Baike.dev
All toolsOnline toolsAI codingTrendingOpen sourceNewsSubmit
Log in
< Back to tools
K

keras-spp

> 编程语言
Open source

Spatial pyramid pooling layers for keras

392 stars0 likes0 views
WebsiteGitHub

About

Spatial pyramid pooling layers for keras

keras-spp

Spatial pyramid pooling layers for keras, based on https://arxiv.org/abs/1406.4729 . This code requires Keras version 2.0 or greater.

(Image credit: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, K. He, X. Zhang, S. Ren, J. Sun)

Three types of pooling layers are currently available:

  • SpatialPyramidPooling: apply the pooling procedure on the entire image, given an image batch. This is especially useful if the image input can have varying dimensions, but needs to be fed to a fully connected layer.

For example, this trains a network on images of both 32x32 and 64x64 size:

…
  • RoiPooling: extract multiple rois from a single image. In roi pooling, the spatial pyramid pooling is applied at the specified subregions of the image. This is useful for object detection, and is used in fast-RCNN and faster-RCNN. Note that the batch_size is limited to 1 currently.
…
  • RoiPoolingConv: like RoiPooling, but maintains spatial information.

  • Thank you to @jlhbaseball15 for his contribution

Issues· 0 open

View all issuesOpen on GitHub

No open issues yet, or sync has not completed.

> Tags

Pythonkeraskeras-layer

No comments yet. Be the first to share.

> Details

PublishedAug 1, 2026
UpdatedSep 17, 2026
Category编程语言
PricingOpen source

> Related tools

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言