Hot take: deep learning is slowly going to make large swaths of remote sensing research irrelevant. It takes a PhD to understand sensors and physics and ecology enough to write an algorithm to deduce crop type. It takes a weekend to train a deep learning model to do it.
-
-
No more foolish than explaining in detail why a model fails on a certain type of test data with no remedy available. The mistakes DL algorithms make are often instructive and are straightforward (although laborious) to address with more training datahttps://www.azavea.com/blog/2019/02/13/accuracy-is-in-the-eye-of-the-beholder/ …
-
Can DL tell you how to improve your next generation sensor?

- Näytä vastaukset
Uusi keskustelu -
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.


