Coder Social home page Coder Social logo

sgraine / point-label-aware-superpixels Goto Github PK

View Code? Open in Web Editor NEW
4.0 2.0 0.0 112 KB

This repository contains the code implementation used in the paper: "Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery"

License: GNU General Public License v3.0

Python 100.00%
deep-learning label-propagation multi-species pytorch remote-sensing superpixels underwater-images underwater-robotics coral-segmentation ground-truth-augmentation

point-label-aware-superpixels's Issues

Better variable names

Find a better name for flag (

def forward(self, flag=True):
), sth like distortion_loss_from_sparse_pixels (don't be afraid of long but self-explanatory variables). Also, is that really what it does? It seems like it's actually used to enable/disable the conflict loss? Does it work if you set flag to false?

Rename hard() to soft_to_hard() and rename the first argument to soft.

I think x is y and y is x in:

for x in range(image_size[0]):
for y in range(image_size[1]):
if mask_np[x,y]>0:
spixel_num = connected[int(x), int(y)]
labels.append( [mask_np[x,y]-1, spixel_num, x, y] ) # This is the class !

Make pip installable

See https://goodresearch.dev/setup.html#create-a-pip-installable-package-recommended and https://github.com/QVPR/Patch-NetVLAD/blob/main/setup.py

This will require a split of the code into re-useable modules, and a script that calls those modules. The code is already well organised so this shouldn't be much of a deal.

Once that's done, we can publish the package automatically to PyPi for everyone to use (https://github.com/QVPR/Patch-NetVLAD/blob/main/.github/workflows/python-publish.yml) and then create a conda package, too.

Add LICENSE

Make sure to adhere to code licenses that you use within the code

dataset

where is dataset.can't find it.Link has expired

Simplify conda environment & installation

  • All packages are available on conda-forge, so let's stick to just a single channel. pyg is called (py?)torch_geometric on conda-forge.
  • Installing dependencies can then be done in a one-liner: mamba create -n pointlabelspix python pytorch .... -c conda-forge
  • Loosen version requirements (e.g. there is no need to pin to cuda=11.3).

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.