blended-tiling-numpy 0.0.1.dev7

Blended tiling with Numpy

blended-tiling-numpy

This library is adapted from https://github.com/ProGamerGov/blended-tiling to work with numpy arrays. All credit for design goes to Ben Egan. Basic functionality works, but there may be edge errors.

This library adds support for splitting NCHW tensor inputs like images & activations into overlapping tiles of equal size, and then blending those overlapping tiles together after they have been altered.

This tiling solution is intended for situations where one wishes to render / generate outputs that are larger than what their computing device can support. Tiles can be separately rendered and periodically blended together to maintain tile feature coherence.

Setup:

Installation Requirements

• Python >= 3.6
• Numpy

Installation via pip:

pip install blended-tiling-numpy

Dev / Manual install:

git clone https://github.com/rymuelle/blended-tiling-numpy
cd blended-tiling-numpy
pip install -e .

# Notebook installs also require appending to environment variables
# import sys
# sys.path.append('/content/blended-tiling-numpy')

Documentation

TilingModule

The base blended tiling module.

blended_tiling_numpy.TilingModule(tile_size=(224, 224), tile_overlap=(0.25, 0.25), base_size=(512, 512))

Initialization Variables

• tile_size (int or tuple of int): The size of tiles to use. A single integer to use for both the height and width dimensions, or a list / tuple of dimensions with a shape of: [height, width]. The chosen tile sizes should be less than or equal to the sizes of the full NCHW tensor (base_size).
• tile_overlap (int or tuple of int): The amount of overlap to use when creating tiles. A single integer to use for both the height and width dimensions, or a list / tuple of dimensions with a shape of: [height, width]. The chosen overlap percentages should be in the range [0.0, 0.50] (0% - 50%).
• base_size (int or tuple of int): The size of the NCHW tensor being split into tiles. A single integer to use for both the height and width dimensions, or a list / tuple of dimensions with a shape of: [height, width].