tf.keras.datasets.mnist.load_data
Stay organized with collections
Save and categorize content based on your preferences.
Loads the MNIST dataset.
tf.keras.datasets.mnist.load_data(
path='mnist.npz'
)
Used in the notebooks
| Used in the guide |
Used in the tutorials |
|
|
|
This is a dataset of 60,000 28x28 grayscale images of the 10 digits,
along with a test set of 10,000 images.
More info can be found at the
MNIST homepage.
Args |
|---|
path
|
path where to cache the dataset locally
(relative to ~/.keras/datasets).
|
Returns |
|---|
Tuple of NumPy arrays: (x_train, y_train), (x_test, y_test).
|
x_train: uint8 NumPy array of grayscale image data with shapes
(60000, 28, 28), containing the training data. Pixel values range
from 0 to 255.
y_train: uint8 NumPy array of digit labels (integers in range 0-9)
with shape (60000,) for the training data.
x_test: uint8 NumPy array of grayscale image data with shapes
(10000, 28, 28), containing the test data. Pixel values range
from 0 to 255.
y_test: uint8 NumPy array of digit labels (integers in range 0-9)
with shape (10000,) for the test data.
Example:
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
assert x_train.shape == (60000, 28, 28)
assert x_test.shape == (10000, 28, 28)
assert y_train.shape == (60000,)
assert y_test.shape == (10000,)
License:
Yann LeCun and Corinna Cortes hold the copyright of MNIST dataset,
which is a derivative work from original NIST datasets.
MNIST dataset is made available under the terms of the
Creative Commons Attribution-Share Alike 3.0 license.
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. Some content is licensed under the numpy license.
Last updated 2024-06-07 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-06-07 UTC."],[],[],null,["# tf.keras.datasets.mnist.load_data\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/datasets/mnist.py#L9-L71) |\n\nLoads the MNIST dataset. \n\n tf.keras.datasets.mnist.load_data(\n path='mnist.npz'\n )\n\n### Used in the notebooks\n\n| Used in the guide | Used in the tutorials |\n|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| - [Import a JAX model using JAX2TF](https://www.tensorflow.org/guide/jax2tf) - [Mixed precision](https://www.tensorflow.org/guide/mixed_precision) - [Multi-GPU and distributed training](https://www.tensorflow.org/guide/keras/distributed_training) - [Weight clustering in Keras example](https://www.tensorflow.org/model_optimization/guide/clustering/clustering_example) - [Pruning in Keras example](https://www.tensorflow.org/model_optimization/guide/pruning/pruning_with_keras) | - [Custom training loop with Keras and MultiWorkerMirroredStrategy](https://www.tensorflow.org/tutorials/distribute/multi_worker_with_ctl) - [Multi-worker training with Keras](https://www.tensorflow.org/tutorials/distribute/multi_worker_with_keras) - [Convolutional Variational Autoencoder](https://www.tensorflow.org/tutorials/generative/cvae) - [Deep Convolutional Generative Adversarial Network](https://www.tensorflow.org/tutorials/generative/dcgan) - [Save and load models](https://www.tensorflow.org/tutorials/keras/save_and_load) |\n\nThis is a dataset of 60,000 28x28 grayscale images of the 10 digits,\nalong with a test set of 10,000 images.\nMore info can be found at the\n[MNIST homepage](http://yann.lecun.com/exdb/mnist/).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|----------------------------------------------------------------------------|\n| `path` | path where to cache the dataset locally (relative to `~/.keras/datasets`). |\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)`. ||\n\n\u003cbr /\u003e\n\n**`x_train`** : `uint8` NumPy array of grayscale image data with shapes\n`(60000, 28, 28)`, containing the training data. Pixel values range\nfrom 0 to 255.\n\n**`y_train`** : `uint8` NumPy array of digit labels (integers in range 0-9)\nwith shape `(60000,)` for the training data.\n\n**`x_test`** : `uint8` NumPy array of grayscale image data with shapes\n`(10000, 28, 28)`, containing the test data. Pixel values range\nfrom 0 to 255.\n\n**`y_test`** : `uint8` NumPy array of digit labels (integers in range 0-9)\nwith shape `(10000,)` for the test data.\n\n#### Example:\n\n (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()\n assert x_train.shape == (60000, 28, 28)\n assert x_test.shape == (10000, 28, 28)\n assert y_train.shape == (60000,)\n assert y_test.shape == (10000,)\n\n#### License:\n\nYann LeCun and Corinna Cortes hold the copyright of MNIST dataset,\nwhich is a derivative work from original NIST datasets.\nMNIST dataset is made available under the terms of the\n[Creative Commons Attribution-Share Alike 3.0 license.](https://creativecommons.org/licenses/by-sa/3.0/)"]]
View source on GitHub