CapsNet and CapsNet-pytorch
These are **competitor implementations** of the same foundational CapsNet architecture—both are independent recreations of Hinton's Dynamic Routing Between Capsules paper in different deep learning frameworks (TensorFlow and PyTorch respectively), serving the same purpose with no interdependencies.
About CapsNet
loretoparisi/CapsNet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art
This project offers a collection of implementations and resources for Capsule Networks (CapsNets), a type of neural network capable of recognizing objects more effectively than traditional Convolutional Neural Networks, especially in complex scenarios. It takes image data as input and outputs highly accurate object classifications, even when objects overlap. Data scientists and machine learning researchers exploring advanced computer vision techniques would use this project.
About CapsNet-pytorch
adambielski/CapsNet-pytorch
PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules
This project offers a PyTorch implementation for the 'Dynamic Routing Between Capsules' neural network architecture, enabling researchers to explore advanced image recognition. It takes raw image data, like the MNIST dataset, and outputs classifications and detailed visualizations of how the network 'sees' and reconstructs digits. Machine learning researchers and academics specializing in computer vision will find this useful for experimenting with capsule networks.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work