Function Differences with tf.keras.datasets.cifar100

tf.keras.datasets.cifar100

class tf.keras.datasets.cifar100()

For more information, see tf.keras.datasets.cifar100.

mindspore.dataset.Cifar100Dataset

class mindspore.dataset.Cifar100Dataset(
    dataset_dir,
    usage=None,
    num_samples=None,
    num_parallel_workers=None,
    shuffle=None,
    sampler=None,
    num_shards=None,
    shard_id=None,
    cache=None
)

For more information, see mindspore.dataset.Cifar100Dataset.

Differences

TensorFlow: The Cifar100 dataset can be downloaded and loaded using the load_data method within this class.

MindSpore: Load the Cifar100 dataset file from the specified path and return the Dataset.

Code Example

# The following implements Cifar100Dataset with MindSpore.
import mindspore.dataset as ds

cifar100_dataset_dir = "/path/to/cifar100_dataset_directory"
dataset = ds.Cifar100Dataset(dataset_dir=cifar100_dataset_dir)

# The following implements cifar100 with TensorFlow.
import tensorflow as tf

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar100.load_data()