You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your excellent work! When I was testing, why is it that for different texts, such as "strawberries", "plates", they have different text_token, but the text_embedding output through CLIP is exactly the same? This results in different text input, but the results of the count are exactly the same.
The text was updated successfully, but these errors were encountered:
Thank for your creative work. I reproduce the same result as @wangyutian73 said, would you please show me why and what can be gained from CLIP text prompt?
Thank you for your excellent work! When I was testing, why is it that for different texts, such as "strawberries", "plates", they have different text_token, but the text_embedding output through CLIP is exactly the same? This results in different text input, but the results of the count are exactly the same.
The text was updated successfully, but these errors were encountered: