TensorFlow utilities for complex neural networks.
Project description
tf-complex
This package was inspired by the work of Elizabeth Cole et al.: Image Reconstruction using an Unrolled DL Architecture including Complex-Valued Convolution and Activation Functions. Please cite their work appropriately if you use this package. The code for their work is available here.
Installation
You can install tf-complex
using pypi:
pip install tf-complex
Example use
You can define a complex convolution in the following way to use in one of your models:
from tf_complex.convolutions import ComplexConv2D
conv = ComplexConv2D(
16,
3,
padding='same',
activation='crelu',
)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tf-complex-0.0.2.tar.gz
(4.8 kB
view details)
Built Distribution
File details
Details for the file tf-complex-0.0.2.tar.gz
.
File metadata
- Download URL: tf-complex-0.0.2.tar.gz
- Upload date:
- Size: 4.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.6.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b5d081203ad88e22d893f9d7a7a63a37c36b26b5eda5a3b2d7425886c5145302 |
|
MD5 | 5b3ef983268dec46b3c3a3f761a6ccb3 |
|
BLAKE2b-256 | b0f62ab5e03c98cb7c5c0e061cb3a5e742a7a9c72e117ea4dbdf43ee1b497394 |
File details
Details for the file tf_complex-0.0.2-py3-none-any.whl
.
File metadata
- Download URL: tf_complex-0.0.2-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.6.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b7a9664e619e7891d21d944894dc83ba00eebc3d74f6ecfaf0f8f8a272276afc |
|
MD5 | aab0b62509936f88e7b6e47dec44438b |
|
BLAKE2b-256 | 890b9bb48887196204a30f7e5d1c07a7449e78a9992fd5e0de49e1d3dc2bf7a6 |