Mask Generation
PyTorch
ONNX
Safetensors
sam2
video-object-segmentation
knowledge-distillation
Pablopigue commited on
Commit
f3387fa
·
verified ·
1 Parent(s): 2a25d2c

Upload sam2-lite

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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 ≈ a free Hugging Face CPU Space.
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