Git Product home page Git Product logo

cnn-rnn's Introduction

CNN-RNN

Tensorflow based implementation of convolution-reccurent network for classification of human interactions on video.
Uses SDHA 2010 High-level Human Interaction Recognition Challenge dataset.

Requirements

  • Python 3.5.2
  • Tensorflow > 1.0
  • Python OpenCV > 3.0

Evaluation

Example:

python main.py --lrate 0.001 --update
Parameter Default value Description
epoch 1 Number of epoch
esize 50 Size of examples
estep 20 Length of step for grouping frames into examples
height 240 Height of frames
width 320 Width of frames
lrate 1e-4 Learning rate
logdir network/logs Path to store logs and checkpoints
conv standard Type of CNN block (inception/vgg16)
rnn GRU Type of RNN block (LSTM/GRU)
update False Re-Generate TFRecords
download False Download dataset
restore False Restore from previous checkpoint
test False Test evaluation

cnn-rnn's People

Contributors

donfaq avatar

Watchers

James Cloos avatar queenie avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.