🔒 Handling Varied Input Data and Masking Issues in Model Training

[muted aspen]

Hello everyone,

I'm working on training a model where the input data varies significantly. Sometimes, I provide arrays that are 90% zeros, while other times, the arrays have large values throughout. The model needs to handle both cases.
The main issue comes when I mask certain layers (which are sometimes already mainly zeros) and try to use them to make decisions. This causes errors during training. Does anyone know a good way to handle situations like this?

Thanks in advance

[versed cradle]

@muted aspen

Python help channel opened

Remember to:

• Ask your Python question, not if you can ask or if there's an expert who can help.
• Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
• Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.

[versed cradle]

@muted aspen

Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.