# argus-torch Argus (103M) multi-task perception model on a frozen EUPE-ViT-B backbone for COCO detection, ImageNet classification, ADE20K semantic segmentation and indoor metric depth. **Details** - Model name: `argus-torch` - Model source: [https://huggingface.co/phanerozoic/argus](https://huggingface.co/phanerozoic/argus) - Model author: Charles Norton (phanerozoic) - Model license: FAIR Noncommercial Research License - Model size: 393.22 MB - Exposes embeddings? yes - Tags: `detection, classification, segmentation, depth, embeddings, torch, transformer` **Requirements** - Packages: `torch, torchvision>=0.16, transformers` - CPU support - yes - GPU support - yes **Example usage** ```python import fiftyone as fo import fiftyone.zoo as foz dataset = foz.load_zoo_dataset( "coco-2017", split="validation", dataset_name=fo.get_default_dataset_name(), max_samples=50, shuffle=True, ) model = foz.load_zoo_model("argus-torch") dataset.apply_model(model, label_field="predictions") session = fo.launch_app(dataset) ```