Instructions to use bukuroo/EdgeTAM-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use bukuroo/EdgeTAM-ONNX with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(bukuroo/EdgeTAM-ONNX) 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(bukuroo/EdgeTAM-ONNX) 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- onnx
|
| 5 |
+
- segmentation
|
| 6 |
+
- sam2
|
| 7 |
+
- ezonnx
|
| 8 |
+
---
|
| 9 |
+
### EdgeTAM
|
| 10 |
+
ONNX models for inference with [EZONNX](https://github.com/ikeboo/ezonnx)
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
- Model type:
|
| 14 |
+
Segmentation
|
| 15 |
+
|
| 16 |
+
- Official repository:
|
| 17 |
+
[EdgeTAM](https://github.com/facebookresearch/EdgeTAM)
|
| 18 |
+
- Setup
|
| 19 |
+
```
|
| 20 |
+
pip install git+https://github.com/ikeboo/ezonnx.git
|
| 21 |
+
```
|
| 22 |
+
- Usage
|
| 23 |
+
```python
|
| 24 |
+
from ezonnx import EdgeTAM, visualize_images
|
| 25 |
+
tam = EdgeTAM()
|
| 26 |
+
res = tam.set_image("images/cat.jpg")
|
| 27 |
+
# add point with positive or not and its label
|
| 28 |
+
res = tam.set_point((240, 180), True, 1)
|
| 29 |
+
res = tam.set_point((50,50), True, 2)
|
| 30 |
+
res = tam.set_point((400,50), True, 2)
|
| 31 |
+
res = tam.set_point((150, 330), True, 3)
|
| 32 |
+
visualize_images("Masked Image",res.visualized_img)
|
| 33 |
+
```
|