Skip to main content

Tensorflow 2.0 implementation of Fourier Features mapping networks.

Project description

Tensorflow Fourier Feature Mapping Networks

Tensorflow 2.0 implementation of Fourier Feature Mapping networks from the paper Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains.

Installation

  • Pip install
$ pip install --upgrade tf_fourier_features
  • Pip install (test support)
$ pip install --upgrade tf_fourier_features[tests]

Usage

from tf_fourier_features import FourierFeatureProjection
from tf_fourier_features import FourierFeatureMLP

# You should use FourierFeatureProjection right after the input layer.
ip = tf.keras.layers.Input(shape=[2])
x = FourierFeatureProjection(gaussian_projection = 256, gaussian_scale = 1.0)(ip)
x = tf.keras.layers.Dense(256, activation='relu')(x)
x = tf.keras.layers.Dense(3, activation='sigmoid')(x)

model = tf.keras.Model(inputs=ip, outputs=x)

# Or directly use the model class to build a multi layer Fourier Feature Mapping Network
model = FourierFeatureMLP(units=256, final_units=3, final_activation='sigmoid', num_layers=4,
                          gaussian_projection=256, gaussian_scale=10.0)

Results on Image Inpainting task

A partial implementation of the image inpainting task is available as the train_inpainting_fourier.py and eval_inpainting_fourier.py scripts inside the scripts directory.

Weight files are made available in the repository under the Release tab of the project. Extract the weights and place the checkpoints folder at the scripts directory.

These weights generates the following output after 2000 epochs of training with batch size 8192 while using only 10% of the available pixels in the image during training phase.


If we train for using only 20% of the available pixels in the image during training phase -


If we train for using only 30% of the available pixels in the image during training phase - .

Citation

@misc{tancik2020fourier,
    title={Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains},
    author={Matthew Tancik and Pratul P. Srinivasan and Ben Mildenhall and Sara Fridovich-Keil and Nithin Raghavan and Utkarsh Singhal and Ravi Ramamoorthi and Jonathan T. Barron and Ren Ng},
    year={2020},
    eprint={2006.10739},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

Requirements

  • Tensorflow 2.0+
  • Matplotlib to visualize eval result

Project details


Download files

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

Source Distribution

tf_fourier_features-0.0.2.1.tar.gz (6.7 kB view details)

Uploaded Source

Built Distribution

tf_fourier_features-0.0.2.1-py2.py3-none-any.whl (6.2 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file tf_fourier_features-0.0.2.1.tar.gz.

File metadata

  • Download URL: tf_fourier_features-0.0.2.1.tar.gz
  • Upload date:
  • Size: 6.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3.post20200330 requests-toolbelt/0.9.1 tqdm/4.44.1 CPython/3.7.4

File hashes

Hashes for tf_fourier_features-0.0.2.1.tar.gz
Algorithm Hash digest
SHA256 8dd78055117ee3164c611b7b7110dc66f2d6b755f93dcef3ee89a5ed0417f09c
MD5 131d848fc631b8ef42f01cd6e8ed86ae
BLAKE2b-256 63155456dbac22fdef24a4ffc76e51c92fa7a26624bed43dcc58df35f1080d71

See more details on using hashes here.

File details

Details for the file tf_fourier_features-0.0.2.1-py2.py3-none-any.whl.

File metadata

  • Download URL: tf_fourier_features-0.0.2.1-py2.py3-none-any.whl
  • Upload date:
  • Size: 6.2 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3.post20200330 requests-toolbelt/0.9.1 tqdm/4.44.1 CPython/3.7.4

File hashes

Hashes for tf_fourier_features-0.0.2.1-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 6691b415c5e2b85c65e198c03bb3aa1a5f3897339b15ec557f8999a023e2d98a
MD5 e10e1d46be189b840b02642c01cf8a8a
BLAKE2b-256 a1d0e5e907b7680a2f79c90f6a41ae1d744c358e254ee5bbfea45f1b1960cf01

See more details on using hashes here.

Supported by

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