🔒 why is my network learning slow?

[novel ridge]

code: https://paste.pythondiscord.com/JY7A
im training on the mnist data set according to this tutorial
the code is the same with minor changes to how the shape is stored (in the example w and b are sepearate i made it be shape and by default the zip of the 2)
changes to some var names
added annotation
made it run in python 3 instead of 2

it is supposed to start at or at least aproach 90% accuracy but it starts at 50-60% and stays there
why? (the values are from tests but even the original setting dont preform well)

to be real i got how it works but all i know of the matrix algebra is what sizes are compatible for the dot product bc i had to search that for debugging

[earnest oar]

@novel ridge

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.

[novel ridge]

why is my network not learning ?

[earnest oar]

@novel ridge

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.