|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- maskformer |
|
|
- instance-segmentation |
|
|
- abnormal-detection |
|
|
datasets: |
|
|
- custom |
|
|
--- |
|
|
|
|
|
# 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 |
|
|
import torch |
|
|
from PIL import Image |
|
|
import requests |
|
|
from transformers import MaskFormerImageProcessor |
|
|
|
|
|
# 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) |
|
|
``` |
|
|
|
