Git Product home page Git Product logo

multileveloptnn's Introduction

Multi-level Optimization for Neural Network

Workflow:

  1. define an old tf.Graph
  2. train the network with data with [train_load_net] function
  3. to expand a network, call [extract_weight] function, weights will be returned as numpy.ndarray
  4. call [Net2Net] functions to expand weights and layers
  5. define new tf.Graph
  6. call [train_load_net] to restart from a checkpoint with new graph and new weights

To be finished [LungNodule]:

  1. expand conv2 twice as wide
  2. add 1 more convolutional layer after conv3
  3. add skip layer (cautious)

Notice when using K40C GPU

  1. Default session will only allocate 512MB of GDDR. Add the following to your session:
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction= any 0~1 number)
    with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:

  2. Total GDDR of K40C is 10GB, call nvidia-smi to see memory allocation status first before run.

  3. Let us share memory by calculate how much memory is needed first and then change the factor in code,

multileveloptnn's People

Contributors

dirkxie avatar

Watchers

avatar avatar

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.