Code Monkey home page Code Monkey logo

keras_tta's Introduction

keras_tta's People

Contributors

tsterbak avatar

Stargazers

 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

keras_tta's Issues

How to modify the test time augmentation wrapper for a RGB mask

When I run the code using RGB masks, I get the following error:

ValueError: Exception encountered when calling layer "model_2" (type Functional).
    
    Input 0 of layer "block1_conv1" is incompatible with the layer: expected axis -1of input shape to have value 3, but received input with shape (None, 256, 256, 1)
    
    Call arguments received:
      โ€ข inputs=tf.Tensor(shape=(None, 256, 256, 1), dtype=float32)
      โ€ข training=False
      โ€ข mask=None

TTA clarify

please clear me TTA concept for segmentation.

lets see i have one test image, then apply flip left,flip right augmentation during testing.
I pass those three images [original,flip-left,flip-right] to model for prediction .
I will get three outputs , after that i have to directly average those prediction or take reverse of augmentation[ i.e again reverse the flipped images to original] and then average the prediction.

please clarify whats the way to merge prediction ?

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.