Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Window functions for patch aggregation

See original GitHub issue

🚀 Feature

Add the support to window functions as overlap_mode when aggregating patches with GridAggregator

Motivation

Windows functions, widely used in audio encoding, are good at reducing edge effects when aggregating a batch of overlapping patches. A the moment GridAggregator only support ‘crop’ and ‘average’ as overlap mode.

Pitch Have the possibility to choose as an overlapping mode a window function. I expect to write something like: tio.GridAggregator(sampler, overlap_mode='hann') Different types of window function can be implemented:

Hann window
Triangular window
Pyramidal window
Kaiser-Bessel window

Additional context Different window functions have been proven to be more effective than other modes to overlap patches: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0229839

Issue Analytics

State:
Created a year ago
Comments:5 (5 by maintainers)

Top GitHub Comments

1reaction

fepegarcommented, Jul 14, 2022

Apologies, I’ll review tomorrow!

0reactions

LucaLumetticommented, Jul 14, 2022

@fepegar Any comments on the PR?

Top Results From Across the Web

Window function calls | BigQuery - Google Cloud

A window function, also known as an analytic function, computes values over a group of rows and returns a single result for each...

Window functions

Window functions include variations on aggregate functions, like cumsum() and cummean() , functions for ranking and ordering, like rank() , and functions for ......

Introducing Window Functions in Spark SQL - Databricks

Aggregate functions, such as SUM or MAX , operate on a group of rows and calculate a single return value for every group....

Deep Multi-Patch Aggregation Network for ... - Xiaohui Shen

This paper investigates problems of image style, aes- thetics, and quality estimation, which require fine-grained details from high-resolution images, ...

Introducing Hann windows for reducing edge-effects in patch ...

The proposed window patch-based method is a refinement step that reduces the edge artefacts at patch borders. Inspired by signal processing, we ...