Giter Club home page Giter Club logo

caffe-mobilenet-v3's Introduction

caffe-mobilenet-v3

Introduction

This is a personal Caffe implementation of MobileNetV3. For details, please read the original papers: Searching for MobileNetV3.

How to use

  1. Requirements for Caffe (see: Caffe installation instructions)
  2. Add new caffe layers and rebuild the caffe:
  3. Run test
    CPU:
    $CAFFE_ROOT/build/tools/caffe time -model mobilenet_v3_large_1.0.prototxt
    GPU:
    $CAFFE_ROOT/build/tools/caffe time -model mobilenet_v3_large_1.0.prototxt -gpu 0

Performance on MobileNetV3

Backbone CPU-Forward CPU-Backward GPU-Forward GPU-Backward
V3-Large 1.0 134.55 ms 140.23 ms 15.44 ms 21.79 ms
V3-Small 1.0 58.64 ms 59.30 ms 11.49 ms 12.58 ms

TODO

  • More MobileNetV3 architectures.
  • Traning & validation.

caffe-mobilenet-v3's People

Contributors

jixing0415 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  avatar  avatar  avatar

caffe-mobilenet-v3's Issues

mobilenet v3 trian

Why did you use relu6 instead of relu after scale layer in blocks?I think the paper used relu.How many batches when you train? Can you release your train.prorotxt and solver.prototxt?I can't reproduce your result.Thank you!

pretrained model

Hello, could you please upload the pretrained MobileNet v3 models on ImageNet dataset? Thanks a lot!

Why the loss stayed the same value?

I have tried this model on binary classification, but the loss is same (value 0.693147) all the time. I am sure the data is right, and have tried other depthwise conv, relu6 and bn parameter also. All methods can't work. It really works???

How can I train my own data?

Hi,
I am wonder how can I train my own data, I think mobilenet_v3_small_1.0.prototxt is the deploy prototxt not train.prototxt?

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.