All Projects → wang-chen → kervolution

wang-chen / kervolution

Licence: GPL-3.0 License
Kervolution Library in PyTorch (CVPR 2019 Oral)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to kervolution

Handwritten-Digits-Classification-Using-KNN-Multiclass Perceptron-SVM
🏆 A Comparative Study on Handwritten Digits Recognition using Classifiers like K-Nearest Neighbours (K-NN), Multiclass Perceptron/Artificial Neural Network (ANN) and Support Vector Machine (SVM) discussing the pros and cons of each algorithm and providing the comparison results in terms of accuracy and efficiecy of each algorithm.
Stars: ✭ 42 (+27.27%)
Mutual labels:  knn
ml
经典机器学习算法的极简实现
Stars: ✭ 130 (+293.94%)
Mutual labels:  knn
Audio-Classification-using-CNN-MLP
Multi class audio classification using Deep Learning (MLP, CNN): The objective of this project is to build a multi class classifier to identify sound of a bee, cricket or noise.
Stars: ✭ 36 (+9.09%)
Mutual labels:  cnn
deforestation
A machine learning exercise, using KNN to classify deforested areas
Stars: ✭ 26 (-21.21%)
Mutual labels:  knn
knn-cpp
A header-only C++ library for k nearest neighbor search with Eigen3.
Stars: ✭ 25 (-24.24%)
Mutual labels:  knn
Breast-Cancer-Scikitlearn
simple tutorial on Machine Learning with Scikitlearn
Stars: ✭ 33 (+0%)
Mutual labels:  knn
MSF
Official code for "Mean Shift for Self-Supervised Learning"
Stars: ✭ 42 (+27.27%)
Mutual labels:  knn
WSCNNTDSaliency
[BMVC17] Weakly Supervised Saliency Detection with A Category-Driven Map Generator
Stars: ✭ 19 (-42.42%)
Mutual labels:  cnn
facenet-darknet-inference
Face recognition using facenet
Stars: ✭ 29 (-12.12%)
Mutual labels:  knn
finetuneAlexVGG
Finetune ConvNets with Tensorflow
Stars: ✭ 20 (-39.39%)
Mutual labels:  cnn
MachineLearning
机器学习教程,本教程包含基于numpy、sklearn与tensorflow机器学习,也会包含利用spark、flink加快模型训练等用法。本着能够较全的引导读者入门机器学习。
Stars: ✭ 23 (-30.3%)
Mutual labels:  knn
KernelKnn
Kernel k Nearest Neighbors in R
Stars: ✭ 14 (-57.58%)
Mutual labels:  knn
CS231n
My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 30 (-9.09%)
Mutual labels:  knn
fastknn
Fast k-Nearest Neighbors Classifier for Large Datasets
Stars: ✭ 64 (+93.94%)
Mutual labels:  knn
stylenet
A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"
Stars: ✭ 58 (+75.76%)
Mutual labels:  cnn
Clustering-Python
Python Clustering Algorithms
Stars: ✭ 23 (-30.3%)
Mutual labels:  knn
NIDS-Intrusion-Detection
Simple Implementation of Network Intrusion Detection System. KddCup'99 Data set is used for this project. kdd_cup_10_percent is used for training test. correct set is used for test. PCA is used for dimension reduction. SVM and KNN supervised algorithms are the classification algorithms of project. Accuracy : %83.5 For SVM , %80 For KNN
Stars: ✭ 45 (+36.36%)
Mutual labels:  knn
mods-light-zmq
MODS with external deep descriptors/detectors
Stars: ✭ 46 (+39.39%)
Mutual labels:  cnn
DLSS
Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.
Stars: ✭ 88 (+166.67%)
Mutual labels:  cnn
Awesome-Scripts
A collection of awesome scripts from developers around the globe.
Stars: ✭ 135 (+309.09%)
Mutual labels:  knn

kervolution

Kervolution Library in PyTorch

Usage

It is suggested to add this repo as a submodule in your project.

git submodule add https://github.com/wang-chen/kervolution [target folder]

Then you can replace nn.Conv by nn.Kerv directly in you python script.

You may also need the following commands.

git submodule init
git submodule update

Citation

@inproceedings{wang2019kervolutional,
  title={Kervolutional Neural Networks},
  author={Wang, Chen and Yang, Jianfei and Xie, Lihua and Yuan, Junsong},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={31--40},
  year={2019}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].