Discrete Cosine Transform in PyTorch
Project description
DCT-Autoencoder
A PyTorch-based implementation of 2D Discrete Cosine Transform (DCT) autoencoder.
Overview
The dct-autoencoder package offers a PyTorch implementation of the 2D Discrete Cosine Transform (DCT), which is fully differentiable and can be integrated into deep learning models. It is particularly useful for reducing the spatial dimensions of images by transforming them into the frequency domain via DCT. Inspired by the JPEG algorithm, the package also includes a compression method using low-pass filtering, which reduces the number of frequency domain coefficients while retaining most of the image information.
Installation
Install the package via pip:
pip install dct-autoencoder
Usage
For detailed usage examples, refer to the Usage Notebook. It provides code snippets and demonstrations of the DCT autoencoder in action.
Visualizations
Computation Graph
The following figure illustrates the computation graph of the DCT autoencoder:
DCT Basis Functions
DCT basis functions for a block size of 16:
TODO
- Add support for color images
- Improve documentation
- Add unit tests
- Distribute package on PyPI
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file dct_autoencoder-0.3.0.tar.gz.
File metadata
- Download URL: dct_autoencoder-0.3.0.tar.gz
- Upload date:
- Size: 4.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.16 {"installer":{"name":"uv","version":"0.11.16","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b576fd3296ef29fff30c34907b08b54c10677fde1537b0522d5954d94a54ff1
|
|
| MD5 |
4d1616cd240771e831555f635309232e
|
|
| BLAKE2b-256 |
1f34629f913d6ec1109f4107e177499c11b94f537325a24161940fca9177c88d
|
File details
Details for the file dct_autoencoder-0.3.0-py3-none-any.whl.
File metadata
- Download URL: dct_autoencoder-0.3.0-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.16 {"installer":{"name":"uv","version":"0.11.16","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
75cc6c1b8d57e7cc76ab6bbf8b0b4358350e9c7bdbb08d2f3789a548c11f7cc7
|
|
| MD5 |
e865c89a5e3422df3fbfef795ca8b869
|
|
| BLAKE2b-256 |
59330a5e65b56b13417f95772a229c947441a29615d2218ff2c23921d9e7cb77
|
