Giter Site home page Giter Site logo

snehasinghania / stresnet Goto Github PK

View Code? Open in Web Editor NEW
105.0 4.0 46.0 1.6 MB

A TensorFlow Implementation of Deep Spatio-Temporal Residual Networks (ST-ResNet): https://arxiv.org/abs/1610.00081

Python 100.00%
spatio-temporal-prediction tensorflow deep-learning

stresnet's People

Contributors

snehasinghania 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  avatar

stresnet's Issues

Weather data

I can not find the weather data and corresponding source codes.
However, the weather data is contained in the original paper.

reproduce the results

Hi Senhasinghuania,

Thanks for you work. Have you ever run the code with dataset used in the original paper and replicate the results?

Thanks
Lei

数据集在哪里寻找?

  老师,您好!想请问您一下,关于ST-ResNet网络的论文《Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction》中提到的两个数据集TaxiBJ和BikeNYC在哪里下载?期待您的早日回复,万分感谢!  

'outputs' is not used in moduls.py at line 23

'outputs' is not used in moduls.py at line 23

# perform a 2D convolution
outputs = tf.layers.conv2d(outputs, filters, kernel_size, strides, padding="SAME", name="conv1", reuse=reuse)          
# use layernorm before applying convolution
outputs = tf.contrib.layers.layer_norm(inputs, scope="layernorm2", reuse=reuse)

Should we replace 'inputs' with 'outputs' at line 25?

Wrong type of multiplication in function Fusion,

Hello,

I was using this code as inspiration as I am building my own, to see what functions and keras libraries to use. When multiplying close_output with the weights matrix, you used matmul which is a standard matrix multiplication when the paper used 'Hadamard product (i.e., element-wise multiplication)'.

I believe tf.keras.layers.Multiply should be used intead.

Thank you for providing this code and I hope this helps :)

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.