I feel it's a good idea for those building native clients for Lemmy implement projects like these to run offline inferences on feed content for the time-being. To cover content that are not marked NSFW and should be.

What does everyone think, about enforcing further censorship, especially in open-source clients, on the client side as long as it pertains to this type of content?

Edit:

There's also this, but it takes a bit more effort to implement properly. And provides a hash that can be used for reporting needs. https://github.com/AsuharietYgvar/AppleNeuralHash2ONNX .

Python package MIT: https://pypi.org/project/opennsfw-standalone/

you are viewing a single comment's thread
view the rest of the comments

[–] pexavc@lemmy.world 1 points 1 year ago* (last edited 1 year ago) (1 children)

good point, but was just providing samples. I myself would gladly create a simple package for inferencing using a properly licensed model file.

Edit: Linked a MIT keras model for instance, also thanks for the tip didn't know about GPL / BSD relationship

[–] wildbus8979@sh.itjust.works 5 points 1 year ago (1 children)

That person is wrong about the BSD-3 license, so it's not a very good "tip".

[–] pexavc@lemmy.world 2 points 1 year ago

oh i see, just saw your other comment as well