Show newer

The second last layer was set to relu which messed everything up.

Show thread

Lmao, re-running an neural network training thing I did a month ago and it's no longer able to train a working model. Not even sure what changed 🤷

tips for folks getting started.

Don't use the system-level python as that can update and break dependencies. E.g. Arch uses 3.13 if you update and Tensorflow can't go above 3.12.

Use pyenv to do version management per project. github.com/pyenv/pyenv

Don't install pip dependencies globally. Use virtualenv to set up dependencies per project. virtualenv.pypa.io/

Python versioning is rough out of the box and these tips can save you some pain.

The appeal of machine learning to me is how clean the actual structure of models can be once you split it up in the right layers.

A lot of "application" code is a tangled web of dependencies and small independent or coupled bits of state that you need to coordinate in bizarre ways to account for the difficulty of state management in distributed systems.

ML on the other hand needs maths knowledge but the blocks fit together in a nice clean linear way of input to output.

youtube.com/watch?v=0VLAoVGf_7

Friendly reminder for those looking for a new , Agregore has built in UBlock origin ad blocking and doesn't track you or sell your data.

In manual memory management, the garbage collects YOU.

Looks like the emails used to register for fediforum have either been leaked or scraped or something because I've been getting spam on the one I created just for the event. 😿

Hard to find time to become transhuman while I gotta do my tasks. Luckily humans on average have a decent lifespan to get stuff done in.

Don't forget to eat your clocks this weekend. Completing the Sisyphusian cycle of how time consumes us.

A/B testing with zero user consent or disclosure is messed up. It's gross how tech people treat users like fodder with little care for their agency.

Updating my code to the latest version of

Hopefully the route instability stuff will be fixed now!

Fascinating practical networking research that exposes the gap between networking theory & real-world implementations. Valuable for security researchers, network engineers, and anyone building custom network protocols. github.com/Hawzen/hdp

"Thank you for screaming at the void. Your scream is important to us. All our customer service associates are currently assisting other screamers. Please wait and a representative will be with you shortly."

"Pour crier en Français, s'il vous plaît criez deux"

Show older
Mauvestodon

Escape ship from centralized social media run by Mauve.