Instructions to use shi-labs/oneformer_ade20k_swin_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shi-labs/oneformer_ade20k_swin_large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="shi-labs/oneformer_ade20k_swin_large")# Load model directly from transformers import AutoProcessor, OneFormerForUniversalSegmentation processor = AutoProcessor.from_pretrained("shi-labs/oneformer_ade20k_swin_large") model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_swin_large", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f8dce50feb60133aaa106c3de3365b10509de6e330d656aba63df386339de589
- Size of remote file:
- 950 MB
- SHA256:
- f7ac095c28ddea4715e854a587eaee24327c624cbbdb17095bc9903c51930b16
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.