Skip to main content

The official implementation of MLP Mixer by Tolstikhin, Houlsby, Kolesnikov, Beyer et al.

Project description

MLP Mixer

The unofficial implementation of MLP Mixer by Tolstikhin, Houlsby, Kolesnikov, Beyer et all based on the official JAX implementation.

Installation

You can install this package using pip simply by running following command.

pip install mlpmixer

Usage

import torch
from mlpmixer import MLPMixer

images = torch.randn(1, 3, 224, 224)
classifier = MLPMixer(
        num_classes = 10,
        num_blocks = 5,
        hidden_dimension = 512,
        tokens_mlp_dimension = 128,
        channels_mlp_dimension = 128,
        patch_size = 16,
        image_size = 224
)

print(classifier(images))

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

image_mixer-0.0.1-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file image_mixer-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: image_mixer-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for image_mixer-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 84900adfa00beb207afc29a4abecdec56be613959839e278b96c1ea6ee6efc00
MD5 d0da08a93543fa00b7fee1ef4f481de9
BLAKE2b-256 04b49e21061a71a4215f65f0e61c840a9267581f17a24cc54cceb457b8270392

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page