Keypoint Detection
Transformers
PyTorch
Safetensors
superpoint
feature-extraction
vision
image-matching
Instructions to use magic-leap-community/superpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use magic-leap-community/superpoint with Transformers:
# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("magic-leap-community/superpoint") model = AutoModel.from_pretrained("magic-leap-community/superpoint") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SuperPointModel" | |
| ], | |
| "border_removal_distance": 4, | |
| "decoder_hidden_size": 256, | |
| "descriptor_decoder_dim": 256, | |
| "encoder_hidden_sizes": [ | |
| 64, | |
| 64, | |
| 128, | |
| 128 | |
| ], | |
| "initializer_range": 0.02, | |
| "keypoint_decoder_dim": 65, | |
| "keypoint_threshold": 0.005, | |
| "max_keypoints": -1, | |
| "model_type": "superpoint", | |
| "nms_radius": 4, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.0.dev0" | |
| } | |