facebook
/
maskformer-swin-large-coco
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Niels Rogge 2023-02-27 15:10:23 +00:00 committed by huggingface-web
parent 8c011b6777
commit 5f009df218
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -34,17 +34,17 @@ fine-tuned versions on a task that interests you.
Here is how to use this model: Here is how to use this model:
```python ```python
from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation from transformers import MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
from PIL import Image from PIL import Image
import requests import requests
# load MaskFormer fine-tuned on COCO panoptic segmentation # load MaskFormer fine-tuned on COCO panoptic segmentation
feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-large-coco") processor = MaskFormerImageProcessor.from_pretrained("facebook/maskformer-swin-large-coco")
model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-coco") model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-coco")
url = "http://images.cocodataset.org/val2017/000000039769.jpg" url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw) image = Image.open(requests.get(url, stream=True).raw)
inputs = feature_extractor(images=image, return_tensors="pt") inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs) outputs = model(**inputs)
# model predicts class_queries_logits of shape `(batch_size, num_queries)` # model predicts class_queries_logits of shape `(batch_size, num_queries)`
@ -52,8 +52,8 @@ outputs = model(**inputs)
class_queries_logits = outputs.class_queries_logits class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits masks_queries_logits = outputs.masks_queries_logits
# you can pass them to feature_extractor for postprocessing # you can pass them to processor for postprocessing
result = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0] result = processor.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) # we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_panoptic_map = result["segmentation"] predicted_panoptic_map = result["segmentation"]
``` ```