Instructions to use square-zero-labs/sam2.1-tiny-video-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use square-zero-labs/sam2.1-tiny-video-onnx with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(square-zero-labs/sam2.1-tiny-video-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(square-zero-labs/sam2.1-tiny-video-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
mask_decoder: replace rank-5 GatherElements with one-hot Mul+ReduceSum selection (GatherElements generates invalid WGSL in ort-web WebGPU EP). Bit-identical outputs verified vs previous decoder.
Browse files- onnx/mask_decoder.onnx +2 -2
onnx/mask_decoder.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0461896de3db00936fe1643506f129d71cb6d5d2ae15754811756b7ea1b070c6
|
| 3 |
+
size 17794355
|