card: update from fastforks 1cbf1671
Browse files
README.md
CHANGED
|
@@ -9,6 +9,7 @@ tags:
|
|
| 9 |
- "cuda"
|
| 10 |
- "pytorch"
|
| 11 |
- "fastforks"
|
|
|
|
| 12 |
---
|
| 13 |
# Segment Anything (SAM) (fastforks)
|
| 14 |
|
|
@@ -32,7 +33,7 @@ Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex di
|
|
| 32 |
|
| 33 |
## Licence
|
| 34 |
|
| 35 |
-
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0.
|
| 36 |
|
| 37 |
Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.
|
| 38 |
|
|
@@ -120,4 +121,4 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
|
|
| 120 |
|
| 121 |
`promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.
|
| 122 |
|
| 123 |
-
<!-- staged from fastforks
|
|
|
|
| 9 |
- "cuda"
|
| 10 |
- "pytorch"
|
| 11 |
- "fastforks"
|
| 12 |
+
- "fastforks-card"
|
| 13 |
---
|
| 14 |
# Segment Anything (SAM) (fastforks)
|
| 15 |
|
|
|
|
| 33 |
|
| 34 |
## Licence
|
| 35 |
|
| 36 |
+
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Licence files: `LICENSE`.
|
| 37 |
|
| 38 |
Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.
|
| 39 |
|
|
|
|
| 121 |
|
| 122 |
`promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.
|
| 123 |
|
| 124 |
+
<!-- staged from fastforks 1cbf1671 (2026-11-15) -->
|