup = np.array([]) for idx, (image, _) in enumerate(data1): if idx == 0: images_mixup = image.asnumpy() else: images_mixup = np.append(images_mixup, image.asnumpy(), axis=0) if plot: visualize_list(images_original, images_mixup) num_samples = images_original.shape[0] mse = np.zeros(num_samples) for i in range(num_samples): mse[i] = diff_mse(images_mixup[i], images_original[i]) logger.info("MSE= {}".format(str(np.mean(mse))))
def test_mixup_batch_success2(plot=False): """ Test MixUpBatch op with specified alpha parameter on ImageFolderDataset """ logger.info("test_mixup_batch_success2") # Original Images ds_original = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False) decode_op = vision.Decode() ds_original = ds_original.map(operations=[decode_op], input_columns=["image"]) ds_original = ds_original.batch(4, pad_info={}, drop_remainder=True) images_original = None for idx, (image, _) in enumerate(ds_original): if idx == 0: images_original = image.asnumpy() else: images_original = np.append(images_original, image.asnumpy(), axis=0) # MixUp Images data1 = ds.ImageFolderDataset(dataset_dir=DATA_DIR2, shuffle=False) decode_op = vision.Decode() data1 = data1.map(operations=[decode_op], input_columns=["image"]) one_hot_op = data_trans.OneHot(num_classes=10) data1 = data1.map(operations=one_hot_op, input_columns=["label"]) mixup_batch_op = vision.MixUpBatch(2.0) data1 = data1.batch(4, pad_info={}, drop_remainder=True) data1 = data1.map(operations=mixup_batch_op, input_columns=["image", "label"]) images_mixup = None for idx, (image, _) in enumerate(data1): if idx == 0: images_mixup = image.asnumpy() else: images_mixup = np.append(images_mixup, image.asnumpy(), axis=0) if plot: visualize_list(images_original, images_mixup) num_samples = images_original.shape[0] mse = np.zeros(num_samples) for i in range(num_samples): mse[i] = diff_mse(images_mixup[i], images_original[i]) logger.info("MSE= {}".format(str(np.mean(mse))))
def test_mixup_batch_md5(): """ Test MixUpBatch with MD5: """ logger.info("test_mixup_batch_md5") original_seed = config_get_set_seed(0) original_num_parallel_workers = config_get_set_num_parallel_workers(1) # MixUp Images data = ds.Cifar10Dataset(DATA_DIR, num_samples=10, shuffle=False) one_hot_op = data_trans.OneHot(num_classes=10) data = data.map(operations=one_hot_op, input_columns=["label"]) mixup_batch_op = vision.MixUpBatch() data = data.batch(5, drop_remainder=True) data = data.map(operations=mixup_batch_op, input_columns=["image", "label"]) filename = "mixup_batch_c_result.npz" save_and_check_md5(data, filename, generate_golden=GENERATE_GOLDEN) # Restore config setting ds.config.set_seed(original_seed) ds.config.set_num_parallel_workers(original_num_parallel_workers)