| > I tried and got the same outcome. Hm, I've tried it just now and got this: https://i.imgur.com/01MIEWD.png > Note: Wait more time to repost. Thanks, I'll remember that. I saw the previous post gaining no traction, and personally had fun testing the service with C / Audio code before, so I wanted it to stay afloat a bit longer, at least. > It's hard to believe that the system can detect that it's the "mean squared error". I won't be surprised ML model detected it, statistics-wise, associating "Tensorflow" and "mean" with "mean squared error".
Happened when I fed it CLIP-related code. > Don't you want to use the average instead of "0.5"? It was tested on the real-life code, looks like a Colab I have previously recommended. https://colab.research.google.com/drive/1WWo2L7ZMdslbZyOg-pq... |
