PIX

PIX is an image processing library in JAX, for JAX.

Overview

JAX is a library resulting from the union of Autograd and XLA for high-performance machine learning research. It provides NumPy, SciPy, automatic differentiation and first-class GPU/TPU support.

PIX is a library built on top of JAX with the goal of providing image processing functions and tools to JAX in a way that they can be optimised and parallelised through jax.jit, jax.vmap and jax.pmap.

Installation

PIX is written in pure Python, but depends on C++ code via JAX.

Because JAX installation is different depending on your CUDA version, PIX does not list JAX as a dependency in requirements.txt, although it is technically listed for reference, but commented.

First, follow JAX installation instructions to install JAX with the relevant accelerator support.

Then, install PIX using pip:

pip install dm-pix

API Documentation

• Augmentations
  • adjust_brightness
  • adjust_contrast
  • adjust_gamma
  • adjust_hue
  • adjust_saturation
  • affine_transform
  • center_crop
  • elastic_deformation
  • flip_left_right
  • flip_up_down
  • gaussian_blur
  • pad_to_size
  • random_brightness
  • random_contrast
  • random_crop
  • random_flip_left_right
  • random_flip_up_down
  • random_gamma
  • random_hue
  • random_saturation
  • resize_with_crop_or_pad
  • rotate
  • rot90
  • solarize
• Color conversions
  • hsl_to_rgb
  • hsv_to_rgb
  • rgb_to_hsl
  • rgb_to_hsv
  • rgb_to_grayscale
• Depth and space transformations
  • depth_to_space
  • space_to_depth
• Interpolation functions
  • flat_nd_linear_interpolate
  • flat_nd_linear_interpolate_constant
• Metrics
  • mae
  • mse
  • psnr
  • rmse
  • simse
  • ssim
• Patch extraction functions
  • extract_patches

Contribute

• Issue tracker

• Source code

Support

If you are having issues, please let us know by filing an issue on our issue tracker.

License

PIX is licensed under the Apache 2.0 License.

Indices and Tables

• Index