Open xiaoyangbenjiance opened 7 months ago
can you provide the text embedding generation .
Refer to the official implementation of CLIP for the text embedding generation. For the foreground classes, I recommend using "a photo of a [classname]" as a prompt to generate the category embedding. For the background category, we can directly input "background" into the text encoder of CLIP to get the text embedding.
can you provide the text embedding generation .