Giter Site home page Giter Site logo

chencodex / rnn_pytorch Goto Github PK

View Code? Open in Web Editor NEW
105.0 3.0 42.0 15 KB

Using the Pytorch to build an image temporal prediction model of the encoder-forecaster structure, ConvGRU kernel & ConvLSTM kernel

Python 100.00%
convlstm convgru pytorch rnn-pytorch encoder-decoder

rnn_pytorch's Introduction

RNN_Pytorch

使用pytorch框架搭建一个encoder-forecaster结构的图像时序预测模型,ConvGRU内核

##文件说明

BMSELoss.py 一个对不同降雨级别进行加权损失的loss函数。
ConvGRUCell.py 利用卷积操作实现的ConvGRU内核,单Cell
ConvLSTM.py 利用卷积操作实现的ConvLSTM内核,包含了单Cell,多层Cell的实现方式,以及一个实验用的RNN模型
encoder.py 序列编码结构
forecaster.py 序列预测结构
HKO_EF.py 尝试一个试验性质的训练方式
HKO_model.py HKO-7模型的搭建和训练
RNN.py 一般的RNN模型
RNN_train.py RNN模型的训练

##模型说明

本项目参考的HKO模型为论文  [Deep learning for precipitation nowcasting: A benchmark and a new model](http://papers.nips.cc/paper/7145-deep-learning-for-precipitation-nowcasting-a-benchmark-and-a-new-model)
encoder和forecaster 结构皆参照此论文编写
本文的数据样本原始大为20*1*477*477,训练过程中会缩放或随机切割到120*120大小。
原始数据为0-70之间的DBz值,在输入网络前已经映射到(0-255)/255.所以代码中的BMSELoss的阈值也经过了调整。

LICENSE

rnn_pytorch's People

Contributors

chencodex avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

rnn_pytorch's Issues

data的数据结构

您好,请问下train_arr, train_imgs_maps的数据结构分别是什么,谢谢

运行代码出现OOM问题

您好,我更改了卷积核的一些参数,放在GPU上面跑,出现了Out Of Memory问题,已经把数据量改小了,按理GPU也是够用的,找不到问题在哪儿。不知道您在运行代码的时候是否有这些问题?

关于forcaster的输入

您好,trajgru那篇论文里的emcoder-forecaster结构中,forecaster的所有时间步的输入是全0吗,还是说是这个时间步输入是上一个的时间步输出,我看您的代码实现好像是前者,可能我理解的不对,希望您解答一下,非常感谢。

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.