ask for help

[ilikeyouyoulikeme]

Outline & Motivation

from PIL import Image
from lang_sam import LangSAM

model = LangSAM()
image_pil = Image.open("./assets/car.jpeg").convert("RGB")
text_prompt = "all wheel."
results = model.predict([image_pil], [text_prompt]) Hello, I used this code and it indicated that all wheels were processed, but in the end only one mask was output—why is that?

Pitch

No response

Additional context

No response

[luca-medeiros]

@ilikeyouyoulikeme your prompting style is somehow not the expected.
Instead of 'asking' for "all wheel." you should just state the object you want to mask, "wheel."
As this is not some language model, text prompt such as 'only wheels' or 'the ones the in back' etc might not properly work. Stick to simple straightforward labels instead.