All Projects → xylcbd → Easycnn

xylcbd / Easycnn

easy convolution neural network

Projects that are alternatives of or similar to Easycnn

Komputation
Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.
Stars: ✭ 295 (+116.91%)
Mutual labels:  framework, convolutional-neural-networks
Miscnn
A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
Stars: ✭ 194 (+42.65%)
Mutual labels:  framework, convolutional-neural-networks
Cyclejs.cn
The Cycle.js Chinese documentation website.
Stars: ✭ 132 (-2.94%)
Mutual labels:  framework
Portfolio Generator
JS framework to dynamically generate a portfolio site from a JSON file
Stars: ✭ 135 (-0.74%)
Mutual labels:  framework
Chainer Cifar10
Various CNN models for CIFAR10 with Chainer
Stars: ✭ 134 (-1.47%)
Mutual labels:  convolutional-neural-networks
Lsoftmax Pytorch
The Pytorch Implementation of L-Softmax
Stars: ✭ 133 (-2.21%)
Mutual labels:  convolutional-neural-networks
Bolt Js
A framework to build Slack apps using JavaScript
Stars: ✭ 1,971 (+1349.26%)
Mutual labels:  framework
Parlour
A package of UI extensions, components and improvements for Unity's UI frameworks.
Stars: ✭ 132 (-2.94%)
Mutual labels:  framework
Deep Steganography
Hiding Images within other images using Deep Learning
Stars: ✭ 136 (+0%)
Mutual labels:  convolutional-neural-networks
Imagenet
Pytorch Imagenet Models Example + Transfer Learning (and fine-tuning)
Stars: ✭ 134 (-1.47%)
Mutual labels:  convolutional-neural-networks
Mrcnn Scene Recognition
MR-CNNs for Large-Scale Scene Recognition
Stars: ✭ 135 (-0.74%)
Mutual labels:  convolutional-neural-networks
Intelegent lock
lock mechanism with face recognition and liveness detection
Stars: ✭ 134 (-1.47%)
Mutual labels:  convolutional-neural-networks
Deep Learning With Pytorch Tutorials
深度学习与PyTorch入门实战视频教程 配套源代码和PPT
Stars: ✭ 1,986 (+1360.29%)
Mutual labels:  convolutional-neural-networks
October
Self-hosted CMS platform based on the Laravel PHP Framework.
Stars: ✭ 10,740 (+7797.06%)
Mutual labels:  framework
Wookiee
Scala based lightweight service framework using akka and other popular technologies.
Stars: ✭ 132 (-2.94%)
Mutual labels:  framework
Muta
Muta is a high-performance blockchain framework.
Stars: ✭ 135 (-0.74%)
Mutual labels:  framework
Visualizingcnn
🙈A PyTorch implementation of the paper "Visualizing and Understanding Convolutional Networks." (ECCV 2014)
Stars: ✭ 132 (-2.94%)
Mutual labels:  convolutional-neural-networks
Dedsploit
Network protocol auditing framework
Stars: ✭ 133 (-2.21%)
Mutual labels:  framework
Hadron
⚛️Framework for building a testable, modular backend with a dependency injection pattern in plain JavaScript.
Stars: ✭ 135 (-0.74%)
Mutual labels:  framework
Http
An opinionated framework for scalable web 🌎
Stars: ✭ 136 (+0%)
Mutual labels:  framework

EasyCNN

Easy convolution neural network framework.

small, clean, easy to understand!

QQ群:603891505

blog about EasyCNN in Chinese.

port tensorflow model to easycnn model

Features

  • All in one: without any dependency, pure c++ implemented.
  • Basic layer: data layer, convolution layer, pooling layer, full connect layer, softmax layer, activation layers(sigmod, tanh, RELU)
  • Loss function: Cross Entropy, MSE.
  • Optimize method: SGD, SGDWithMomentum.
  • Multi-thread parallel optimized.
  • Tensorflow model support (traditional CNN only now).(link)

Examples

Todo List

  • fix train error when batch > 1 issue.
  • add load & save model function.
  • add more layer, such as batch normalization layer, dropout layer, etc.
  • add weight regular.
  • port to other platforms, such as linux, mac, android, iOS, etc.
  • optimize network train/test speed, use cuBLAS/OpenBLAS etc.
  • add more optimize method.
  • add unit test.
  • add license.

Bug Report

Use github issues please.

Pull Request

Pull request is welcome.

License

This project is released under the WTFPL LICENSE.

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].