Hi how about Search Score What are your thoughts about it? will it represent the accuracy of the information taken from the DB which relates to the query?
Great demo on the basics of image search! Thx! I do have some follow up questions: 1. Looks like the label is single-class (i.e. bird, jelly fish, dog). In the embedding-creation step, how is multi-class picture being handled? For example, if a picture has both a woman and a dog, would there be multiple labels (or perhaps a label is a list of classes)? Would squeeze net able to handle this situation? 2. Similarly, in the matching stage, would it be able to handle multiple labels? 3. Or in general, does it require a pre-processing stage to dissect the images into multiple objects, and feed each object into detection algorithm? Thx
Was fun until more errors than I could be bothered to debug. Deprecated functions, missing parameters, mislabeled parameters, then eventually the batch upsert issue that stopped me.
Data scientists need to start using the word “complicated” more often lol. Watched this whole video waiting for when complex valued vectors would be used.
wish this went into some of the high level of how those indices worked. I mean, the whole crux and selling point of your company is that this is the new hotness but it's much too hard for the average joe to manage themselves so we should trust your service. Give us a taste of just how difficult that is and the heuristics involved in swapping and selecting different algos. That was I can say, wow that sounds like a huge cluster f, let me just use a managed service instead
Always good to hear from the boss. REALLY helpful presentation. LOTS of insights! Thank you
we are witnessing an amazing moment in the history of humanity
here for the history
+1
+1
Noice 👍
+1
+1
Hi how about Search Score What are your thoughts about it? will it represent the accuracy of the information taken from the DB which relates to the query?
Is there a 'Northwind' database example I can play with to help understand vector db's?
Now I know 10X'S more about this than I did before I watched this video. Thanks !
Great demo on the basics of image search! Thx! I do have some follow up questions:
1. Looks like the label is single-class (i.e. bird, jelly fish, dog). In the embedding-creation step, how is multi-class picture being handled? For example, if a picture has both a woman and a dog, would there be multiple labels (or perhaps a label is a list of classes)? Would squeeze net able to handle this situation?
2. Similarly, in the matching stage, would it be able to handle multiple labels?
3. Or in general, does it require a pre-processing stage to dissect the images into multiple objects, and feed each object into detection algorithm? Thx
Probably shouldn't say "Complex" in the title/thumbnail since this isn't about complex numbers.
"Complicated" or "involved" or "interesting" maybe
Was fun until more errors than I could be bothered to debug.
Deprecated functions, missing parameters, mislabeled parameters, then eventually the batch upsert issue that stopped me.
Same here. Closed colab out of frustration.
Data scientists need to start using the word “complicated” more often lol.
Watched this whole video waiting for when complex valued vectors would be used.
Thank you for warning me. I'm going to stop watching now, was only interested in learning something about vector math.
Thx
wish this went into some of the high level of how those indices worked. I mean, the whole crux and selling point of your company is that this is the new hotness but it's much too hard for the average joe to manage themselves so we should trust your service. Give us a taste of just how difficult that is and the heuristics involved in swapping and selecting different algos. That was I can say, wow that sounds like a huge cluster f, let me just use a managed service instead
awesome presentation
What is this pinecone? For dummies please 😅
the possibilities are limitless with vector data
Great, thanks
very helpful thank you
Great!
Developers developers developers developers
Early bird!!
Gets the ladies!
Not first. But im here
NIce
🗯️