Git Product home page Git Product logo

enas-tf2's Introduction

ENAS in Tensorflow2.0

Tensorflow2.0 implementation of Efficient Neural Architecture Search via Parameters Sharing.

TF1.* implementation (official code) can be taken from the link

Results

macro search

whole searching phase(300 epochs) needs ~5 hours with 1024 batch-size on Titan RTX 24G

if 256 batch-size, it needs ~10 hours

  • 1024 batch-size result:
    • train acc
    • eval acc

macro retrain

None

STILL DEVELOPING

  • macro search
  • not search_whole_channels
  • low GPU-util while searching(solution:increase batch-size)
  • micro search
  • BN infer case
  • fixed_arc training
  • aux_heads
  • lr_cosine
  • test data
  • multi gpu
  • save model weights

Prerequisites

  • python 3.5+
  • tensorflow2.0
  • matplotlib

Usage

macro

  • run main_macro.py directly

micro

None

Reference

enas-tf2's People

Contributors

liufg avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

Forkers

gong1337

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.