card: update from fastforks 1cbf1671
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
library_name: "fastforks"
|
| 3 |
pipeline_tag: "image-classification"
|
| 4 |
license: "other"
|
| 5 |
-
license_name: "
|
| 6 |
license_link: "https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE"
|
| 7 |
tags:
|
| 8 |
- "classification"
|
|
@@ -10,6 +10,7 @@ tags:
|
|
| 10 |
- "cuda"
|
| 11 |
- "pytorch"
|
| 12 |
- "fastforks"
|
|
|
|
| 13 |
---
|
| 14 |
# DenseNet (fastforks)
|
| 15 |
|
|
@@ -31,7 +32,7 @@ Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex di
|
|
| 31 |
|
| 32 |
## Licence
|
| 33 |
|
| 34 |
-
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause.
|
| 35 |
|
| 36 |
Code licence: BSD-3-Clause; the authors do not state a separate weights licence.
|
| 37 |
|
|
@@ -101,4 +102,4 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
|
|
| 101 |
|
| 102 |
`classification.load("densenet121.tv_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). 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.
|
| 103 |
|
| 104 |
-
<!-- staged from fastforks
|
|
|
|
| 2 |
library_name: "fastforks"
|
| 3 |
pipeline_tag: "image-classification"
|
| 4 |
license: "other"
|
| 5 |
+
license_name: "see-model-card"
|
| 6 |
license_link: "https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE"
|
| 7 |
tags:
|
| 8 |
- "classification"
|
|
|
|
| 10 |
- "cuda"
|
| 11 |
- "pytorch"
|
| 12 |
- "fastforks"
|
| 13 |
+
- "fastforks-card"
|
| 14 |
---
|
| 15 |
# DenseNet (fastforks)
|
| 16 |
|
|
|
|
| 32 |
|
| 33 |
## Licence
|
| 34 |
|
| 35 |
+
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause.
|
| 36 |
|
| 37 |
Code licence: BSD-3-Clause; the authors do not state a separate weights licence.
|
| 38 |
|
|
|
|
| 102 |
|
| 103 |
`classification.load("densenet121.tv_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). 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.
|
| 104 |
|
| 105 |
+
<!-- staged from fastforks 1cbf1671 (2026-11-15) -->
|