Mask Generation
ONNX
sam2
segment-anything
sam-med3d
microscopy
medical-imaging
interactive-segmentation
feature-extraction
pixel-classification
dinov2
vgg16
cellpose
micro-sam
Instructions to use voxide/voxide-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use voxide/voxide-models with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("voxide/voxide-models") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained("voxide/voxide-models") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>) # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
README: one statement of the per-file licences
Browse files
README.md
CHANGED
|
@@ -77,12 +77,10 @@ and so are these exports.
|
|
| 77 |
- **SAM 2.1** © Meta Platforms, Inc. — <https://github.com/facebookresearch/sam2>
|
| 78 |
- **SAM-Med3D** © the SAM-Med3D authors — <https://github.com/uni-medical/SAM-Med3D>
|
| 79 |
|
| 80 |
-
The network-feature models carry their own licences
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
(`license: other`): Apache-2.0, BSD-3-Clause or CC-BY-4.0, as listed for each file, with the
|
| 85 |
-
attribution each licence requires under [Licences and attribution](#licences-and-attribution).
|
| 86 |
|
| 87 |
If you use these models in published work, please cite the original papers:
|
| 88 |
|
|
|
|
| 77 |
- **SAM 2.1** © Meta Platforms, Inc. — <https://github.com/facebookresearch/sam2>
|
| 78 |
- **SAM-Med3D** © the SAM-Med3D authors — <https://github.com/uni-medical/SAM-Med3D>
|
| 79 |
|
| 80 |
+
The network-feature models carry their own licences, so this card's licence is per file
|
| 81 |
+
(`license: other`): Apache-2.0, BSD-3-Clause or CC-BY-4.0 (micro-sam's ViT-T encoder), as listed for
|
| 82 |
+
each file in [their section](#network-feature-models-pixel-classifier), with the attribution each
|
| 83 |
+
licence requires under [Licences and attribution](#licences-and-attribution).
|
|
|
|
|
|
|
| 84 |
|
| 85 |
If you use these models in published work, please cite the original papers:
|
| 86 |
|