SKNet
Convolutional network
Implementation of a deep learning model that combines convolutional neural networks with selective kernel networks for image recognition tasks.
Code for our CVPR 2019 paper: Selective Kernel Networks; See zhihu：https://zhuanlan.zhihu.com/p/59690223
593 stars
9 watching
106 forks
Language: C++
last commit: over 5 years ago
Linked from 1 awesome list
cnnselective-kernel-networkssknet
weiaicunzai/awesome-image-classificationRelated projects:
| Repository | Description | Stars |
|---|---|---|
 bruinxiong/modified-crunet-and-residual-attention-network.mxnet | An MXNet implementation of a modified deep neural network architecture for image classification | 67 |
 preritj/segmentation | Deep learning models for semantic segmentation of images | 100 |
 jihongju/keras-fcn | A library implementing a Fully Convolutional Network architecture with Keras support | 202 |
 rcmalli/keras-squeezenet | An implementation of the SqueezeNet neural network model in the Keras framework | 404 |
 cszn/srmd | Develops a single convolutional network to handle various image degradations with improved scalability and efficiency | 426 |
 theduynguyen/keras-fcn | An implementation of fully convolutional neural networks for semantic segmentation using TensorFlow as the backend. | 15 |
 charlotte-pel/temporalcnn | A deep learning-based approach to classifying satellite image time series using convolutional neural networks. | 149 |
 deepakkumar1984/mxnet.sharp | A .NET Standard library providing C# bindings for the Apache MXNet deep learning framework | 149 |
 shichenliu/condensenet | An efficient CNN architecture for mobile devices with learned group convolutions and dense connectivity | 694 |
 benedekrozemberczki/sgcn | An implementation of a deep learning algorithm for graph data | 268 |
 tyill/sunnet | A lightweight C++ deep learning library for building and training neural networks. | 61 |
 xternalz/sdpoint | A deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency. | 18 |
| cszn/ircnn | This project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods. | 600 |
 wkentaro/fcn | An implementation of fully convolutional networks in Chainer, a deep learning framework. | 218 |
 xuzhenqi/cnn | Provides an implementation of convolutional neural networks in MATLAB. | 95 |