darknet VS pytorch_nsfw_model

This reminds me of the resume for the guy who made darknet https://pjreddie.com/darknet/

Love the darknet (also made by him) github. Like what is this?

I don’t know, the OG author seemed pretty lax on its use based on the license.

In that case you're sure to enjoy this one.

Literally the first google link dude… https://github.com/pjreddie/darknet

Election of tools: you should define if you are going to use machine/deep learning methods or classical approaches such as the Viola-Jones algorithm. I will recommend you to use ML/DL with TensorFlow (Object Detection API) or Darknet (YOLO).

It's interesting. I've not tested the model on anything too risque, but again, with the well known Baywatch intro as a frame of reference, wide angle group shots of the whole cast in their swimsuits, is fine. A close up of any single cast member in the famous red swimsuit, will invariably trigger the model. Male or female.

In the blog, I suggest this could be the result of an uncultured data set, which is one part of it. Or perhaps the dataset was fine, and this is pushing the hard limit of what ResNet50 can do (the off the shelf model I use for this is a ResNet50 extension).

Some of the anomalous results are amusing. One day, I passed through a video of a female violinist in concert, and the model flagged every close up of her as NSFW! Just those closeups. Wide shots, and closeups of other musicians were absolutely fine.

Again some of that might be down to me (clucky code, very low NSFW threshold). And I suspect the model I used was itself a PoC (https://github.com/emiliantolo/pytorch_nsfw_model). But it does make you wonder how the bigger labs with critical products like Palantir handle doubts like this.