Giter Club home page Giter Club logo

ir-redo's Introduction

IR final project

This section deals with the use of the list loss function to train a neural net to generate an embedding of images. The embedding of images is thus used to idenitfy images that are similar for image search purposes

Step 1: Pre train on tiny-imagenet

run the scripts in train_tiny_scripts to generate an initial model that learns "shape" features and such to distinguish between natural images

Step 2: Train on medical images

run train_med_scripts to run training on the medical image dataset. Should provide a prevState variable to the bash scripts pointing to the last checkpoitn of step 1

Step 3. Generate embeddigns

Run bash script that loads model from step2 and generates embeddings of the data in the embeddigns folder

Step 4: evaluation

TODO 1. MAP across categories 2. gradCAM visualization of activation layers 3. TSNE plots of embedding space?

ir-redo's People

Watchers

 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.