Closed N0rbi closed 2 years ago
Hello @N0rbi, Thank you very much for your interest in contributing. You can find the whole dataset here: https://drive.google.com/drive/folders/1VP8d5Rle5NWI-30EeXDdZ-mcO3Q3CSVI
A guide how to train the model can be found here: https://developer.apple.com/documentation/createml/creating-an-image-classifier-model Its a straightforward process.
In order to collect trainings data there is a functionality implemented to store the screenshots in the correct folder by pressing number keys: https://github.com/andresavic/AmongKey/blob/cf393332aab1b98b61de3fd0df9b2dbe2579b067/AmongKey/AmongKeyApp.swift#L189
Let me know if you have any further questions.
Best, Andre
Thank you for guiding me through. This helped me a lot in starting out.
This should be useful to the problem mentioned in #28 but since chat is not a game breaking feature, I think it would be a minor improvement (or at least for my use case).
Hi @andresavic could you please create a brief guide / wiki on how you created the AmongUsClassifier.mlmodel file? I'm interested in the input dataset and the expected output of the model. I would like to make a PR with the updated UI of among us.
Thank you