-
AI@home: Classifying images with Ollama – part six: More about locations – and even more prompt improvements
In part five, I started on injecting info about the place the picture was taken into my classifier. I did this by taking the embedded GPS coordinates from an image and translate this to something more meaningful. I had two ways to translate this: For the manual register, I also introcuded kinds, basically to decide…
-
AI@home: Classifying images with Ollama – part five: Places and more!
I am kind of still amazed how much information exists in mere 7 billion tokens in an ai model (my current preferred model, qwen2.5vl:7b). It is pretty good at understand what happens in an image, and it also is able to, all by itself, recognize places like the Corinth Canal, Eiffel Tower, the Kiomizu-Dera Temple…
-
AI@home: Classifying images with Ollama – part four: Face recognizion
Most modern systems have some form of face recognizion. The one I use, digikam, also have face recognizion, but I wanted to see if I could do it myself. Besides, wouldn’t it be cool if my ollama-generated descriptions could say «Vegard And Anita on a mountain top» instead of just «A man and a woman…
-
Docker networking part four – hacking around docker limitations.
After part 3, my setup was pretty good, and I was pretty sure I had come to the end of the road. There was just one thing that was bugging me: I needed to do NAT (MASQUERADE) in my firewall to get around the fact that docker routing table management is pretty limited. And with…
-
Partiprogram for Folkets Faktaparti.
(Dette innlegget ble skrevet i et øyeblikks frustrasjon over faktaresistente mennesker, særlig i kjølvannet av pandemien)