#318: Measuring your ML impact with CodeCarbon

1:07:43
 
שתפו
 

Manage episode 293604939 series 2453836
על ידי Michael Kennedy and Michael Kennedy (@mkennedy) התגלה על ידי Player FM והקהילה שלנו - זכויות היוצרים שמורות למפרסם, לא ל-Player FM, והשמע מוזרם ישירות מהשרתים שלכם. הירשמו כדי לעקוב אחר עדכונים ב-Player FM, או הדביקו את כתובת העדכונים באפליקציות פודקאסט אחרות.
Machine learning has made huge advancements in the past couple of years. We now have ML models helping doctors catch disease early. Google is using ML to suggest traffic routes in their maps app that will lesson the amount of gasoline used in the trip. And many more examples. But there is a heavy cost for training machine learning models.
In this episode, you'll meet Victor Schmidt, Jonathan Wilson, and Boris Feld. They work on the CodeCarbon project together. This project offers a Python package and dashboarding tool to help you understand and minimize your ML model's environmental impact.
Links from the show
Guests
Victor Schmidt: @vict0rsch
Jonathan Wilson: haverford.edu
Boris Feld: @Lothiraldan
CodeCarbon project: codecarbon.io
MIT "5 Cars" Article: technologyreview.com
Green Future Choice Renewable Power in Portland: portlandgeneral.com
YouTube Live Stream: youtube.com
Episode transcripts: talkpython.fm

Sponsors
Square
Talk Python Training
AssemblyAI

334 פרקים