Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://huggingface.co/shi-labs/oneformer_ade20k_swin_large below:

Website Navigation

• 🎗️

  diegoccx/OneFormerMentoria

• 👀

  lichih/LaDeco

• 🧠

  lolout1/NeuroNest

• 👀

  skallewag/SegMatch

• shi-labs/OneFormer

• 🎗️

  Laihiujin/OneFormer

• 🎗️

  wJFFF/OneFormer

• 😻

  yang01/shi-labs-oneformer_ade20k_swin_large

• 🚀

  hpwang/VistaDream

• TOS
• Privacy
• About
• Jobs
• Models
• Datasets
• Spaces
• Pricing
• Docs

shi-labs/oneformer_ade20k_swin_large · Hugging Face

OneFormer model trained on the ADE20k dataset (large-sized version, Swin backbone). It was introduced in the paper OneFormer: One Transformer to Rule Universal Image Segmentation by Jain et al. and first released in this repository.

OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model.

You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the model hub to look for other fine-tuned versions on a different dataset.

Here is how to use this model:

from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
from PIL import Image
import requests
url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg"
image = Image.open(requests.get(url, stream=True).raw)


processor = OneFormerProcessor.from_pretrained("shi-labs/oneformer_ade20k_swin_large")
model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_swin_large")


semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
semantic_outputs = model(**semantic_inputs)

predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]


instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
instance_outputs = model(**instance_inputs)

predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]


panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
panoptic_outputs = model(**panoptic_inputs)

predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]

For more examples, please refer to the documentation.

@article{jain2022oneformer,
      title={{OneFormer: One Transformer to Rule Universal Image Segmentation}},
      author={Jitesh Jain and Jiachen Li and MangTik Chiu and Ali Hassani and Nikita Orlov and Humphrey Shi},
      journal={arXiv}, 
      year={2022}
    }

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4