Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Comparison to Zooniverse, track users? #10

Open
bw4sz opened this issue Nov 25, 2019 · 4 comments
Open

Comparison to Zooniverse, track users? #10

bw4sz opened this issue Nov 25, 2019 · 4 comments

Comments

@bw4sz
Copy link

bw4sz commented Nov 25, 2019

This looks like a great tool! Well done.

We'd be interested in setting up an instance for Tree Detection (also a AI4earth project). Couple quick questions as I scan the repo.

Does the workflow track users? Can be useful for scoring annotator quality.

I like the integrated model training, looks attractive. In general, how should I think about this tool versus Zooniverse? Where to use one versus another. They've got a nice front end builder, but this has better backend active learning? Is that the general idea?

@agentmorris if you've got feedback too.

@bkellenb
Copy link
Collaborator

Hi!

Thank you for your interest and kind words! I would be happy to help out for your use case, if needed.
The current model does not support user tracking, but we are actively implementing this functionality in the upcoming major release. We will keep you posted about progress on this front.

The main difference to Zooniverse is indeed the Active Learning and model support. Also, our software is significantly leaner, and perhaps more targeted towards wildlife conservation (which was the starting point for developing it in the first place).

@bw4sz
Copy link
Author

bw4sz commented Nov 27, 2019

Solid. Pencil us in for a week's worth of work maybe in a few weeks. Let me know if I can be useful as a test user.

In terms of functionality I can imagine a few interesting aspects of our use case.

One other area of interest for us would be the ability to overlap multiple layers and have a toggle on/off. We have RGB images as well as coregistered LiDAR/hyperspectral images which we can show as a .tif. I am happy to fork the repo and work a bit to help too.

http://tree.westus.cloudapp.azure.com/shiny/

@bw4sz
Copy link
Author

bw4sz commented Nov 28, 2019

Should I wait to play around until the major release, or will the workflow be similar enough that I can get the hang of it?

@bkellenb
Copy link
Collaborator

Most of the workflow will be the same; the new version will mainly have a lot of added functionality to it.
You can have a look at an early stage of the new version here. It is under active development and not everything is working fine yet, but the basic functionality is the same.

In the future, we will replace the main branch with this one. Users running the current version and wanting to upgrade can do so by cloning the new version and migrating the database with the provided script.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants