Without going into detail, our model outputs the coordinates of the html element... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		johndamaia on Aug 6, 2019 \| parent \| context \| favorite \| on: Show HN: I trained a deep learning model to build ... Without going into detail, our model outputs the coordinates of the html elements it recognize. We are taking a visual approach to the problem.

xcubic on Aug 7, 2019 | [–]

I imagine you do some kind of image recognition on the sketch files and then do the code generation.

attilakun on Aug 6, 2019 | [–]

Did you use a recurrent neural network? And/or reinforcement learning?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact