21–30 of 34 posts
I wanted this meme : https://knowyourmeme.com/memes/for-five-minutes "Shrek 5 minutes" None of the results is Shrek. Ok... may be something simpler: "Shrek" Same...
Searching on google for old english meme immediately pulls up a bunch of Joseph Ducreux memes which is exactly what I was looking for. But this one does not return any. Are they not present in the dataset or could it be because of the way the algorithm works? Interested to hear some details on this setup.
Since I helped build it, I'll explain :) This example is quick and dirty, indexing only about 1,000 images from a dataset we pulled from Kaggle. So if results suck, that's due to either the meme you search for not being in the dataset, or it just didn't get indexed in the random batch of 1,000.
This is a text to image search using deep learning, vector similarity search. Ask me anything.
Earlier quoted context omitted.
Since I helped build it, I'll explain :) This example is quick and dirty, indexing only about 1,000 images from a dataset we pulled from Kaggle. So if results suck, that's due to either the meme you search for not being in the dataset, or it just didn't get indexed in the random batch of 1,000.
I see. 1000 is probably a bit less to showcase a search concept but this is definitely a very interesting problem.
Earlier quoted context omitted.
Is this comment on the wrong post?
I guess this comment was meant for https://notegarden.web.app/ on https://news.ycombinator.com/item?id=28400446
This is a text to image search using deep learning, vector similarity search. Ask me anything.
What in your system is doing the text-to-vector encoding, and how did you train it?
The framework is Jina (https://github.com/jina-ai/jina/) so it's pretty high-level. You can see the indexing/search Flow on lines 37-52 of https://github.com/alexcg1/jina-meme-search-example/blob/mai...
Earlier quoted context omitted.
I see. 1000 is probably a bit less to showcase a search concept but this is definitely a very interesting problem.
I'm indexing 10k as we speak. At least for text. Indexing 10k images will take a bit longer.
Also swapped out the model
This is a text to image search using deep learning, vector similarity search. Ask me anything.
What in your system is doing the text-to-vector encoding, and how did you train it?
For image search we use Big Transfer Encoder (https://github.com/jina-ai/executors/tree/main/jinahub/encod...) but may switch to CLIPImage encoder at some point
This is a text to image search using deep learning, vector similarity search. Ask me anything.
not useful for me, since I usually want a meme to match a mood or theme