Mask2former Swin Base IN21k Coco Instance

🚀 Mask2Former

The Mask2Former model is trained on COCO instance segmentation (base-sized IN21k version, Swin backbone). It offers a unified approach for various image segmentation tasks.

🚀 Quick Start

The Mask2Former model is designed to handle instance, semantic, and panoptic segmentation using a single paradigm. It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and initially released in this repository.

Disclaimer: The team releasing Mask2Former did not write a model card for this model, so this model card has been written by the Hugging Face team.

✨ Features

• Unified Paradigm: Addresses instance, semantic, and panoptic segmentation by predicting a set of masks and corresponding labels, treating all three tasks as instance segmentation.
• Performance and Efficiency: Outperforms the previous SOTA, MaskFormer, in both performance and efficiency through several key improvements:
  • Replaces the pixel decoder with a more advanced multi - scale deformable attention Transformer.
  • Adopts a Transformer decoder with masked attention to boost performance without additional computation.
  • Improves training efficiency by calculating the loss on subsampled points instead of whole masks.

📚 Documentation

Intended uses & limitations

You can use this particular checkpoint for instance segmentation. Check the model hub to find other fine - tuned versions for tasks that interest you.

How to use

Here is how to use this model:

import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation


# load Mask2Former fine-tuned on COCO instance segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-base-IN21k-coco-instance")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-base-IN21k-coco-instance")

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

with torch.no_grad():
    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 processor for postprocessing
result = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
predicted_instance_map = result["segmentation"]

For more code examples, refer to the documentation.

📄 License

License: other