|
--- |
|
license: other |
|
tags: |
|
- vision |
|
- image-segmentation |
|
datasets: |
|
- coco |
|
widget: |
|
- src: http://images.cocodataset.org/val2017/000000039769.jpg |
|
example_title: Cats |
|
- src: http://images.cocodataset.org/val2017/000000039770.jpg |
|
example_title: Castle |
|
--- |
|
|
|
# Mask2Former |
|
|
|
Mask2Former model trained on ADE20k semantic segmentation (large-sized version, Swin backbone). It was introduced in the paper [Masked-attention Mask Transformer for Universal Image Segmentation |
|
](https://arxiv.org/abs/2112.01527) and first released in [this repository](https://github.com/facebookresearch/Mask2Former/). |
|
|
|
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. |
|
|
|
## Model description |
|
|
|
Mask2Former 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. Mask2Former outperforms the previous SOTA, |
|
[MaskFormer](https://arxiv.org/abs/2107.06278) both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without |
|
without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks. |
|
|
|
 |
|
|
|
## Intended uses & limitations |
|
|
|
You can use this particular checkpoint for panoptic segmentation. See the [model hub](https://huggingface.co/models?search=mask2former) to look for other |
|
fine-tuned versions on a task that interests you. |
|
|
|
### How to use |
|
|
|
Here is how to use this model: |
|
|
|
```python |
|
import requests |
|
import torch |
|
from PIL import Image |
|
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation |
|
|
|
|
|
# load Mask2Former fine-tuned on ADE20k semantic segmentation |
|
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-ade-semantic") |
|
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-ade-semantic") |
|
|
|
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 |
|
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0] |
|
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs) |
|
``` |
|
|
|
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/mask2former). |
