TFDWT: Fast Discrete Wavelet Transform TensorFlow Layers

Fast $1\text{D}$, $2\text{D}$ and $3\text{D}$ Discrete Wavelet Transform ($\text{DWT}$) and Inverse Discrete Wavelet Transform ($\text{IDWT}$) layers for backpropagation networks.

Available wavelet families ―

        Haar (haar)
        Daubechies (db)
        Symlets (sym)
        Coiflets (coif)
        Biorthogonal (bior)
        Reverse biorthogonal (rbio)

Note ― Shape requirements

• Single‑level: dimensions must be even. For 1D, N is even; for 2D and 3D, each side is even and the input is square/cubic respectively.
• Multilevel (L levels): each side must be divisible by $2^L$. In practice, pad to the nearest multiple of $2^L$ when needed.
• Our examples and tests center‑pad rather than crop, to preserve data.

---

Installation guide

The installation of the TFDWT package is recommended inside a virtual environment with tensorflow[and-cuda] installed at first.

Pre-installation checks (Tested in Gentoo and Debian bookworm)

• Create a new virtual enironment with a specific Python version (use the Python version supported by TensorFlow)

conda info --envs
env_name='tf219'
conda create -n $env_name python=3.12 ipykernel

# activate virtual environment
conda activate tf219

• Install TensorFlow using official guide in https://www.tensorflow.org/install/pip

# For GPU users
pip install tensorflow[and-cuda]
# Verify setup
python3 -c "import tensorflow as tf; print(f'{tf.config.list_physical_devices('GPU')}, \nTF version {tf.__version__}')"

Install TFDWT from PyPI (Option $1$)

pip install TFDWT

Install TFDWT from Github (Option $2$)

Download the package

git clone https://github.com/kkt-ee/TFDWT.git

Change directory to the downloaded TFDWT 

cd TFDWT

Run the following command to install the TFDWT package

pip install .

---

Verify installation

Compute $\text{DWT}$ $1\text{D}$ and $\text{IDWT}$ $1\text{D}$ of batched, multichannel $x$ of shape $(\text{batch, length, channels})$

"""Perfect Reconstruction 1D DWT level-1 Filter bank"""
from TFDWT.DWT1DFB import DWT1D, IDWT1D

LH = DWT1D(wave='bior3.1')(x)       # Analysis
x_hat = IDWT1D(wave='bior3.1')(LH)  # Synthesis

Compute $\text{DWT}$ $2\text{D}$ and $\text{IDWT}$ $2\text{D}$ of batched, multichannel $x$ of shape $(\text{batch, height, width, channels})$

"""Perfect Reconstruction 2D DWT level-1 Filter bank"""
from TFDWT.DWT2DFB import DWT2D, IDWT2D

LLLHHLHH = DWT2D(wave='bior1.3')(x)        # Analysis
x_hat = IDWT2D(wave='bior1.3')(LLLHHLHH)   # Synthesis
# `wave` can be any supported orthogonal or biorthogonal wavelet

Compute $\text{DWT}$ $3\text{D}$ and $\text{IDWT}$ $3\text{D}$ of batched, multichannel $x$ of shape $(\text{batch, height, width, depth, channels})$

"""Perfect Reconstruction 3D DWT level-1 Filter bank"""
from TFDWT.DWT3DFB import DWT3D, IDWT3D

LLLLLHLHLLHHHLLHLHHHLHHH = DWT3D(wave='bior1.3')(x)        # Analysis
x_hat = IDWT3D(wave='bior1.3')(LLLLLHLHLLHHHLLHLHHHLHHH)   # Synthesis
# `wave` can be any supported orthogonal or biorthogonal wavelet

NOTE ― Using the above forward and inverse transforms the above $\text{DWT}$ and $\text{IDWT}$ layers can be used to construct multilevel $\text{DWT}$ filter banks and $\text{Wave Packet Transform}$ filter banks.

Multilevel helpers (convenience API)

The package also provides simple helpers for building multilevel pyramids using the single‑level layers internally.

1D

from TFDWT.multilevel.dwt import dwt, idwt

level = 3
subbands = dwt(x, level=level, Ψ='haar')   # returns [H1, H2, ..., HL, LL]
x_hat    = idwt(subbands, level=level, Ψ='haar')

2D

from TFDWT.multilevel.dwt2 import dwt2, idwt2

level = 3
subbands = dwt2(x, level=level, Ψ='haar')  # [H1, H2, ..., HL, LL]
x_hat    = idwt2(subbands, level=level, Ψ='haar')

3D

from TFDWT.multilevel.dwt3 import dwt3, idwt3

level = 3
subbands = dwt3(x, level=level, Ψ='haar')  # [H1, H2, ..., HL, LL]
x_hat    = idwt3(subbands, level=level, Ψ='haar')

Each Hi contains all high‑pass subbands at level i (1 for 1D, 3 for 2D, 7 for 3D), concatenated along the channel axis; the last element is the final low‑pass LL.

---

Package is tested with dependency versions

        Python 3.12.7
        TensorFlow 2.15+ (verified on 2.21.0)
        Keras 2 and 3
        CUDA 12+

---

Uninstall TFDWT

pip uninstall TFDWT

---

TFDWT (C) 2026 Kishore Kumar Tarafdar, भारत 🇮🇳