Git Product home page Git Product logo

depth_estimation_with_densenet-unet_hybrid's Introduction

Hybrid DenseNet-based CNN for Single Image Depth Estimation

This repository contains an updated version of the CNN from my repository DE_resnet_unet_hyb. The ResNet backbone has been replaced with a DenseNet169.

Requirements

The code was tested with:

  • python 3.5 and 3.6
  • pytorch (and torchvision) 1.3.0
  • opencv-python 3.4.3
  • matplotlib 2.2.3
  • numpy 1.15.4

Guide

  • Predicting the depth of an arbitrary image:
python3 predict_img.py -i <path_to_image>

Evalutation

  • Quantitative results on the NYU depth v2 test set:
REL RMSE Log10 δ1 δ2 δ3
0.129 0.588 0.056 0.833 0.962 0.990

depth_estimation_with_densenet-unet_hybrid's People

Contributors

karoly-hars 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.