✳flâneur — a map of the web's best reading

Mark Tenenholtz on X: "I spent 400+ hours training computer vision models last year on my road to Kaggle Master. I recently revisited my code and notes from those competitions and distilled them into a repeatable process that anyone can follow. 7 steps to train any computer vision model 🧵" / X

twitter.com · 79 words · saved by 1 readers

To view keyboard shortcuts, press question mark View keyboard shortcuts Messages Home Explore Notifications Messages Grok Lists Bookmarks Communities Premium Profile More Post Vyom Pathak @stancosmos01 Post See new posts Conversation Mark Tenenholtz @marktenenholtz I spent 400+ hours training computer vision models last year on my road to Kaggle Master. I recently revisited my code and notes from those competitions and distilled them into a repeatable process that anyone can follow. 7 steps to train any computer vision model 5:00 AM · Feb 16, 2022 18 376 1.9K 1.1K Post your reply Reply Mark Tenenholtz @marktenenholtz · Feb 16, 2022 1. Immerse yourself in the data The great part about image data is that it's as visual as it gets. You should scroll through as many images as possible and try to find patterns. The best models come from those who have spent hours on this, not minutes. 1 5 86 Mark Tenenholtz @marktenenholtz · Feb 16, 2022 You can use Jupyter widget to make this faste

Mark Tenenholtz @marktenenholtz I spent 400+ hours training computer vision models last year on my road to Kaggle Master. I recently revisited my code and notes from those competitions and distilled them into a repeatable process that anyone can follow. 7 steps to train any computer vision model 🧵 1:00 PM · Feb 16, 2022 16 0 1 6 340 0 3 4 0 1.8K 0 1 . 8 K 1.1K 0 1 . 1 K Read 16 replies

Explore this link on the map →

related reading