license: apache-2.0
tags:
- vision
- image-segmentation
datasets:
- ade-20k
MaskFormer
MaskFormer model trained on ADE20k semantic segmentation (large-sized version, Swin backbone). It 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.
Model description
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.
Intended uses & limitations
You can use this particular checkpoint for semantic segmentation. See the model hub to look for other fine-tuned versions on a task that interests you.
How to use
Here is how to use this model:
>>> from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
>>> from PIL import Image
>>> import requests
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-base-ade")
>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-base-ade")
>>> 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
>>> predicted_semantic_map = feature_extractor.post_process_semantic_segmentation(outputs)[0]
For more code examples, we refer to the documentation.