tf.keras.datasets.cifar100.load_data
Stay organized with collections
Save and categorize content based on your preferences.
Loads CIFAR100 dataset.
tf.keras.datasets.cifar100.load_data(
label_mode='fine'
)
This is a dataset of 50,000 32x32 color training images and
10,000 test images, labeled over 100 fine-grained classes that are
grouped into 20 coarse-grained classes. See more info at the
CIFAR homepage.
Arguments |
|---|
label_mode
|
one of "fine", "coarse". If it is "fine" the category labels
are the fine-grained labels, if it is "coarse" the output labels are the
coarse-grained superclasses.
|
Returns |
|---|
Tuple of Numpy arrays: (x_train, y_train), (x_test, y_test).
x_train, x_test: uint8 arrays of RGB image data with shape
(num_samples, 3, 32, 32) if tf.keras.backend.image_data_format() is
'channels_first', or (num_samples, 32, 32, 3) if the data format
is 'channels_last'.
y_train, y_test: uint8 arrays of category labels with shape
(num_samples, 1).
|
Raises |
|---|
ValueError
|
in case of invalid label_mode.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.keras.datasets.cifar100.load_data\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/datasets/cifar100/load_data) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/datasets/cifar100.py#L31-L84) |\n\nLoads [CIFAR100 dataset](https://www.cs.toronto.edu/%7Ekriz/cifar.html).\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.datasets.cifar100.load_data`](/api_docs/python/tf/keras/datasets/cifar100/load_data)\n\n\u003cbr /\u003e\n\n tf.keras.datasets.cifar100.load_data(\n label_mode='fine'\n )\n\nThis is a dataset of 50,000 32x32 color training images and\n10,000 test images, labeled over 100 fine-grained classes that are\ngrouped into 20 coarse-grained classes. See more info at the\n[CIFAR homepage](https://www.cs.toronto.edu/%7Ekriz/cifar.html).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|--------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `label_mode` | one of \"fine\", \"coarse\". If it is \"fine\" the category labels are the fine-grained labels, if it is \"coarse\" the output labels are the coarse-grained superclasses. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. \u003cbr /\u003e **x_train, x_test** : uint8 arrays of RGB image data with shape `(num_samples, 3, 32, 32)` if [`tf.keras.backend.image_data_format()`](../../../../tf/keras/backend/image_data_format) is `'channels_first'`, or `(num_samples, 32, 32, 3)` if the data format is `'channels_last'`. **y_train, y_test**: uint8 arrays of category labels with shape (num_samples, 1). ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------|\n| `ValueError` | in case of invalid `label_mode`. |\n\n\u003cbr /\u003e"]]
TensorFlow 1 version
View source on GitHub