Comparison of image moderation APIs

It would be nice if someone could compare these commercially available APIs with Yahoo&#x27;s open_nsfw model in terms of accuracy: <a href="https:&#x2F;&#x2F;github.com&#x2F;yahoo&#x2F;open_nsfw" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;yahoo&#x2F;open_nsfw</a><p>I&#x27;m currently building an API wrapper around it and running it on a Hetzner server with a GTX 1080 - prediction takes about 0.25 seconds and while I haven&#x27;t optimised it for parallel execution, I think it should be able to handle at least +10 images&#x2F;sec comfortably. I&#x27;m also testing video moderation by using ffmpeg to slice the video into screenshots and predicting the min&#x2F;avg&#x2F;high scores.<p>Moderating 25 million explicit images using Google Cloud Vision would cost around $19,500&#x2F;mo vs €99&#x2F;mo on Hetzner.

I really hope you haven’t picked a dataset that features only women nudity, but sample images suggest otherwise: <a href="https:&#x2F;&#x2F;dataturks.com&#x2F;projects&#x2F;Mohan&#x2F;NSFW(Nudity%20Detection)%20Image%20Moderation%20Datatset" rel="nofollow">https:&#x2F;&#x2F;dataturks.com&#x2F;projects&#x2F;Mohan&#x2F;NSFW(Nudity%20Detection...</a>

I tried out various image labeling APIs, including Google Vision (Safe Search) for exactly this use case (moderation). I was honestly astonished at the pricing of these APIs. Google is somewhere at 1.50€ for 1000 images which is - imo - very expensive. I tried out the default models that come with Tensorflow but well, they are trained on scientific datasets which typically involve species and flowers - no luck there either. Any good tips for pre-trained models that solve this (for tensorflow)?

For those interested, PixLab let you analyze 50K images or video frames via its &#x2F;nsfw endpoint for $25. They charge $0.9 per 1000 requests after you reach this quota.<p><a href="https:&#x2F;&#x2F;pixlab.io&#x2F;cmd?id=nsfw" rel="nofollow">https:&#x2F;&#x2F;pixlab.io&#x2F;cmd?id=nsfw</a><p><a href="https:&#x2F;&#x2F;pixlab.io&#x2F;pricing" rel="nofollow">https:&#x2F;&#x2F;pixlab.io&#x2F;pricing</a>

what is the verdict? i been just scrolling down to see which is best and cant find any.

The sample images shown only feature white women. Is that a limitation of the dataset?

BTW we had a question in general to anyone who can help us, Does hosting such a dataset cause issues with SEO etc? Anything else we should be aware of?