Log in | Register
« first < prev Page 1 of 12 next > last »
6 days ago - context

Do you have any tips for frameworks / libraries / general approaches to get started with something like this? I do have more than 0 knowledge of ML but I am not very experienced in it.

Any application of ML to GWM seems to me like it would involve heavy image processing (and probably not apply to videos).

Agree that videos would be more tricky, but for single images once trained, using a deep model is not very expensive. I would estimate that a regular GeForce 1060-70 would be able to parse at least 60 images per sec. Training the model is expensive, but it can be done offline once in a while

As for libraries, i would go with pytorch which is very intuitive. This link is a good starting point: transfer_learning_tutorial. html (search it on pytorch website, i can't post links)

The given example is for single label classification, but it is easy to adapt it to multiple labels (the tags). If we find a platform to collaborate on, i'd be willing to help with code.

Chainer
6 days ago - context

Hi, great feature!

It doesn't always actually pick "similar images", but that's expected as it has no notion of content. I think some deep learning could do a lot here, I have many years of experience and would be happy to help.

To give an idea, it would be possible to train a model on a relevant task (e.g. correctly assigning tags) and then use it to extract features from the images. Once you have the image features it would be trivial to simply pick the nearest neighbors in feature space. If the model was trained properly the nearest images should be semantically and visually similar (depending on what task was used to train the model).

Do you have any tips for frameworks / libraries / general approaches to get started with something like this? I do have more than 0 knowledge of ML but I am not very experienced in it.

Any application of ML to GWM seems to me like it would involve heavy image processing (and probably not apply to videos).

Apr 05, 2021 - edited Apr 05, 2021 - context

It doesn't always actually pick "similar images"

At first I was also expecting visually similar images. Maybe "Users also liked/favorited" would be more self explanatory, but I don't mind the current text.

To give an idea, it would be possible to train a model on a relevant task (e.g. correctly assigning tags) and then use it to extract features from the images. Once you have the image features it would be trivial to simply pick the nearest neighbors in feature space. If the model was trained properly the nearest images should be semantically and visually similar (depending on what task was used to train the model).

I was also thinking about playing with something like this to suggest tags when I upload something.

Apr 05, 2021 - context

Hi, great feature!

It doesn't always actually pick "similar images", but that's expected as it has no notion of content. I think some deep learning could do a lot here, I have many years of experience and would be happy to help.

To give an idea, it would be possible to train a model on a relevant task (e.g. correctly assigning tags) and then use it to extract features from the images. Once you have the image features it would be trivial to simply pick the nearest neighbors in feature space. If the model was trained properly the nearest images should be semantically and visually similar (depending on what task was used to train the model).

Chainer
Apr 04, 2021 - context

Did you base you approach on an existing algorithm somewhere?

No, I just messed around with various aspects of it until it was working well.

tamarok
Apr 03, 2021 - context

Did you base you approach on an existing algorithm somewhere?

Apr 03, 2021 - context

This is great. Each subject picture matched a lot of others with similar muscle tone. I searched a group pic and it came up with some other group pics. Abs pics focus on abs, biceps on biceps, etc. Awesome feature!

Apr 03, 2021 - context

Algorithm works great, knocked the ball out of the park, great stuff 👌

Apr 03, 2021 - context

this is a feature i was hoping this site would implement!

Apr 03, 2021 - context

another very pleasantly surprised visitor here :)

Apr 03, 2021 - context

I like this feature alot it made me find amazing pics in a short time.

Chainer
Apr 02, 2021 - context

Glad this is catching on!

Out of curiosity, does GWM use a NoSQL / Graph database or are you able to do this with a classical relational database? Do you cache the pairings or is it always recomputed?

Relational DB (Postgres). The pairings are cached for 10 mins after they are loaded by someone. I didn't think longer caching would really make a difference; I don't want to cache results for newer pics because they might change, and as for older pics, there are too many for caching to make a meaningful difference.

Seems a bit slow though?

Yes, it does take 5-10 seconds to generate results for a single image.

Does this also return images with similar tags?

It does not take tags into account at all.

Apr 01, 2021 - context

Good Idea

Apr 01, 2021 - context

This new feature is amazing! Works very well. It’s the feature nobody knew they wanted but now can’t live without lol well done!!!

Apr 01, 2021 - context

That feature is awesome, thank you!

Apr 01, 2021 - context

Love it Chainer! Does this also return images with similar tags? It says "users who liked X Also liked Y" but some of the images don't seem to use the same tags as the source image

Apr 01, 2021 - context

I like this a lot, and it does seem to work. Seems a bit slow though?

Apr 01, 2021 - context

Thoroughly approved.

Apr 01, 2021 - edited Apr 01, 2021 - context

This is a very creative way of combining human pattern recognition and dopamine response with statistical overlaps in order to return image results that users will find appealing.

Who needs machine learning when you can just hijack users' own content preference behaviours to generate ultra-specific recommendations?

This appears to be very effective, great work everyone involved!

Apr 01, 2021 - context

Man, quite some skilled programmers working on this site. Awesome, seems to work pretty nicely. Out of curiosity, does GWM use a NoSQL / Graph database or are you able to do this with a classical relational database? Do you cache the pairings or is it always recomputed?

Apr 01, 2021 - context

Good

Apr 01, 2021 - context

Agree with asqwert. This certainly is superior to hidden gems. This really improves the site immensely. Thanks Chainer

Apr 01, 2021 - context

Agree !

Apr 01, 2021 - edited Apr 01, 2021 - context

Great work, one of your best ideas yet.

I saw pics and vids that are new to me even though I've visited the site for years already. Hope it really takes off, I feel like this is where we'll see more hidden gems

Apr 01, 2021 - context

Well done Chainer. I hope it can last.

« first < prev Page 1 of 12 next > last »