tiler 0.0.1

N-dimensional tiling and merging library

tiler

Work in progress!

This packages provides tools for N-dimensional tiling (patch extraction) and subsequent merging with tapering (window) functions.

This is especially helpful for semantic segmentation tasks in deep learning, where we often have to work with images that do not fit into GPU memory (2D hyperspectral satellite images, 3D tomographic data, whole slide images etc.).

Implemented features

• Data reader agnostic: works with numpy arrays
• Optimized to avoid unnecessary memory copies: numpy views for all tiles, except border tiles that require padding
• N-dimensional array tiling (but for now tiles must have the same number of dimensions as the array)
• Supports channel dimension: dimension that will not be tiled
• Overlapping support: you can specify tile percentage overlap or the overlap size
• Access individual tiles with consistent indexing or with convenience iterator
• Merging tiles back into full array: optional un-padding to original shape
• Merging supports scipy window functions

Roadmap

• Tests
• Add border windows generation (like in Pielawski et. al - see references))
• More examples
• Implement windows functions and remove scipy dependency (we need only a couple of functions that generate windows)
• PyTorch Dataset class convenience wrapper?
• Arbitrary sized tiles (m-dim window over n-dim array, m <= n)?
  • Some leads here
• Optional augmentation modes for smoother segmentations?
  • D4 rotation group
  • Mirroring
• Benchmark with plain for loops, determine overhead

Installation

The latest release is available through pip:

pip install tiler 

Alternatively, you can clone the repository and install it manually:

git clone [e-mail]:the-lay/tiler.git
cd tiler
pip install .

Examples

For now, only the one examples/tiler_example.py

Motivation & other tiling/patching libraries

I work on semantic segmentation of patched 3D data and I often found myself reusing tiling functions that I wrote for previous projects. No existing libraries listed below fit my use case, so that's why I wrote tiler.

However, there are other libraries that might fit you better:

• vfdev-5/ImageTilingUtils

  • Minimalistic image reader agnostic 2D tiling tools

• BloodAxe/pytorch-toolbelt

  • Powerful PyTorch toolset that has 2D image tiling and on-GPU merger

• Vooban/Smoothly-Blend-Image-Patches

  • Mirroring and D4 rotations data (8-fold) augmentation with squared spline window function for 2D images

• samdobson/image_slicer

  • Slicing and merging 2D image into N equally sized tiles

• Do you know any other libraries?

  • Please make a PR
  • or open a new issue.

References

Introducing Hann windows for reducing edge-effects in patch-based image segmentation, Pielawski and Wählby, March 2020