A PyTorch implementation of Spatial and Temporal Pyramid Pooling

# Pyramid Pooling implemented in PyTorch

This Module implements Spatial Pyramid Pooling (SPP) and Temporal Pyramid Pooling (TPP) as described in different papers.

NOTE This repo has been forked from Revidee's original (which seems to no longer be under maintenance) to publish on Pypi. I (Eric Musa) take no credit for writing the Pyramid Pooling code, but could not find any information on Revidee to provide proper credit.

# The purpose of this fork is to continue maintenance of this package and post on Pypi

## Temporal Pyramid Pooling:

Sudholt, Fink: Evaluating Word String Embeddings and LossFunctions for CNN-based Word Spotting

### Principle

Given an 2D input Tensor, Temporal Pyramid Pooling divides the input in x stripes which extend through the height of the image and width of roughly (input_width / x). These stripes are then each pooled with max- or avg-pooling to calculate the output.

## Spatial Pyramid Pooling:

He, et. al.: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

### Principle

Given an 2D input Tensor, Spatial Pyramid Pooling divides the input in rectangles with height of roughly (input_height / x) and width of roughly (input_width / x). These rectangles are then each pooled with max- or avg-pooling to calculate the output.

## Project details

Uploaded source
Uploaded py3