Tags: Busty datesSex chat op skype6911 sexAdult video sex indochristmas gift ideas for a guy you just started datingSkype live online video chat sex hotduggar girls dating 2016Okc chat free no registerNo register no credit card no email all free mobile phone sex cam number
I spent hours and hours swiping and collected about 10,000 images.One problem I noticed, was I swiped left for about 80% of the women. How would the BAE-TA miner know where her face was located?
Assuming an attractive female could get 20 matches in an hour, they do not have the time to go out with every man that messages them.
Obviously, they’ll pick the man they like most based off their profile initial message. However, in a sea of asian men, based purely on looks, my face wouldn’t pop out the page. The top investors earn a profit through informational advantages.
Now that I have the images, there are a number of problems. Passes it through a pre-trained Ada Boost model to detect the likely facial dimensions: The Algorithm failed to detect the faces for about 70% of the data. To model this data, I used a Convolutional Neural Network.
Because my classification problem was extremely detailed & subjective, I needed an algorithm that could extract a large enough amount of features to detect a difference between the girls that I liked and disliked.
While this doesn’t give me a competitive advantage in photos, this does give me an advantage in swipe volume & initial message.
Let’s dive into my methodology: To build the BAE-TA MINER, I needed to feed her A LOT of images.
As a result, I had about 8000 in dislikes and 2000 in the likes folder. Because I have such few images for the likes folder, the bae-ta miner won’t be well-trained to know what I like. To fix this problem, I searched google “attractive women” and permutations of that phrase. To solve this problem, I used a Haars Cascade Classifier Algorithm to extract the faces from images and then saved it.
Then I scraped these images off of Google and used these within my dataset. The Classifier, essentially uses multiple positive/negative rectangles.
The other day, while I sat on the toilet to take a *poop*, I whipped out my phone, opened up the king of all toilet apps: Tinder.
I clicked open the application and started the mindless swiping. Now that we have dating apps, everyone suddenly has access to exponentially more people to date compared to the pre-app era. The Bay Area also attracts uber-successful, smart men from all around the world.