---
license: apache-2.0
tags:
- maskformer
- instance-segmentation
- abnormal-detection
- image-segmentation
datasets:
- custom
pipeline_tag: image-segmentation
---

# MaskFormer for Normal/Abnormal Detection

This model is fine-tuned to detect and segment regions classified as either "Normal" or "Abnormal".

## Model description

This is a MaskFormer model fine-tuned on a custom dataset with polygon annotations in COCO format. It has two classes:
- Normal (ID: 0)
- Abnormal (ID: 1)

## Intended uses & limitations

This model is intended for instance segmentation tasks to identify normal and abnormal regions in images.

### How to use in CVAT

1. In CVAT, go to Models → Add Model
2. Select Hugging Face as the source
3. Enter the model path: "{your-username}/maskformer-abnormal-detection"
4. Configure the appropriate mapping for your labels (Normal and Abnormal)

### Usage in Python

```python
from transformers import MaskFormerForInstanceSegmentation, MaskFormerImageProcessor
import torch
from PIL import Image

# Load model and processor
model = MaskFormerForInstanceSegmentation.from_pretrained("{your-username}/maskformer-abnormal-detection")
processor = MaskFormerImageProcessor.from_pretrained("facebook/maskformer-swin-tiny-ade")

# 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)
```