Maskformer Swin Small Coco

🚀 MaskFormer

The MaskFormer model is trained on COCO panoptic segmentation (small - sized version, Swin backbone). It offers a unified approach for instance, semantic, and panoptic segmentation.

🚀 Quick Start

The MaskFormer model trained on COCO panoptic segmentation can be used for semantic segmentation tasks. You can find other fine - tuned versions on the model hub.

✨ Features

• Unified Paradigm: MaskFormer addresses instance, semantic, and panoptic segmentation using the same approach, by predicting a set of masks and corresponding labels.
• Visual Representation: You can visualize the model architecture through the following image:

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
from PIL import Image
import requests

# load MaskFormer fine-tuned on COCO panoptic segmentation
feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-small-coco")
model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-small-coco")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = feature_extractor(images=image, return_tensors="pt")

outputs = model(**inputs)
# model predicts class_queries_logits of shape `(batch_size, num_queries)`
# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits

# you can pass them to feature_extractor for postprocessing
result = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_panoptic_map = result["segmentation"]

For more code examples, refer to the documentation.

📚 Documentation

The MaskFormer model was introduced in the paper Per - Pixel Classification is Not All You Need for Semantic Segmentation and first released in this repository.

Disclaimer: The team releasing MaskFormer did not write a model card for this model, so this model card has been written by the Hugging Face team.

🔧 Technical Details

MaskFormer addresses instance, semantic, and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation.

📄 License

The license for this model is "other".