Instructions to use Pablopigue/sam2-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use Pablopigue/sam2-lite with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("Pablopigue/sam2-lite") 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("Pablopigue/sam2-lite") 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
Upload sam2-lite
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ DAVIS 2017 val (30 videos, semi-supervised, J&F), per-frame latency of the full
|
|
| 26 |
| CPU 2 threads (ms/frame) | 4949 | 2270 | 398 |
|
| 27 |
| Model size, fp32 (MB) | 149 | 74 | 74 |
|
| 28 |
|
| 29 |
-
sam2-lite-mobile is the same weights at a 576×576 input; it was measured in a different session from the other latency numbers (~10 % run-to-run variation). 2 CPU threads
|
| 30 |
|
| 31 |
### ONNX Runtime encoder
|
| 32 |
|
|
|
|
| 26 |
| CPU 2 threads (ms/frame) | 4949 | 2270 | 398 |
|
| 27 |
| Model size, fp32 (MB) | 149 | 74 | 74 |
|
| 28 |
|
| 29 |
+
sam2-lite-mobile is the same weights at a 576×576 input; it was measured in a different session from the other latency numbers (~10 % run-to-run variation). 2 CPU threads = a modest 2-core CPU.
|
| 30 |
|
| 31 |
### ONNX Runtime encoder
|
| 32 |
|