A library to work with complex number deep learning.
Project description
TF Complex Channels
TF complex channels contains a set of utility tools for working with complex numbers in a channel oriented way.
This approach is proposed and described in this blog post.
The primary purpose of this library and approach is to allow the community to push forward with academic research on complex number neural networks without waiting on ml library development.
Request for contributions
If an operation you want is not supported, please submit an issue or open a pull request
Basic Usage
import tf_complex_channels
print(x.dtype)
# > tf.complex64
print(x.shape)
# > (1, 2, 3)
x = complex_to_channels(x)
print(x.dtype)
# > tf.float64
print(x.shape)
# > (1, 2, 3, 2)
Documentation
Examples
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
Close
Hashes for tf_complex_channels-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 67441042459e0569297aadd50b918f7982129083eda07c8ee19956a7330ba5f2 |
|
MD5 | d7f3633d41b5c1c730dec0a759798597 |
|
BLAKE2b-256 | 2a4aa1f9fd502eef2c27c5ebe968aa860164bdeab67b9b351596c2d27f43f4a5 |