This model is intended for universal segmentation tasks to identify the specified region types in images. Mask2Former supports instance, semantic, and panoptic segmentation.

How to use in CVAT

In CVAT, go to Models → Add Model
Select Hugging Face as the source
Enter the model path: "{your-username}/mask2former-segmentation"
Configure the appropriate mapping for your labels

Usage in Python

python

from transformers import Mask2FormerForUniversalSegmentation, Mask2FormerImageProcessor
import torch
from PIL import Image

# Load model and processor
model = Mask2FormerForUniversalSegmentation.from_pretrained("{your-username}/mask2former-segmentation")
processor = Mask2FormerImageProcessor.from_pretrained("{your-username}/mask2former-segmentation")

# Prepare image
image = Image.open("your_image.jpg")
inputs = processor(images=image, return_tensors="pt")

# Make prediction
with torch.no_grad():
    outputs = model(**inputs)

# Process outputs for visualization
# (see example code in model repository)

Dreamy0/mask2former-segmentation-all-data

Mask2Former for Segmentation

Model description

Intended uses & limitations

How to use in CVAT

Usage in Python

Dreamy0/
mask2former-segmentation-all-data